Forensics in Telecommunications, Information and Multimedia. Second International Conference, e-Forensics 2009, Adelaide, Australia, January 19-21, 2009, Revised Selected Papers

Research Article

Surveillance Applications of Biologically-Inspired Smart Cameras

Download
584 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-02312-5_8,
        author={Kosta Haltis and Lee Andersson and Matthew Sorell and Russell Brinkworth},
        title={Surveillance Applications of Biologically-Inspired Smart Cameras},
        proceedings={Forensics in Telecommunications, Information and Multimedia. Second International Conference, e-Forensics 2009, Adelaide, Australia, January 19-21, 2009, Revised Selected Papers},
        proceedings_a={E-FORENSICS},
        year={2012},
        month={5},
        keywords={Surveillance digital video processing biological vision motion detection image enhancement},
        doi={10.1007/978-3-642-02312-5_8}
    }
    
  • Kosta Haltis
    Lee Andersson
    Matthew Sorell
    Russell Brinkworth
    Year: 2012
    Surveillance Applications of Biologically-Inspired Smart Cameras
    E-FORENSICS
    Springer
    DOI: 10.1007/978-3-642-02312-5_8
Kosta Haltis1, Lee Andersson1, Matthew Sorell1, Russell Brinkworth2,*
  • 1: School of Electrical and Electronic Engineering
  • 2: University of Adelaide
*Contact email: russell.brinkworth@adelaide.edu.au

Abstract

Biological vision systems are capable of discerning detail and detecting motion in a wide range of highly variable lighting conditions. We describe the real-time implementation of a biological vision model using a high dynamic range video camera and a General Purpose Graphics Processing Unit (GPGPU) and demonstrate the effectiveness of the implementation in two surveillance applications: dynamic equalization of contrast for improved recognition of scene detail; and the use of biologically-inspired motion processing for the detection of small or distant moving objects in a complex scene.