NDLI: Principled fusion of high-level model and low-level cues for motion segmentation

Content Provider	IEEE Xplore Digital Library
Author	Thayananthan, A. Iwasaki, M. Cipolla, R.
Copyright Year	2008
Description	Author affiliation: Dept. of Eng., Cambridge Univ., Cambridge (Thayananthan, A.)
Abstract	High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, approximate inference in these models often require ad-hoc initialization to avoid local minima issues. Low-level cues, obtained independently from the high-level model, can constrain the search space and reduce the chance of inference algorithms falling into a local minima. This paper introduces a novel principled fusion framework where, local hierarchical superpixels segmentation of images are used to capture local motion. The low-level cues such as local motion, on their own, not adequate to obtain full motion segmentation as occlusion needs to be handled globally. We fuse the low-level motion cues with the high-level model in a principled manner to surmount the shortcomings of using only the high-level model or low-level cues to perform motion segmentation. The fused model contains both continuous and discrete variables which forms a number of Markov Random fields. Variational approximation or belief propagation algorithms cannot be applied due to the complex interactions between the variables. Hence, approximate inference is performed using expectation propagation (EP) algorithm. The scheme is demonstrated by performing motion segmentation in two video sequences.
Starting Page	1
Ending Page	8
File Size	1468637
Page Count	8
File Format	PDF
ISBN	9781424422425
ISSN	10636919
DOI	10.1109/CVPR.2008.4587438
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2008-06-23
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Motion segmentation Computer vision Inference algorithms Fusion power generation Videos Image segmentation Fuses Markov random fields Belief propagation Approximation algorithms
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

Efficiently solving dynamic Markov random fields using graph cuts

Efficient belief propagation for early vision

The infinite Hidden Markov random field model

Fusion Moves for Markov Random Field Optimization

Ray Markov Random Fields for image-based 3D modeling: Model and efficient inference

Principled fusion of high-level model and low-level cues for motion segmentation (2008)

Principled fusion of high-level model and low-level cues for motion segmentation (2008)

Alphabet SOUP: A framework for approximate energy minimization

Learning real-time MRF inference for image denoising

Principled fusion of high-level model and low-level cues for motion segmentation

Similar Documents

Efficiently solving dynamic Markov random fields using graph cuts

Efficient belief propagation for early vision

The infinite Hidden Markov random field model

Fusion Moves for Markov Random Field Optimization

Ray Markov Random Fields for image-based 3D modeling: Model and efficient inference

Principled fusion of high-level model and low-level cues for motion segmentation (2008)

Principled fusion of high-level model and low-level cues for motion segmentation (2008)

Alphabet SOUP: A framework for approximate energy minimization

Learning real-time MRF inference for image denoising

Principled fusion of high-level model and low-level cues for motion segmentation