Special Section on Video Surveillance and Transportation Imaging Applications

Human object annotation for surveillance video forensics

[+] Author Affiliations
Muhammad Fraz

Loughborough University, Department of Computer Science, Loughborough LE11 3TU, United Kingdom

Iffat Zafar

Loughborough University, Department of Computer Science, Loughborough LE11 3TU, United Kingdom

Giounona Tzanidou

Loughborough University, Department of Computer Science, Loughborough LE11 3TU, United Kingdom

Eran A. Edirisinghe

Loughborough University, Department of Computer Science, Loughborough LE11 3TU, United Kingdom

Muhammad Saquib Sarfraz

Karlsruhe Institute of Technology, Computer Vision for Human Computer Interaction Lab, 76131 Karlsruhe, Germany

J. Electron. Imaging. 22(4), 041115 (Aug 29, 2013). doi:10.1117/1.JEI.22.4.041115
History: Received April 17, 2013; Revised July 20, 2013; Accepted July 30, 2013
Text Size: A A A

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.

Figures in this Article
© 2013 SPIE and IS&T

Citation

Muhammad Fraz ; Iffat Zafar ; Giounona Tzanidou ; Eran A. Edirisinghe and Muhammad Saquib Sarfraz
"Human object annotation for surveillance video forensics", J. Electron. Imaging. 22(4), 041115 (Aug 29, 2013). ; http://dx.doi.org/10.1117/1.JEI.22.4.041115


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.