An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation
Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-co...
Ausführliche Beschreibung
Autor*in: |
Senthooran, Ilankaikone [verfasserIn] |
---|
Format: |
Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2018 |
---|
Schlagwörter: |
---|
Anmerkung: |
© Springer Science+Business Media, LLC, part of Springer Nature 2018 |
---|
Übergeordnetes Werk: |
Enthalten in: Autonomous robots - Springer US, 1994, 43(2018), 5 vom: 20. Aug., Seite 1257-1270 |
---|---|
Übergeordnetes Werk: |
volume:43 ; year:2018 ; number:5 ; day:20 ; month:08 ; pages:1257-1270 |
Links: |
---|
DOI / URN: |
10.1007/s10514-018-9801-y |
---|
Katalog-ID: |
OLC2052752994 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | OLC2052752994 | ||
003 | DE-627 | ||
005 | 20230502215408.0 | ||
007 | tu | ||
008 | 200820s2018 xx ||||| 00| ||eng c | ||
024 | 7 | |a 10.1007/s10514-018-9801-y |2 doi | |
035 | |a (DE-627)OLC2052752994 | ||
035 | |a (DE-He213)s10514-018-9801-y-p | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 620 |q VZ |
100 | 1 | |a Senthooran, Ilankaikone |e verfasserin |0 (orcid)0000-0001-6207-3780 |4 aut | |
245 | 1 | 0 | |a An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation |
264 | 1 | |c 2018 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
338 | |a Band |b nc |2 rdacarrier | ||
500 | |a © Springer Science+Business Media, LLC, part of Springer Nature 2018 | ||
520 | |a Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times. | ||
650 | 4 | |a Pose estimation | |
650 | 4 | |a Visual odometry | |
650 | 4 | |a RANSAC | |
650 | 4 | |a RGB-D | |
650 | 4 | |a MAV | |
650 | 4 | |a Limited processing | |
700 | 1 | |a Murshed, Manzur |4 aut | |
700 | 1 | |a Barca, Jan Carlo |4 aut | |
700 | 1 | |a Kamruzzaman, Joarder |4 aut | |
700 | 1 | |a Chung, Hoam |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Autonomous robots |d Springer US, 1994 |g 43(2018), 5 vom: 20. Aug., Seite 1257-1270 |w (DE-627)186689446 |w (DE-600)1252189-9 |w (DE-576)053002199 |x 0929-5593 |7 nnns |
773 | 1 | 8 | |g volume:43 |g year:2018 |g number:5 |g day:20 |g month:08 |g pages:1257-1270 |
856 | 4 | 1 | |u https://doi.org/10.1007/s10514-018-9801-y |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_OLC | ||
912 | |a SSG-OLC-TEC | ||
912 | |a GBV_ILN_70 | ||
951 | |a AR | ||
952 | |d 43 |j 2018 |e 5 |b 20 |c 08 |h 1257-1270 |
author_variant |
i s is m m mm j c b jc jcb j k jk h c hc |
---|---|
matchkey_str |
article:09295593:2018----::nfiinrnahpteieautouigufcetttsi |
hierarchy_sort_str |
2018 |
publishDate |
2018 |
allfields |
10.1007/s10514-018-9801-y doi (DE-627)OLC2052752994 (DE-He213)s10514-018-9801-y-p DE-627 ger DE-627 rakwb eng 620 VZ Senthooran, Ilankaikone verfasserin (orcid)0000-0001-6207-3780 aut An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times. Pose estimation Visual odometry RANSAC RGB-D MAV Limited processing Murshed, Manzur aut Barca, Jan Carlo aut Kamruzzaman, Joarder aut Chung, Hoam aut Enthalten in Autonomous robots Springer US, 1994 43(2018), 5 vom: 20. Aug., Seite 1257-1270 (DE-627)186689446 (DE-600)1252189-9 (DE-576)053002199 0929-5593 nnns volume:43 year:2018 number:5 day:20 month:08 pages:1257-1270 https://doi.org/10.1007/s10514-018-9801-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_70 AR 43 2018 5 20 08 1257-1270 |
spelling |
10.1007/s10514-018-9801-y doi (DE-627)OLC2052752994 (DE-He213)s10514-018-9801-y-p DE-627 ger DE-627 rakwb eng 620 VZ Senthooran, Ilankaikone verfasserin (orcid)0000-0001-6207-3780 aut An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times. Pose estimation Visual odometry RANSAC RGB-D MAV Limited processing Murshed, Manzur aut Barca, Jan Carlo aut Kamruzzaman, Joarder aut Chung, Hoam aut Enthalten in Autonomous robots Springer US, 1994 43(2018), 5 vom: 20. Aug., Seite 1257-1270 (DE-627)186689446 (DE-600)1252189-9 (DE-576)053002199 0929-5593 nnns volume:43 year:2018 number:5 day:20 month:08 pages:1257-1270 https://doi.org/10.1007/s10514-018-9801-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_70 AR 43 2018 5 20 08 1257-1270 |
allfields_unstemmed |
10.1007/s10514-018-9801-y doi (DE-627)OLC2052752994 (DE-He213)s10514-018-9801-y-p DE-627 ger DE-627 rakwb eng 620 VZ Senthooran, Ilankaikone verfasserin (orcid)0000-0001-6207-3780 aut An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times. Pose estimation Visual odometry RANSAC RGB-D MAV Limited processing Murshed, Manzur aut Barca, Jan Carlo aut Kamruzzaman, Joarder aut Chung, Hoam aut Enthalten in Autonomous robots Springer US, 1994 43(2018), 5 vom: 20. Aug., Seite 1257-1270 (DE-627)186689446 (DE-600)1252189-9 (DE-576)053002199 0929-5593 nnns volume:43 year:2018 number:5 day:20 month:08 pages:1257-1270 https://doi.org/10.1007/s10514-018-9801-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_70 AR 43 2018 5 20 08 1257-1270 |
allfieldsGer |
10.1007/s10514-018-9801-y doi (DE-627)OLC2052752994 (DE-He213)s10514-018-9801-y-p DE-627 ger DE-627 rakwb eng 620 VZ Senthooran, Ilankaikone verfasserin (orcid)0000-0001-6207-3780 aut An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times. Pose estimation Visual odometry RANSAC RGB-D MAV Limited processing Murshed, Manzur aut Barca, Jan Carlo aut Kamruzzaman, Joarder aut Chung, Hoam aut Enthalten in Autonomous robots Springer US, 1994 43(2018), 5 vom: 20. Aug., Seite 1257-1270 (DE-627)186689446 (DE-600)1252189-9 (DE-576)053002199 0929-5593 nnns volume:43 year:2018 number:5 day:20 month:08 pages:1257-1270 https://doi.org/10.1007/s10514-018-9801-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_70 AR 43 2018 5 20 08 1257-1270 |
allfieldsSound |
10.1007/s10514-018-9801-y doi (DE-627)OLC2052752994 (DE-He213)s10514-018-9801-y-p DE-627 ger DE-627 rakwb eng 620 VZ Senthooran, Ilankaikone verfasserin (orcid)0000-0001-6207-3780 aut An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation 2018 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times. Pose estimation Visual odometry RANSAC RGB-D MAV Limited processing Murshed, Manzur aut Barca, Jan Carlo aut Kamruzzaman, Joarder aut Chung, Hoam aut Enthalten in Autonomous robots Springer US, 1994 43(2018), 5 vom: 20. Aug., Seite 1257-1270 (DE-627)186689446 (DE-600)1252189-9 (DE-576)053002199 0929-5593 nnns volume:43 year:2018 number:5 day:20 month:08 pages:1257-1270 https://doi.org/10.1007/s10514-018-9801-y lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_70 AR 43 2018 5 20 08 1257-1270 |
language |
English |
source |
Enthalten in Autonomous robots 43(2018), 5 vom: 20. Aug., Seite 1257-1270 volume:43 year:2018 number:5 day:20 month:08 pages:1257-1270 |
sourceStr |
Enthalten in Autonomous robots 43(2018), 5 vom: 20. Aug., Seite 1257-1270 volume:43 year:2018 number:5 day:20 month:08 pages:1257-1270 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Pose estimation Visual odometry RANSAC RGB-D MAV Limited processing |
dewey-raw |
620 |
isfreeaccess_bool |
false |
container_title |
Autonomous robots |
authorswithroles_txt_mv |
Senthooran, Ilankaikone @@aut@@ Murshed, Manzur @@aut@@ Barca, Jan Carlo @@aut@@ Kamruzzaman, Joarder @@aut@@ Chung, Hoam @@aut@@ |
publishDateDaySort_date |
2018-08-20T00:00:00Z |
hierarchy_top_id |
186689446 |
dewey-sort |
3620 |
id |
OLC2052752994 |
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">OLC2052752994</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230502215408.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2018 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10514-018-9801-y</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2052752994</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10514-018-9801-y-p</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="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Senthooran, Ilankaikone</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-6207-3780</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2018</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="500" ind1=" " ind2=" "><subfield code="a">© Springer Science+Business Media, LLC, part of Springer Nature 2018</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pose estimation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visual odometry</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">RANSAC</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">RGB-D</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">MAV</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Limited processing</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Murshed, Manzur</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Barca, Jan Carlo</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kamruzzaman, Joarder</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chung, Hoam</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Autonomous robots</subfield><subfield code="d">Springer US, 1994</subfield><subfield code="g">43(2018), 5 vom: 20. Aug., Seite 1257-1270</subfield><subfield code="w">(DE-627)186689446</subfield><subfield code="w">(DE-600)1252189-9</subfield><subfield code="w">(DE-576)053002199</subfield><subfield code="x">0929-5593</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:43</subfield><subfield code="g">year:2018</subfield><subfield code="g">number:5</subfield><subfield code="g">day:20</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:1257-1270</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10514-018-9801-y</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</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-TEC</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">43</subfield><subfield code="j">2018</subfield><subfield code="e">5</subfield><subfield code="b">20</subfield><subfield code="c">08</subfield><subfield code="h">1257-1270</subfield></datafield></record></collection>
|
author |
Senthooran, Ilankaikone |
spellingShingle |
Senthooran, Ilankaikone ddc 620 misc Pose estimation misc Visual odometry misc RANSAC misc RGB-D misc MAV misc Limited processing An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation |
authorStr |
Senthooran, Ilankaikone |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)186689446 |
format |
Article |
dewey-ones |
620 - Engineering & allied operations |
delete_txt_mv |
keep |
author_role |
aut aut aut aut aut |
collection |
OLC |
remote_str |
false |
illustrated |
Not Illustrated |
issn |
0929-5593 |
topic_title |
620 VZ An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation Pose estimation Visual odometry RANSAC RGB-D MAV Limited processing |
topic |
ddc 620 misc Pose estimation misc Visual odometry misc RANSAC misc RGB-D misc MAV misc Limited processing |
topic_unstemmed |
ddc 620 misc Pose estimation misc Visual odometry misc RANSAC misc RGB-D misc MAV misc Limited processing |
topic_browse |
ddc 620 misc Pose estimation misc Visual odometry misc RANSAC misc RGB-D misc MAV misc Limited processing |
format_facet |
Aufsätze Gedruckte Aufsätze |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
nc |
hierarchy_parent_title |
Autonomous robots |
hierarchy_parent_id |
186689446 |
dewey-tens |
620 - Engineering |
hierarchy_top_title |
Autonomous robots |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)186689446 (DE-600)1252189-9 (DE-576)053002199 |
title |
An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation |
ctrlnum |
(DE-627)OLC2052752994 (DE-He213)s10514-018-9801-y-p |
title_full |
An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation |
author_sort |
Senthooran, Ilankaikone |
journal |
Autonomous robots |
journalStr |
Autonomous robots |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
600 - Technology |
recordtype |
marc |
publishDateSort |
2018 |
contenttype_str_mv |
txt |
container_start_page |
1257 |
author_browse |
Senthooran, Ilankaikone Murshed, Manzur Barca, Jan Carlo Kamruzzaman, Joarder Chung, Hoam |
container_volume |
43 |
class |
620 VZ |
format_se |
Aufsätze |
author-letter |
Senthooran, Ilankaikone |
doi_str_mv |
10.1007/s10514-018-9801-y |
normlink |
(ORCID)0000-0001-6207-3780 |
normlink_prefix_str_mv |
(orcid)0000-0001-6207-3780 |
dewey-full |
620 |
title_sort |
an efficient ransac hypothesis evaluation using sufficient statistics for rgb-d pose estimation |
title_auth |
An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation |
abstract |
Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times. © Springer Science+Business Media, LLC, part of Springer Nature 2018 |
abstractGer |
Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times. © Springer Science+Business Media, LLC, part of Springer Nature 2018 |
abstract_unstemmed |
Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times. © Springer Science+Business Media, LLC, part of Springer Nature 2018 |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-TEC GBV_ILN_70 |
container_issue |
5 |
title_short |
An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation |
url |
https://doi.org/10.1007/s10514-018-9801-y |
remote_bool |
false |
author2 |
Murshed, Manzur Barca, Jan Carlo Kamruzzaman, Joarder Chung, Hoam |
author2Str |
Murshed, Manzur Barca, Jan Carlo Kamruzzaman, Joarder Chung, Hoam |
ppnlink |
186689446 |
mediatype_str_mv |
n |
isOA_txt |
false |
hochschulschrift_bool |
false |
doi_str |
10.1007/s10514-018-9801-y |
up_date |
2024-07-03T16:24:23.366Z |
_version_ |
1803575742559158272 |
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">OLC2052752994</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230502215408.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200820s2018 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s10514-018-9801-y</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2052752994</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s10514-018-9801-y-p</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="q">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Senthooran, Ilankaikone</subfield><subfield code="e">verfasserin</subfield><subfield code="0">(orcid)0000-0001-6207-3780</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">An efficient RANSAC hypothesis evaluation using sufficient statistics for RGB-D pose estimation</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2018</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="500" ind1=" " ind2=" "><subfield code="a">© Springer Science+Business Media, LLC, part of Springer Nature 2018</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Achieving autonomous flight in GPS-denied environments begins with pose estimation in three-dimensional space, and this is much more challenging in an MAV in a swarm robotic system due to limited computational resources. In vision-based pose estimation, outlier detection is the most time-consuming step. This usually involves a RANSAC procedure using the reprojection-error method for hypothesis evaluation. Realignment-based hypothesis evaluation method is observed to be more accurate, but the considerably slower speed makes it unsuitable for robots with limited resources. We use sufficient statistics of least-squares minimisation to speed up this process. The additive nature of these sufficient statistics makes it possible to compute pose estimates in each evaluation by reusing previously computed statistics. Thus estimates need not be calculated from scratch each time. The proposed method is tested on standard RANSAC, Preemptive RANSAC and R-RANSAC using benchmark datasets. The results show that the use of sufficient statistics speeds up the outlier detection process with realignment hypothesis evaluation for all RANSAC variants, achieving an execution speed of up to 6.72 times.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Pose estimation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Visual odometry</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">RANSAC</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">RGB-D</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">MAV</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Limited processing</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Murshed, Manzur</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Barca, Jan Carlo</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Kamruzzaman, Joarder</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chung, Hoam</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Autonomous robots</subfield><subfield code="d">Springer US, 1994</subfield><subfield code="g">43(2018), 5 vom: 20. Aug., Seite 1257-1270</subfield><subfield code="w">(DE-627)186689446</subfield><subfield code="w">(DE-600)1252189-9</subfield><subfield code="w">(DE-576)053002199</subfield><subfield code="x">0929-5593</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:43</subfield><subfield code="g">year:2018</subfield><subfield code="g">number:5</subfield><subfield code="g">day:20</subfield><subfield code="g">month:08</subfield><subfield code="g">pages:1257-1270</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s10514-018-9801-y</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</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-TEC</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">43</subfield><subfield code="j">2018</subfield><subfield code="e">5</subfield><subfield code="b">20</subfield><subfield code="c">08</subfield><subfield code="h">1257-1270</subfield></datafield></record></collection>
|
score |
7.4005327 |