DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features
Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Ye, Liang [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2017 |
|---|
| Schlagwörter: |
ground-based cloud image categorization |
|---|
| Übergeordnetes Werk: |
Enthalten in: IEEE transactions on geoscience and remote sensing - New York, NY : IEEE, 1964, 55(2017), 10, Seite 5729-5740 |
|---|---|
| Übergeordnetes Werk: |
volume:55 ; year:2017 ; number:10 ; pages:5729-5740 |
| Links: |
|---|
| DOI / URN: |
10.1109/TGRS.2017.2712809 |
|---|
| Katalog-ID: |
OLC1997226685 |
|---|
| LEADER | 01000caa a2200265 4500 | ||
|---|---|---|---|
| 001 | OLC1997226685 | ||
| 003 | DE-627 | ||
| 005 | 20230715072832.0 | ||
| 007 | tu | ||
| 008 | 171125s2017 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TGRS.2017.2712809 |2 doi | |
| 028 | 5 | 2 | |a PQ20171228 |
| 035 | |a (DE-627)OLC1997226685 | ||
| 035 | |a (DE-599)GBVOLC1997226685 | ||
| 035 | |a (PRQ)i655-53a8501e7f118c7df4e1914415c4903f47da248944697549cf4a121baeae38d00 | ||
| 035 | |a (KEY)0048677920170000055001005729deepcloudgroundbasedcloudimagecategorizationusingd | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 620 |a 550 |q DNB |
| 100 | 1 | |a Ye, Liang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features |
| 264 | 1 | |c 2017 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 520 | |a Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods. | ||
| 650 | 4 | |a Clouds | |
| 650 | 4 | |a ground-based cloud image categorization | |
| 650 | 4 | |a Encoding | |
| 650 | 4 | |a Convolutional neural network (CNN) | |
| 650 | 4 | |a Convolutional codes | |
| 650 | 4 | |a Visualization | |
| 650 | 4 | |a Meteorology | |
| 650 | 4 | |a Feature extraction | |
| 650 | 4 | |a pattern mining | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a Fisher vector (FV) | |
| 650 | 4 | |a Semantics | |
| 700 | 1 | |a Cao, Zhiguo |4 oth | |
| 700 | 1 | |a Xiao, Yang |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on geoscience and remote sensing |d New York, NY : IEEE, 1964 |g 55(2017), 10, Seite 5729-5740 |w (DE-627)129601667 |w (DE-600)241439-9 |w (DE-576)015095282 |x 0196-2892 |7 nnns |
| 773 | 1 | 8 | |g volume:55 |g year:2017 |g number:10 |g pages:5729-5740 |
| 856 | 4 | 1 | |u http://dx.doi.org/10.1109/TGRS.2017.2712809 |3 Volltext |
| 856 | 4 | 2 | |u http://ieeexplore.ieee.org/document/7964703 |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-ARC | ||
| 912 | |a SSG-OLC-TEC | ||
| 912 | |a SSG-OLC-GEO | ||
| 912 | |a SSG-OLC-FOR | ||
| 912 | |a SSG-OPC-GGO | ||
| 912 | |a SSG-OPC-GEO | ||
| 912 | |a GBV_ILN_70 | ||
| 951 | |a AR | ||
| 952 | |d 55 |j 2017 |e 10 |h 5729-5740 | ||
| author_variant |
l y ly |
|---|---|
| matchkey_str |
article:01962892:2017----::eplugonbsdluiaeaeoiainsndec |
| hierarchy_sort_str |
2017 |
| publishDate |
2017 |
| allfields |
10.1109/TGRS.2017.2712809 doi PQ20171228 (DE-627)OLC1997226685 (DE-599)GBVOLC1997226685 (PRQ)i655-53a8501e7f118c7df4e1914415c4903f47da248944697549cf4a121baeae38d00 (KEY)0048677920170000055001005729deepcloudgroundbasedcloudimagecategorizationusingd DE-627 ger DE-627 rakwb eng 620 550 DNB Ye, Liang verfasserin aut DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods. Clouds ground-based cloud image categorization Encoding Convolutional neural network (CNN) Convolutional codes Visualization Meteorology Feature extraction pattern mining deep learning Fisher vector (FV) Semantics Cao, Zhiguo oth Xiao, Yang oth Enthalten in IEEE transactions on geoscience and remote sensing New York, NY : IEEE, 1964 55(2017), 10, Seite 5729-5740 (DE-627)129601667 (DE-600)241439-9 (DE-576)015095282 0196-2892 nnns volume:55 year:2017 number:10 pages:5729-5740 http://dx.doi.org/10.1109/TGRS.2017.2712809 Volltext http://ieeexplore.ieee.org/document/7964703 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-ARC SSG-OLC-TEC SSG-OLC-GEO SSG-OLC-FOR SSG-OPC-GGO SSG-OPC-GEO GBV_ILN_70 AR 55 2017 10 5729-5740 |
| spelling |
10.1109/TGRS.2017.2712809 doi PQ20171228 (DE-627)OLC1997226685 (DE-599)GBVOLC1997226685 (PRQ)i655-53a8501e7f118c7df4e1914415c4903f47da248944697549cf4a121baeae38d00 (KEY)0048677920170000055001005729deepcloudgroundbasedcloudimagecategorizationusingd DE-627 ger DE-627 rakwb eng 620 550 DNB Ye, Liang verfasserin aut DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods. Clouds ground-based cloud image categorization Encoding Convolutional neural network (CNN) Convolutional codes Visualization Meteorology Feature extraction pattern mining deep learning Fisher vector (FV) Semantics Cao, Zhiguo oth Xiao, Yang oth Enthalten in IEEE transactions on geoscience and remote sensing New York, NY : IEEE, 1964 55(2017), 10, Seite 5729-5740 (DE-627)129601667 (DE-600)241439-9 (DE-576)015095282 0196-2892 nnns volume:55 year:2017 number:10 pages:5729-5740 http://dx.doi.org/10.1109/TGRS.2017.2712809 Volltext http://ieeexplore.ieee.org/document/7964703 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-ARC SSG-OLC-TEC SSG-OLC-GEO SSG-OLC-FOR SSG-OPC-GGO SSG-OPC-GEO GBV_ILN_70 AR 55 2017 10 5729-5740 |
| allfields_unstemmed |
10.1109/TGRS.2017.2712809 doi PQ20171228 (DE-627)OLC1997226685 (DE-599)GBVOLC1997226685 (PRQ)i655-53a8501e7f118c7df4e1914415c4903f47da248944697549cf4a121baeae38d00 (KEY)0048677920170000055001005729deepcloudgroundbasedcloudimagecategorizationusingd DE-627 ger DE-627 rakwb eng 620 550 DNB Ye, Liang verfasserin aut DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods. Clouds ground-based cloud image categorization Encoding Convolutional neural network (CNN) Convolutional codes Visualization Meteorology Feature extraction pattern mining deep learning Fisher vector (FV) Semantics Cao, Zhiguo oth Xiao, Yang oth Enthalten in IEEE transactions on geoscience and remote sensing New York, NY : IEEE, 1964 55(2017), 10, Seite 5729-5740 (DE-627)129601667 (DE-600)241439-9 (DE-576)015095282 0196-2892 nnns volume:55 year:2017 number:10 pages:5729-5740 http://dx.doi.org/10.1109/TGRS.2017.2712809 Volltext http://ieeexplore.ieee.org/document/7964703 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-ARC SSG-OLC-TEC SSG-OLC-GEO SSG-OLC-FOR SSG-OPC-GGO SSG-OPC-GEO GBV_ILN_70 AR 55 2017 10 5729-5740 |
| allfieldsGer |
10.1109/TGRS.2017.2712809 doi PQ20171228 (DE-627)OLC1997226685 (DE-599)GBVOLC1997226685 (PRQ)i655-53a8501e7f118c7df4e1914415c4903f47da248944697549cf4a121baeae38d00 (KEY)0048677920170000055001005729deepcloudgroundbasedcloudimagecategorizationusingd DE-627 ger DE-627 rakwb eng 620 550 DNB Ye, Liang verfasserin aut DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods. Clouds ground-based cloud image categorization Encoding Convolutional neural network (CNN) Convolutional codes Visualization Meteorology Feature extraction pattern mining deep learning Fisher vector (FV) Semantics Cao, Zhiguo oth Xiao, Yang oth Enthalten in IEEE transactions on geoscience and remote sensing New York, NY : IEEE, 1964 55(2017), 10, Seite 5729-5740 (DE-627)129601667 (DE-600)241439-9 (DE-576)015095282 0196-2892 nnns volume:55 year:2017 number:10 pages:5729-5740 http://dx.doi.org/10.1109/TGRS.2017.2712809 Volltext http://ieeexplore.ieee.org/document/7964703 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-ARC SSG-OLC-TEC SSG-OLC-GEO SSG-OLC-FOR SSG-OPC-GGO SSG-OPC-GEO GBV_ILN_70 AR 55 2017 10 5729-5740 |
| allfieldsSound |
10.1109/TGRS.2017.2712809 doi PQ20171228 (DE-627)OLC1997226685 (DE-599)GBVOLC1997226685 (PRQ)i655-53a8501e7f118c7df4e1914415c4903f47da248944697549cf4a121baeae38d00 (KEY)0048677920170000055001005729deepcloudgroundbasedcloudimagecategorizationusingd DE-627 ger DE-627 rakwb eng 620 550 DNB Ye, Liang verfasserin aut DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features 2017 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods. Clouds ground-based cloud image categorization Encoding Convolutional neural network (CNN) Convolutional codes Visualization Meteorology Feature extraction pattern mining deep learning Fisher vector (FV) Semantics Cao, Zhiguo oth Xiao, Yang oth Enthalten in IEEE transactions on geoscience and remote sensing New York, NY : IEEE, 1964 55(2017), 10, Seite 5729-5740 (DE-627)129601667 (DE-600)241439-9 (DE-576)015095282 0196-2892 nnns volume:55 year:2017 number:10 pages:5729-5740 http://dx.doi.org/10.1109/TGRS.2017.2712809 Volltext http://ieeexplore.ieee.org/document/7964703 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-ARC SSG-OLC-TEC SSG-OLC-GEO SSG-OLC-FOR SSG-OPC-GGO SSG-OPC-GEO GBV_ILN_70 AR 55 2017 10 5729-5740 |
| language |
English |
| source |
Enthalten in IEEE transactions on geoscience and remote sensing 55(2017), 10, Seite 5729-5740 volume:55 year:2017 number:10 pages:5729-5740 |
| sourceStr |
Enthalten in IEEE transactions on geoscience and remote sensing 55(2017), 10, Seite 5729-5740 volume:55 year:2017 number:10 pages:5729-5740 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| topic_facet |
Clouds ground-based cloud image categorization Encoding Convolutional neural network (CNN) Convolutional codes Visualization Meteorology Feature extraction pattern mining deep learning Fisher vector (FV) Semantics |
| dewey-raw |
620 |
| isfreeaccess_bool |
false |
| container_title |
IEEE transactions on geoscience and remote sensing |
| authorswithroles_txt_mv |
Ye, Liang @@aut@@ Cao, Zhiguo @@oth@@ Xiao, Yang @@oth@@ |
| publishDateDaySort_date |
2017-01-01T00:00:00Z |
| hierarchy_top_id |
129601667 |
| dewey-sort |
3620 |
| id |
OLC1997226685 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1997226685</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230715072832.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">171125s2017 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/TGRS.2017.2712809</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20171228</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1997226685</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1997226685</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)i655-53a8501e7f118c7df4e1914415c4903f47da248944697549cf4a121baeae38d00</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0048677920170000055001005729deepcloudgroundbasedcloudimagecategorizationusingd</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">620</subfield><subfield code="a">550</subfield><subfield code="q">DNB</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Ye, Liang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Clouds</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">ground-based cloud image categorization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Encoding</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional neural network (CNN)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional codes</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visualization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Meteorology</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Feature extraction</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">pattern mining</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fisher vector (FV)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Semantics</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Cao, Zhiguo</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xiao, Yang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">IEEE transactions on geoscience and remote sensing</subfield><subfield code="d">New York, NY : IEEE, 1964</subfield><subfield code="g">55(2017), 10, Seite 5729-5740</subfield><subfield code="w">(DE-627)129601667</subfield><subfield code="w">(DE-600)241439-9</subfield><subfield code="w">(DE-576)015095282</subfield><subfield code="x">0196-2892</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:55</subfield><subfield code="g">year:2017</subfield><subfield code="g">number:10</subfield><subfield code="g">pages:5729-5740</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1109/TGRS.2017.2712809</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://ieeexplore.ieee.org/document/7964703</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-ARC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-GEO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-FOR</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GEO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">55</subfield><subfield code="j">2017</subfield><subfield code="e">10</subfield><subfield code="h">5729-5740</subfield></datafield></record></collection>
|
| author |
Ye, Liang |
| spellingShingle |
Ye, Liang ddc 620 misc Clouds misc ground-based cloud image categorization misc Encoding misc Convolutional neural network (CNN) misc Convolutional codes misc Visualization misc Meteorology misc Feature extraction misc pattern mining misc deep learning misc Fisher vector (FV) misc Semantics DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features |
| authorStr |
Ye, Liang |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)129601667 |
| format |
Article |
| dewey-ones |
620 - Engineering & allied operations 550 - Earth sciences |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
0196-2892 |
| topic_title |
620 550 DNB DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features Clouds ground-based cloud image categorization Encoding Convolutional neural network (CNN) Convolutional codes Visualization Meteorology Feature extraction pattern mining deep learning Fisher vector (FV) Semantics |
| topic |
ddc 620 misc Clouds misc ground-based cloud image categorization misc Encoding misc Convolutional neural network (CNN) misc Convolutional codes misc Visualization misc Meteorology misc Feature extraction misc pattern mining misc deep learning misc Fisher vector (FV) misc Semantics |
| topic_unstemmed |
ddc 620 misc Clouds misc ground-based cloud image categorization misc Encoding misc Convolutional neural network (CNN) misc Convolutional codes misc Visualization misc Meteorology misc Feature extraction misc pattern mining misc deep learning misc Fisher vector (FV) misc Semantics |
| topic_browse |
ddc 620 misc Clouds misc ground-based cloud image categorization misc Encoding misc Convolutional neural network (CNN) misc Convolutional codes misc Visualization misc Meteorology misc Feature extraction misc pattern mining misc deep learning misc Fisher vector (FV) misc Semantics |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| author2_variant |
z c zc y x yx |
| hierarchy_parent_title |
IEEE transactions on geoscience and remote sensing |
| hierarchy_parent_id |
129601667 |
| dewey-tens |
620 - Engineering 550 - Earth sciences & geology |
| hierarchy_top_title |
IEEE transactions on geoscience and remote sensing |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)129601667 (DE-600)241439-9 (DE-576)015095282 |
| title |
DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features |
| ctrlnum |
(DE-627)OLC1997226685 (DE-599)GBVOLC1997226685 (PRQ)i655-53a8501e7f118c7df4e1914415c4903f47da248944697549cf4a121baeae38d00 (KEY)0048677920170000055001005729deepcloudgroundbasedcloudimagecategorizationusingd |
| title_full |
DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features |
| author_sort |
Ye, Liang |
| journal |
IEEE transactions on geoscience and remote sensing |
| journalStr |
IEEE transactions on geoscience and remote sensing |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
600 - Technology 500 - Science |
| recordtype |
marc |
| publishDateSort |
2017 |
| contenttype_str_mv |
txt |
| container_start_page |
5729 |
| author_browse |
Ye, Liang |
| container_volume |
55 |
| class |
620 550 DNB |
| format_se |
Aufsätze |
| author-letter |
Ye, Liang |
| doi_str_mv |
10.1109/TGRS.2017.2712809 |
| dewey-full |
620 550 |
| title_sort |
deepcloud: ground-based cloud image categorization using deep convolutional features |
| title_auth |
DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features |
| abstract |
Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods. |
| abstractGer |
Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods. |
| abstract_unstemmed |
Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-ARC SSG-OLC-TEC SSG-OLC-GEO SSG-OLC-FOR SSG-OPC-GGO SSG-OPC-GEO GBV_ILN_70 |
| container_issue |
10 |
| title_short |
DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features |
| url |
http://dx.doi.org/10.1109/TGRS.2017.2712809 http://ieeexplore.ieee.org/document/7964703 |
| remote_bool |
false |
| author2 |
Cao, Zhiguo Xiao, Yang |
| author2Str |
Cao, Zhiguo Xiao, Yang |
| ppnlink |
129601667 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth |
| doi_str |
10.1109/TGRS.2017.2712809 |
| up_date |
2024-07-04T02:27:39.931Z |
| _version_ |
1803613697404305408 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1997226685</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230715072832.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">171125s2017 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/TGRS.2017.2712809</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20171228</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1997226685</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1997226685</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)i655-53a8501e7f118c7df4e1914415c4903f47da248944697549cf4a121baeae38d00</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0048677920170000055001005729deepcloudgroundbasedcloudimagecategorizationusingd</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">620</subfield><subfield code="a">550</subfield><subfield code="q">DNB</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Ye, Liang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">DeepCloud: Ground-Based Cloud Image Categorization Using Deep Convolutional Features</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2017</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Accurate ground-based cloud image categorization is a critical but challenging task that has not been well addressed. One of the essential issues that affect the performance is to extract the representative visual features. Nearly all of the existing methods rely on the hand-crafted descriptors (e.g., local binary patterns, CENsus TRsansform hISTogram, and scale-invariant feature transform). Their limited discriminative power indeed leads to the unsatisfactory performance. To alleviate this, we propose "DeepCloud" as a novel cloud image feature extraction approach by resorting to the deep convolutional visual features. In the recent years, the deep convolutional neural network (CNN) has achieved the promising results in lots of computer vision and image understanding fields. Nevertheless, it has not been applied to cloud image classification yet. Thus, we actually pay the first effort to fill this blank. Since cloud image classification can be attributed to a multi-instance learning problem, simply employing the convolutional features within CNN cannot achieve the promising result. To address this, Fisher vector encoding is applied to executing the spatial feature aggregation and high-dimensional feature mapping on the raw deep convolutional features. Moreover, the hierarchical convolutional layers are used simultaneously to capture the fine textural characteristics and high-level semantic information in the unified manner. To further leverage the performance, a cloud pattern mining and selection method are also proposed. It targets at finding the discriminative local patterns to better distinguish the different kinds of clouds. The experiments on a challenging ground-based cloud image data set demonstrate the superiority of the proposition over the state-of-the-art methods.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Clouds</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">ground-based cloud image categorization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Encoding</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional neural network (CNN)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Convolutional codes</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visualization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Meteorology</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Feature extraction</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">pattern mining</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fisher vector (FV)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Semantics</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Cao, Zhiguo</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Xiao, Yang</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">IEEE transactions on geoscience and remote sensing</subfield><subfield code="d">New York, NY : IEEE, 1964</subfield><subfield code="g">55(2017), 10, Seite 5729-5740</subfield><subfield code="w">(DE-627)129601667</subfield><subfield code="w">(DE-600)241439-9</subfield><subfield code="w">(DE-576)015095282</subfield><subfield code="x">0196-2892</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:55</subfield><subfield code="g">year:2017</subfield><subfield code="g">number:10</subfield><subfield code="g">pages:5729-5740</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1109/TGRS.2017.2712809</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://ieeexplore.ieee.org/document/7964703</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-ARC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-TEC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-GEO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-FOR</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GGO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OPC-GEO</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">55</subfield><subfield code="j">2017</subfield><subfield code="e">10</subfield><subfield code="h">5729-5740</subfield></datafield></record></collection>
|
| score |
7.402135 |