Data-driven 3D Voxel Patterns for object category recognition

Despite the great progress achieved in recognizing objects as 2D bounding boxes in images, it is still very challenging to detect occluded objects and estimate the 3D properties of multiple objects from a single image. In this paper, we propose a novel object representation, 3D Voxel Pattern (3DVP),...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) s. 1903 - 1911
Hlavní autoři: Yu Xiang, Wongun Choi, Yuanqing Lin, Savarese, Silvio
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.06.2015
Témata:
Benchmark testing
Computer vision
Detectors
Image detection
Image segmentation
Object detection
Object recognition
Occlusion
Pattern recognition
Three dimensional
Two dimensional
ISSN:1063-6919, 1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Despite the great progress achieved in recognizing objects as 2D bounding boxes in images, it is still very challenging to detect occluded objects and estimate the 3D properties of multiple objects from a single image. In this paper, we propose a novel object representation, 3D Voxel Pattern (3DVP), that jointly encodes the key properties of objects including appearance, 3D shape, viewpoint, occlusion and truncation. We discover 3DVPs in a data-driven way, and train a bank of specialized detectors for a dictionary of 3DVPs. The 3DVP detectors are capable of detecting objects with specific visibility patterns and transferring the meta-data from the 3DVPs to the detected objects, such as 2D segmentation mask, 3D pose as well as occlusion or truncation boundaries. The transferred meta-data allows us to infer the occlusion relationship among objects, which in turn provides improved object recognition results. Experiments are conducted on the KITTI detection benchmark [17] and the outdoor-scene dataset [41]. We improve state-of-the-art results on car detection and pose estimation with notable margins (6% in difficult data of KITTI). We also verify the ability of our method in accurately segmenting objects from the background and localizing them in 3D.
AbstractList Despite the great progress achieved in recognizing objects as 2D bounding boxes in images, it is still very challenging to detect occluded objects and estimate the 3D properties of multiple objects from a single image. In this paper, we propose a novel object representation, 3D Voxel Pattern (3DVP), that jointly encodes the key properties of objects including appearance, 3D shape, viewpoint, occlusion and truncation. We discover 3DVPs in a data-driven way, and train a bank of specialized detectors for a dictionary of 3DVPs. The 3DVP detectors are capable of detecting objects with specific visibility patterns and transferring the meta-data from the 3DVPs to the detected objects, such as 2D segmentation mask, 3D pose as well as occlusion or truncation boundaries. The transferred meta-data allows us to infer the occlusion relationship among objects, which in turn provides improved object recognition results. Experiments are conducted on the KITTI detection benchmark [17] and the outdoor-scene dataset [41]. We improve state-of-the-art results on car detection and pose estimation with notable margins (6% in difficult data of KITTI). We also verify the ability of our method in accurately segmenting objects from the background and localizing them in 3D.
Author Savarese, Silvio
Yu Xiang
Yuanqing Lin
Wongun Choi
Author_xml – sequence: 1
  surname: Yu Xiang
  fullname: Yu Xiang
  email: yuxiang@umich.edu
  organization: Stanford Univ., Stanford, CA, USA
– sequence: 2
  surname: Wongun Choi
  fullname: Wongun Choi
  email: wongun@nec-labs.com
  organization: NEC Labs. America, Inc., CA, USA
– sequence: 3
  surname: Yuanqing Lin
  fullname: Yuanqing Lin
  email: ylin@nec-labs.com
  organization: NEC Labs. America, Inc., CA, USA
– sequence: 4
  givenname: Silvio
  surname: Savarese
  fullname: Savarese, Silvio
  email: ssilvio@stanford.edu
  organization: Stanford Univ., Stanford, CA, USA
BookMark eNpN0DtPwzAUBWCDikRb-gMQS0aWhGs78WNgQC0vqRIVgq6R495URmlcbBfRf0-ldmA6Z_h0hjMig973SMg1hYJS0HfT5eK9YECrQjKtFMAZGdFSSC60KOGcDCkIngtN9eBfvySTGF0DHEBpzWBI7mcmmXwV3A_2GZ9lS_-LXbYwKWHoY9b6kPnmC23KrEm49mGfBbR-3bvkfH9FLlrTRZycckw-nx4_pi_5_O35dfowzx0DlXKmtYSS0waUUZJa1pTCIlON1aiMEFaVtjVt09LK2LJd2YZWqjp4KRQqWfExuT3uboP_3mFM9cZFi11nevS7WFMpgXPGBD3QmyN1iFhvg9uYsK9PJ_E_42lZ4Q
ContentType Conference Proceeding
Journal Article
DBID 6IE
6IH
CBEJK
RIE
RIO
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/CVPR.2015.7298800
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Computer Science
EISBN 1467369640
9781467369640
EISSN 1063-6919
EndPage 1911
ExternalDocumentID 7298800
Genre orig-research
GroupedDBID 23M
29F
29O
6IE
6IH
6IK
ABDPE
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IPLJI
M43
RIE
RIO
RNS
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-i208t-29970431b08a871c2b46ce28bc9e8a66c84cfafbf15ac4fdcb158531b768e8753
IEDL.DBID RIE
ISICitedReferencesCount 197
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000387959201100&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1063-6919
IngestDate Wed Oct 01 14:41:19 EDT 2025
Wed Aug 27 02:49:18 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i208t-29970431b08a871c2b46ce28bc9e8a66c84cfafbf15ac4fdcb158531b768e8753
Notes ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
PQID 1770332261
PQPubID 23500
PageCount 9
ParticipantIDs ieee_primary_7298800
proquest_miscellaneous_1770332261
PublicationCentury 2000
PublicationDate 20150601
PublicationDateYYYYMMDD 2015-06-01
PublicationDate_xml – month: 06
  year: 2015
  text: 20150601
  day: 01
PublicationDecade 2010
PublicationTitle 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublicationTitleAbbrev CVPR
PublicationYear 2015
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib030089920
ssj0023720
ssj0003211698
Score 2.4049714
Snippet Despite the great progress achieved in recognizing objects as 2D bounding boxes in images, it is still very challenging to detect occluded objects and estimate...
SourceID proquest
ieee
SourceType Aggregation Database
Publisher
StartPage 1903
SubjectTerms Benchmark testing
Computer vision
Detectors
Image detection
Image segmentation
Object detection
Object recognition
Occlusion
Pattern recognition
Three dimensional
Two dimensional
Title Data-driven 3D Voxel Patterns for object category recognition
URI https://ieeexplore.ieee.org/document/7298800
https://www.proquest.com/docview/1770332261
WOSCitedRecordID wos000387959201100&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFA9zePA0dRPnFxE8mq1fS5qDp83hQUYRHbuVJE1gIK2snfjn-9Km9aAXL6WElpaXl997L7_38hC64ywA6JWC-AYWeSSCkPCZiogBa8OpZEo1hcLPbLWKNxue9NB9Vwujta6Tz_TE3tZcflaovd0qm4IjCOoGAfoBY7Sp1Wp1J_Qsf-VcH4vCIUQ2lHeMQmC7sdTMJw0J5T53DKfv8el8nbzYJK_ZxH3AdVr5Bc-1zVkO_ve3x2j0U7yHk84snaCezk_RwHmb2K3lEobahg7t2BA9LEQlSLazCIjDBV4XX_odJ_URnHmJwb_FhbQbN9jmUdnaFtwlIBX5CL0tH1_nT8T1VyDbwIsrApaI2bN1pBcLiJtUICPbHyyWiutYUKriSBlhpPFnQkUmU9KH4AKehxBF2zjnDPXzItfnCGvtmSimWWR4FjEDV264YFJJDT6k5GM0tAJKP5ojNFInmzG6bSWcglpbrkLkutiXqc8AigBsqH_x96uX6MhOWZO1dYX61W6vr9Gh-qy25e6m1o1v6Q22Jg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA6lCnqq2or1GcGjafeRfeTgqbVUrGWRWnpbkmwCBdmVbiv-fCf78qAXL8sSdtllMvlmJt9MBqE7FjgAvYITW8Mip9xxCfMkJRqsDfNFIGVZKDwL5vNwtWJRC903tTBKqSL5TA3MbcHlJ5ncma2yITiCoG4QoO95lDpWWa1Va49rGQarcn4MDrsQ2_is4RQc04-l4D59l_jMZhXHaVtsOFpGrybNyxtUn6h6rfwC6MLqTDr_-98j1Psp38NRY5iOUUulJ6hT-Zu4Ws05DNUtHeqxLnoY8y0nycZgIHbHeJl9qXccFYdwpjkGDxdnwmzdYJNJZapbcJOClKU99DZ5XIympOqwQNaOFW4J2KLAnK4jrJBD5CQdQU2HsFBIpkLu-zKkUnMttO1xSXUihQ3hBTwPQYoykc4paqdZqs4QVsrSNPQTqllCAw1XphkPhBQKvEjB-qhrBBR_lIdoxJVs-ui2lnAMim3YCp6qbJfHdgBgBHDj2-d_v3qDDqaLl1k8e5o_X6BDM31lDtclam83O3WF9uXndp1vrgs9-QaSHblt
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=2015+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29&rft.atitle=Data-driven+3D+Voxel+Patterns+for+object+category+recognition&rft.au=Yu+Xiang&rft.au=Wongun+Choi&rft.au=Yuanqing+Lin&rft.au=Savarese%2C+Silvio&rft.date=2015-06-01&rft.pub=IEEE&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=1903&rft.epage=1911&rft_id=info:doi/10.1109%2FCVPR.2015.7298800&rft.externalDocID=7298800
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6919&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6919&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6919&client=summon