NDLI: Bayesian 3D Tracking from Monocular Video

Content Provider	IEEE Xplore Digital Library
Author	Brau, E. Jinyan Guan Simek, K. Del Pero, L. Dawson, C.R. Barnard, K.
Copyright Year	2013
Description	Author affiliation: Comput. Sci., Univ. of Arizona, Tucson, AZ, USA (Brau, E.; Jinyan Guan; Simek, K.) \|\| Sch. of Inf., Univ. of Edinburgh, Edinburgh, UK (Del Pero, L.) \|\| Sch. of Inf., Univ. of Arizona, Tucson, AZ, USA (Dawson, C.R.; Barnard, K.)
Abstract	We develop a Bayesian modeling approach for tracking people in 3D from monocular video with unknown cameras. Modeling in 3D provides natural explanations for occlusions and smoothness discontinuities that result from projection, and allows priors on velocity and smoothness to be grounded in physical quantities: meters and seconds vs. pixels and frames. We pose the problem in the context of data association, in which observations are assigned to tracks. A correct application of Bayesian inference to multi-target tracking must address the fact that the model's dimension changes as tracks are added or removed, and thus, posterior densities of different hypotheses are not comparable. We address this by marginalizing out the trajectory parameters so the resulting posterior over data associations has constant dimension. This is made tractable by using (a) Gaussian process priors for smooth trajectories and (b) approximately Gaussian likelihood functions. Our approach provides a principled method for incorporating multiple sources of evidence, we present results using both optical flow and object detector outputs. Results are comparable to recent work on 3D tracking and, unlike others, our method requires no pre-calibrated cameras.
Sponsorship	IEEE Comput. Soc.
Starting Page	3368
Ending Page	3375
File Size	401299
Page Count	8
File Format	PDF
ISBN	9781479928408
ISSN	15505499
DOI	10.1109/ICCV.2013.418
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2013-12-01
Publisher Place	Australia
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Three-dimensional displays Cameras Trajectory Computational modeling Solid modeling Target tracking MCMCDA multi-object tracking 3D scene modeling Bayesian inference
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Understanding Bayesian Rooms Using Composite 3D Object Models

Monocular 3D scene understanding with explicit occlusion reasoning

Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition

Viewpoint invariant 3D landmark model inference from monocular 2D images using higher-order priors

Understanding tools: Task-oriented object modeling, learning and recognition

Physically Plausible 3D Scene Tracking: The Single Actor Hypothesis

Hypergraphs for Joint Multi-view Reconstruction and Multi-object Tracking

Holistic Scene Understanding for 3D Object Detection with RGBD Cameras

Statistical Error Propagation in 3D Modeling From Monocular Video

Bayesian 3D Tracking from Monocular Video

Similar Documents

Understanding Bayesian Rooms Using Composite 3D Object Models

Monocular 3D scene understanding with explicit occlusion reasoning

Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition

Viewpoint invariant 3D landmark model inference from monocular 2D images using higher-order priors

Understanding tools: Task-oriented object modeling, learning and recognition

Physically Plausible 3D Scene Tracking: The Single Actor Hypothesis

Hypergraphs for Joint Multi-view Reconstruction and Multi-object Tracking

Holistic Scene Understanding for 3D Object Detection with RGBD Cameras

Statistical Error Propagation in 3D Modeling From Monocular Video

Bayesian 3D Tracking from Monocular Video