HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences

We present a new descriptor for activity recognition from videos acquired by a depth sensor. Previous descriptors mostly compute shape and motion features independently, thus, they often fail to capture the complex joint shape-motion cues at pixel-level. In contrast, we describe the depth sequence u...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2013 IEEE Conference on Computer Vision and Pattern Recognition S. 716 - 723
Hauptverfasser: Oreifej, Omar, Zicheng Liu
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2013
Schlagworte:
ISSN:1063-6919, 1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract We present a new descriptor for activity recognition from videos acquired by a depth sensor. Previous descriptors mostly compute shape and motion features independently, thus, they often fail to capture the complex joint shape-motion cues at pixel-level. In contrast, we describe the depth sequence using a histogram capturing the distribution of the surface normal orientation in the 4D space of time, depth, and spatial coordinates. To build the histogram, we create 4D projectors, which quantize the 4D space and represent the possible directions for the 4D normal. We initialize the projectors using the vertices of a regular polychoron. Consequently, we refine the projectors using a discriminative density measure, such that additional projectors are induced in the directions where the 4D normals are more dense and discriminative. Through extensive experiments, we demonstrate that our descriptor better captures the joint shape-motion cues in the depth sequence, and thus outperforms the state-of-the-art on all relevant benchmarks.
AbstractList We present a new descriptor for activity recognition from videos acquired by a depth sensor. Previous descriptors mostly compute shape and motion features independently, thus, they often fail to capture the complex joint shape-motion cues at pixel-level. In contrast, we describe the depth sequence using a histogram capturing the distribution of the surface normal orientation in the 4D space of time, depth, and spatial coordinates. To build the histogram, we create 4D projectors, which quantize the 4D space and represent the possible directions for the 4D normal. We initialize the projectors using the vertices of a regular polychoron. Consequently, we refine the projectors using a discriminative density measure, such that additional projectors are induced in the directions where the 4D normals are more dense and discriminative. Through extensive experiments, we demonstrate that our descriptor better captures the joint shape-motion cues in the depth sequence, and thus outperforms the state-of-the-art on all relevant benchmarks.
Author Oreifej, Omar
Zicheng Liu
Author_xml – sequence: 1
  givenname: Omar
  surname: Oreifej
  fullname: Oreifej, Omar
  email: oreifej@eecs.ucf.edu
  organization: Univ. of Central Florida, Orlando, FL, USA
– sequence: 2
  surname: Zicheng Liu
  fullname: Zicheng Liu
  email: zliu@microsoft.edu
  organization: Microsoft Res., Redmond, WA, USA
BookMark eNpNjktPAjEYRavBREB27tz0D8zY1_ThjgA6JgQMilsyM_2KNc4UO9WEfy-JLlzdm5PckztCgy50gNA1JTmlxNzOXp82OSOU50afoYlRmhZcy0Iqxs_RkBLJM2moGfzrl2jU9--EMK4YGaJtuV6J-R0ufZ_CPlYtDg6vo4cugcVijlchttVHj12IeNok_-3TEW-gCfvOJx867GJo8RwO6Q0_w-cXdA30V-jCnUYw-csx2t4vXmZltlw_PM6my8wzQVMGVENtlS0aQYRkimhXayW54fZ0T8tK2oJTB1TZmtZOVfJEHXemqWoBtuZjdPPr9QCwO0TfVvG4k5JqIxj_AXHUUxg
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2013.98
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
DatabaseTitleList
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 9781538656723
1538656728
EISSN 1063-6919
EndPage 723
ExternalDocumentID 6618942
Genre orig-research
GroupedDBID 23M
29F
29O
6IE
6IH
6IK
ABDPE
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CBEJK
IPLJI
M43
RIE
RIO
RNS
ID FETCH-LOGICAL-i241t-e18ebd7d5c40462708fb876393d23786a6d531fe17db1bf7a6378f3f9cab4edb3
IEDL.DBID RIE
ISICitedReferencesCount 671
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000331094300091&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 Aug 27 02:59:40 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i241t-e18ebd7d5c40462708fb876393d23786a6d531fe17db1bf7a6378f3f9cab4edb3
PageCount 8
ParticipantIDs ieee_primary_6618942
PublicationCentury 2000
PublicationDate 2013-06
PublicationDateYYYYMMDD 2013-06-01
PublicationDate_xml – month: 06
  year: 2013
  text: 2013-06
PublicationDecade 2010
PublicationTitle 2013 IEEE Conference on Computer Vision and Pattern Recognition
PublicationTitleAbbrev CVPR
PublicationYear 2013
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0023720
ssj0003211698
Score 2.470327
Snippet We present a new descriptor for activity recognition from videos acquired by a depth sensor. Previous descriptors mostly compute shape and motion features...
SourceID ieee
SourceType Publisher
StartPage 716
SubjectTerms 4D Normals
Action Recognition
Activity Recognition
Depth
Histogram of Gradients
Histogram of Normals
Histograms
HOG
HON
Joints
Kinect
MSR Action 3D
MSR Action Pairs
MSR Daily Activity
Polychoron
Quantization (signal)
Shape
Support vector machines
Three-dimensional displays
Vectors
Title HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences
URI https://ieeexplore.ieee.org/document/6618942
WOSCitedRecordID wos000331094300091&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/eLvHCXMwlV27TsMwFLVKxcBUoEW85YERt0mc-MGGWqpOaVQo6lbFL1EJJVWb8v3YeSEkFrboTtFN7Hvse849ADxw34JkQzEKmOQoJAYjQaIIRamrOEp4qTKl2QSNY7Za8aQDHlstjNa6JJ_poXsse_kqlwd3VTaytYTx0G64R5SSSqvV3qdge5IhvO0gBM59pex0EowI93lLeuej8XuycKQuPOTsl6lKWVOmvf-9zSkY_IjzYNKWnTPQ0dk56NVoEtZrdW9DjWFDE-uD5Wweh5MnWM4GcbQsmBs4d5OOLe6E4QTGDsF-7qFFsvBZVsYScNFwjPIMOjUKnOht8QFfGxL2ACynL2_jGap9FdDG1usCaZ9poaiKZOikqdRjRrjBdBwrmzZGUqLsyjTap0r4wtCU2KjBhstUhFoJfAG6WZ7pSwCJol7EKDd243QdQSYVFn4k7A8gA0nUFei7xK231eiMdZ2z67_DN-AkqNwmkOffgm6xO-g7cCy_is1-d19-729HiKgo
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4ImugJFYy_7cGjhW3dutabAQlGHATBcCPrr0hiNgLDv992bDMmXrwt77S8rX1f-77vfQDcMdeAZB1i5FHBkE80RpwEAQpiW3Ekd2Kpc7OJMIrofM7GNXBfaWGUUjn5TLXtY97Ll6nY2quyjqkllPlmw92zzlmFWqu6UcHmLENY1UPwrP9K3uskGBHmsor2zjrd9_HE0rpwm9Fftip5Vek3_vc-R6D1I8-D46rwHIOaSk5Ao8CTsFitGxMqLRvKWBPMBqPI7z3AfDqIJWbBVMORnXVskCf0ezCyGPZzAw2WhY9iZy0BJyXLKE2g1aPAnlplH_CtpGG3wKz_NO0OUOGsgJamYmdIuVRxGcpA-FacGjpUczuajmFp0kZJTKRZm1q5oeQu12FMTFRjzUTMfSU5PgX1JE3UGYBEhk5AQ6bN1ml7glRIzN2Am19AeILIc9C0iVusdsMzFkXOLv4O34KDwfR1uBg-Ry-X4NDbeU8gx70C9Wy9VddgX3xly836Jv_23zuiq3E
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%3Abook&rft.genre=proceeding&rft.title=2013+IEEE+Conference+on+Computer+Vision+and+Pattern+Recognition&rft.atitle=HON4D%3A+Histogram+of+Oriented+4D+Normals+for+Activity+Recognition+from+Depth+Sequences&rft.au=Oreifej%2C+Omar&rft.au=Zicheng+Liu&rft.date=2013-06-01&rft.pub=IEEE&rft.issn=1063-6919&rft.eissn=1063-6919&rft.spage=716&rft.epage=723&rft_id=info:doi/10.1109%2FCVPR.2013.98&rft.externalDocID=6618942
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