Share Email Print

Journal of Electronic Imaging

Human object annotation for surveillance video forensics
Author(s): Muhammad Fraz; Iffat Zafar; Giounona Tzanidou; Eran Anusha Edirisinghe; Muhammad Saquib Sarfraz
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A system that can automatically annotate surveillance video in a manner useful for locating a person with a given description of clothing is presented. Each human is annotated based on two appearance features: primary colors of clothes and the presence of text/logos on clothes. The annotation occurs after a robust foreground extraction stage employing a modified Gaussian mixture model-based approach. The proposed pipeline consists of a preprocessing stage where color appearance of an image is improved using a color constancy algorithm. In order to annotate color information for human clothes, we use the color histogram feature in HSV space and find local maxima to extract dominant colors for different parts of a segmented human object. To detect text/logos on clothes, we begin with the extraction of connected components of enhanced horizontal, vertical, and diagonal edges in the frames. These candidate regions are classified as text or nontext on the basis of their local energy-based shape histogram features. Further, to detect humans, a novel technique has been proposed that uses contourlet transform-based local binary pattern (CLBP) features. In the proposed method, we extract the uniform direction invariant LBP feature descriptor for contourlet transformed high-pass subimages from vertical and diagonal directional bands. In the final stage, extracted CLBP descriptors are classified by a trained support vector machine. Experimental results illustrate the superiority of our method on large-scale surveillance video data.

Paper Details

Date Published: 29 August 2013
PDF: 15 pages
J. Electron. Imag. 22(4) 041115 doi: 10.1117/1.JEI.22.4.041115
Published in: Journal of Electronic Imaging Volume 22, Issue 4
Show Author Affiliations
Muhammad Fraz, Loughborough Univ. (United Kingdom)
Iffat Zafar, Loughborough Univ. (United Kingdom)
Giounona Tzanidou, Loughborough Univ. (United Kingdom)
Eran Anusha Edirisinghe, Loughborough Univ. (United Kingdom)
Muhammad Saquib Sarfraz

© SPIE. Terms of Use
Back to Top