Automated extraction of building instances from dual-channel airborne LiDAR point clouds
With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-a...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Feng, Huifang [verfasserIn] |
|---|
| Format: |
E-Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2022transfer abstract |
|---|
| Schlagwörter: |
|---|
| Übergeordnetes Werk: |
Enthalten in: Network-wide assessment of ATM mechanisms using an agent-based model - Delgado, Luis ELSEVIER, 2021transfer abstract, s.l. |
|---|---|
| Übergeordnetes Werk: |
volume:114 ; year:2022 ; pages:0 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.jag.2022.103042 |
|---|
| Katalog-ID: |
ELV059401060 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | ELV059401060 | ||
| 003 | DE-627 | ||
| 005 | 20230626052823.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 221219s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.jag.2022.103042 |2 doi | |
| 028 | 5 | 2 | |a /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001958.pica |
| 035 | |a (DE-627)ELV059401060 | ||
| 035 | |a (ELSEVIER)S1569-8432(22)00230-8 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 610 |q VZ |
| 084 | |a 44.95 |2 bkl | ||
| 100 | 1 | |a Feng, Huifang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Automated extraction of building instances from dual-channel airborne LiDAR point clouds |
| 264 | 1 | |c 2022transfer abstract | |
| 336 | |a nicht spezifiziert |b zzz |2 rdacontent | ||
| 337 | |a nicht spezifiziert |b z |2 rdamedia | ||
| 338 | |a nicht spezifiziert |b zu |2 rdacarrier | ||
| 520 | |a With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. | ||
| 520 | |a With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. | ||
| 650 | 7 | |a Dual-channel airborne LiDAR |2 Elsevier | |
| 650 | 7 | |a Reorganization |2 Elsevier | |
| 650 | 7 | |a Point clouds |2 Elsevier | |
| 650 | 7 | |a Building instance extraction |2 Elsevier | |
| 650 | 7 | |a Preprocessing-free |2 Elsevier | |
| 700 | 1 | |a Chen, Yiping |4 oth | |
| 700 | 1 | |a Luo, Zhipeng |4 oth | |
| 700 | 1 | |a Sun, Wentao |4 oth | |
| 700 | 1 | |a Li, Wen |4 oth | |
| 700 | 1 | |a Li, Jonathan |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |n Elsevier |a Delgado, Luis ELSEVIER |t Network-wide assessment of ATM mechanisms using an agent-based model |d 2021transfer abstract |g s.l. |w (DE-627)ELV054625408 |
| 773 | 1 | 8 | |g volume:114 |g year:2022 |g pages:0 |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.jag.2022.103042 |3 Volltext |
| 912 | |a GBV_USEFLAG_U | ||
| 912 | |a GBV_ELV | ||
| 912 | |a SYSFLAG_U | ||
| 912 | |a SSG-OLC-PHA | ||
| 936 | b | k | |a 44.95 |j Augenheilkunde |q VZ |
| 951 | |a AR | ||
| 952 | |d 114 |j 2022 |h 0 | ||
| author_variant |
h f hf |
|---|---|
| matchkey_str |
fenghuifangchenyipingluozhipengsunwentao:2022----:uoaeetatoobidnisacsrmulhnear |
| hierarchy_sort_str |
2022transfer abstract |
| bklnumber |
44.95 |
| publishDate |
2022 |
| allfields |
10.1016/j.jag.2022.103042 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001958.pica (DE-627)ELV059401060 (ELSEVIER)S1569-8432(22)00230-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.95 bkl Feng, Huifang verfasserin aut Automated extraction of building instances from dual-channel airborne LiDAR point clouds 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free Elsevier Chen, Yiping oth Luo, Zhipeng oth Sun, Wentao oth Li, Wen oth Li, Jonathan oth Enthalten in Elsevier Delgado, Luis ELSEVIER Network-wide assessment of ATM mechanisms using an agent-based model 2021transfer abstract s.l. (DE-627)ELV054625408 volume:114 year:2022 pages:0 https://doi.org/10.1016/j.jag.2022.103042 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.95 Augenheilkunde VZ AR 114 2022 0 |
| spelling |
10.1016/j.jag.2022.103042 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001958.pica (DE-627)ELV059401060 (ELSEVIER)S1569-8432(22)00230-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.95 bkl Feng, Huifang verfasserin aut Automated extraction of building instances from dual-channel airborne LiDAR point clouds 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free Elsevier Chen, Yiping oth Luo, Zhipeng oth Sun, Wentao oth Li, Wen oth Li, Jonathan oth Enthalten in Elsevier Delgado, Luis ELSEVIER Network-wide assessment of ATM mechanisms using an agent-based model 2021transfer abstract s.l. (DE-627)ELV054625408 volume:114 year:2022 pages:0 https://doi.org/10.1016/j.jag.2022.103042 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.95 Augenheilkunde VZ AR 114 2022 0 |
| allfields_unstemmed |
10.1016/j.jag.2022.103042 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001958.pica (DE-627)ELV059401060 (ELSEVIER)S1569-8432(22)00230-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.95 bkl Feng, Huifang verfasserin aut Automated extraction of building instances from dual-channel airborne LiDAR point clouds 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free Elsevier Chen, Yiping oth Luo, Zhipeng oth Sun, Wentao oth Li, Wen oth Li, Jonathan oth Enthalten in Elsevier Delgado, Luis ELSEVIER Network-wide assessment of ATM mechanisms using an agent-based model 2021transfer abstract s.l. (DE-627)ELV054625408 volume:114 year:2022 pages:0 https://doi.org/10.1016/j.jag.2022.103042 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.95 Augenheilkunde VZ AR 114 2022 0 |
| allfieldsGer |
10.1016/j.jag.2022.103042 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001958.pica (DE-627)ELV059401060 (ELSEVIER)S1569-8432(22)00230-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.95 bkl Feng, Huifang verfasserin aut Automated extraction of building instances from dual-channel airborne LiDAR point clouds 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free Elsevier Chen, Yiping oth Luo, Zhipeng oth Sun, Wentao oth Li, Wen oth Li, Jonathan oth Enthalten in Elsevier Delgado, Luis ELSEVIER Network-wide assessment of ATM mechanisms using an agent-based model 2021transfer abstract s.l. (DE-627)ELV054625408 volume:114 year:2022 pages:0 https://doi.org/10.1016/j.jag.2022.103042 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.95 Augenheilkunde VZ AR 114 2022 0 |
| allfieldsSound |
10.1016/j.jag.2022.103042 doi /cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001958.pica (DE-627)ELV059401060 (ELSEVIER)S1569-8432(22)00230-8 DE-627 ger DE-627 rakwb eng 610 VZ 44.95 bkl Feng, Huifang verfasserin aut Automated extraction of building instances from dual-channel airborne LiDAR point clouds 2022transfer abstract nicht spezifiziert zzz rdacontent nicht spezifiziert z rdamedia nicht spezifiziert zu rdacarrier With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free Elsevier Chen, Yiping oth Luo, Zhipeng oth Sun, Wentao oth Li, Wen oth Li, Jonathan oth Enthalten in Elsevier Delgado, Luis ELSEVIER Network-wide assessment of ATM mechanisms using an agent-based model 2021transfer abstract s.l. (DE-627)ELV054625408 volume:114 year:2022 pages:0 https://doi.org/10.1016/j.jag.2022.103042 Volltext GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA 44.95 Augenheilkunde VZ AR 114 2022 0 |
| language |
English |
| source |
Enthalten in Network-wide assessment of ATM mechanisms using an agent-based model s.l. volume:114 year:2022 pages:0 |
| sourceStr |
Enthalten in Network-wide assessment of ATM mechanisms using an agent-based model s.l. volume:114 year:2022 pages:0 |
| format_phy_str_mv |
Article |
| bklname |
Augenheilkunde |
| institution |
findex.gbv.de |
| topic_facet |
Dual-channel airborne LiDAR Reorganization Point clouds Building instance extraction Preprocessing-free |
| dewey-raw |
610 |
| isfreeaccess_bool |
false |
| container_title |
Network-wide assessment of ATM mechanisms using an agent-based model |
| authorswithroles_txt_mv |
Feng, Huifang @@aut@@ Chen, Yiping @@oth@@ Luo, Zhipeng @@oth@@ Sun, Wentao @@oth@@ Li, Wen @@oth@@ Li, Jonathan @@oth@@ |
| publishDateDaySort_date |
2022-01-01T00:00:00Z |
| hierarchy_top_id |
ELV054625408 |
| dewey-sort |
3610 |
| id |
ELV059401060 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV059401060</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626052823.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221219s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.jag.2022.103042</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001958.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV059401060</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1569-8432(22)00230-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.95</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Feng, Huifang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Automated extraction of building instances from dual-channel airborne LiDAR point clouds</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Dual-channel airborne LiDAR</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Reorganization</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Point clouds</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Building instance extraction</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Preprocessing-free</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Yiping</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Luo, Zhipeng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Sun, Wentao</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Wen</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Jonathan</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Delgado, Luis ELSEVIER</subfield><subfield code="t">Network-wide assessment of ATM mechanisms using an agent-based model</subfield><subfield code="d">2021transfer abstract</subfield><subfield code="g">s.l.</subfield><subfield code="w">(DE-627)ELV054625408</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:114</subfield><subfield code="g">year:2022</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.jag.2022.103042</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.95</subfield><subfield code="j">Augenheilkunde</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">114</subfield><subfield code="j">2022</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| author |
Feng, Huifang |
| spellingShingle |
Feng, Huifang ddc 610 bkl 44.95 Elsevier Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free Automated extraction of building instances from dual-channel airborne LiDAR point clouds |
| authorStr |
Feng, Huifang |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)ELV054625408 |
| format |
electronic Article |
| dewey-ones |
610 - Medicine & health |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
elsevier |
| remote_str |
true |
| illustrated |
Not Illustrated |
| topic_title |
610 VZ 44.95 bkl Automated extraction of building instances from dual-channel airborne LiDAR point clouds Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free Elsevier |
| topic |
ddc 610 bkl 44.95 Elsevier Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free |
| topic_unstemmed |
ddc 610 bkl 44.95 Elsevier Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free |
| topic_browse |
ddc 610 bkl 44.95 Elsevier Dual-channel airborne LiDAR Elsevier Reorganization Elsevier Point clouds Elsevier Building instance extraction Elsevier Preprocessing-free |
| format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
zu |
| author2_variant |
y c yc z l zl w s ws w l wl j l jl |
| hierarchy_parent_title |
Network-wide assessment of ATM mechanisms using an agent-based model |
| hierarchy_parent_id |
ELV054625408 |
| dewey-tens |
610 - Medicine & health |
| hierarchy_top_title |
Network-wide assessment of ATM mechanisms using an agent-based model |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)ELV054625408 |
| title |
Automated extraction of building instances from dual-channel airborne LiDAR point clouds |
| ctrlnum |
(DE-627)ELV059401060 (ELSEVIER)S1569-8432(22)00230-8 |
| title_full |
Automated extraction of building instances from dual-channel airborne LiDAR point clouds |
| author_sort |
Feng, Huifang |
| journal |
Network-wide assessment of ATM mechanisms using an agent-based model |
| journalStr |
Network-wide assessment of ATM mechanisms using an agent-based model |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology |
| recordtype |
marc |
| publishDateSort |
2022 |
| contenttype_str_mv |
zzz |
| container_start_page |
0 |
| author_browse |
Feng, Huifang |
| container_volume |
114 |
| class |
610 VZ 44.95 bkl |
| format_se |
Elektronische Aufsätze |
| author-letter |
Feng, Huifang |
| doi_str_mv |
10.1016/j.jag.2022.103042 |
| dewey-full |
610 |
| title_sort |
automated extraction of building instances from dual-channel airborne lidar point clouds |
| title_auth |
Automated extraction of building instances from dual-channel airborne LiDAR point clouds |
| abstract |
With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. |
| abstractGer |
With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. |
| abstract_unstemmed |
With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively. |
| collection_details |
GBV_USEFLAG_U GBV_ELV SYSFLAG_U SSG-OLC-PHA |
| title_short |
Automated extraction of building instances from dual-channel airborne LiDAR point clouds |
| url |
https://doi.org/10.1016/j.jag.2022.103042 |
| remote_bool |
true |
| author2 |
Chen, Yiping Luo, Zhipeng Sun, Wentao Li, Wen Li, Jonathan |
| author2Str |
Chen, Yiping Luo, Zhipeng Sun, Wentao Li, Wen Li, Jonathan |
| ppnlink |
ELV054625408 |
| mediatype_str_mv |
z |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth oth oth |
| doi_str |
10.1016/j.jag.2022.103042 |
| up_date |
2024-07-06T21:53:14.564Z |
| _version_ |
1803868223113789440 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV059401060</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230626052823.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">221219s2022 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.jag.2022.103042</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">/cbs_pica/cbs_olc/import_discovery/elsevier/einzuspielen/GBV00000000001958.pica</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV059401060</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S1569-8432(22)00230-8</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">610</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">44.95</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Feng, Huifang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Automated extraction of building instances from dual-channel airborne LiDAR point clouds</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022transfer abstract</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">z</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zu</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively.</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">With the rapid development of Light Detection And Ranging (LiDAR) systems, the novel dual-channel airborne LiDAR systems have emerged to provide more complete and precise data than traditional scanners for building instance extraction since 2013. RIEGL VQ-1560i, launched in 2016, is a state-of-the-art dual-channel LiDAR system, which is capable of capturing dense points on building rooftops and façades simultaneously, due to the unique and innovative bidirectional scanning angle. Our proposed method is the first ever to use dual-channel airborne LiDAR data for subsequent point clouds processing. The main challenges of the new LiDAR data are significant amount of points, complex data structure and multi-class targets. We proposed a preprocessing-free building instance extraction method consisting of three steps, i.e., point cloud reorganization, rasterization, and constraint-based labeling for improving the extraction performance. First, point cloud reorganization, consisting of point distribution-based slicing, coarse 3D semantic segmentation, and top-down merging, is used to reorganize point cloud scene into interrelated point groups. This greatly reduces the processing difficulty and computational burden of complex structures while removing multiple classes of non-building points. Second, we rasterize the point groups into images to further reduce computational complexity while improving processing efficiency. Finally, we utilize the upper and lower structural relationship of buildings to label them and then remap into 3D buildings. Experimental results on six test point cloud scenes demonstrate the outstanding performance of the proposed preprocessing-free method. For semantic-level performance, our method achieves 95.36% in average recall and 93.59% in average F1-score. While for instance-level performance, our approach reaches 92.86% and 98.31% in quality on two public test scenes, respectively.</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Dual-channel airborne LiDAR</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Reorganization</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Point clouds</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Building instance extraction</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="650" ind1=" " ind2="7"><subfield code="a">Preprocessing-free</subfield><subfield code="2">Elsevier</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Yiping</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Luo, Zhipeng</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Sun, Wentao</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Wen</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Li, Jonathan</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="n">Elsevier</subfield><subfield code="a">Delgado, Luis ELSEVIER</subfield><subfield code="t">Network-wide assessment of ATM mechanisms using an agent-based model</subfield><subfield code="d">2021transfer abstract</subfield><subfield code="g">s.l.</subfield><subfield code="w">(DE-627)ELV054625408</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:114</subfield><subfield code="g">year:2022</subfield><subfield code="g">pages:0</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1016/j.jag.2022.103042</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">44.95</subfield><subfield code="j">Augenheilkunde</subfield><subfield code="q">VZ</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">114</subfield><subfield code="j">2022</subfield><subfield code="h">0</subfield></datafield></record></collection>
|
| score |
7.400154 |