ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Parts based representation for pedestrian using NMF with robustness to partial occlusion

Shankar, Naveen N and Ramakrishnan, KR (2010) Parts based representation for pedestrian using NMF with robustness to partial occlusion. In: International Conference on Signal Processing and Communications, JUL 18-21, 2010, Indian Inst Sci, Bangalore, INDIA.

[img] PDF
Parts.pdf - Published Version
Restricted to Registered users only

Download (172Kb) | Request a copy
Official URL: http://ieeexplore.ieee.org/search/srchabstract.jsp...

Abstract

Computer Vision has seen a resurgence in the parts-based representation for objects over the past few years. The parts are usually annotated beforehand for training. We present an annotation free parts-based representation for the pedestrian using Non-Negative Matrix Factorization (NMF). We show that NMF is able to capture the wide range of pose and clothing of the pedestrians. We use a modified form of NMF i.e. NMF with sparsity constraints on the factored matrices. We also make use of Riemannian distance metric for similarity measurements in NMF space as the basis vectors generated by NMF aren't orthogonal. We show that for 1% drop in accuracy as compared to the Histogram of Oriented Gradients (HOG) representation we can achieve robustness to partial occlusion.

Item Type: Conference Paper
Additional Information: Copyright 2010 IEEE. Personal use of this material is permitted.However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Keywords: Non-Negative Matrix Factorization (NMF); Histogram of Oriented Gradients (HOG)
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 31 Mar 2011 09:23
Last Modified: 31 Mar 2011 09:23
URI: http://eprints.iisc.ernet.in/id/eprint/36373

Actions (login required)

View Item View Item