2 May 2012 Spatio-temporal features for tracking and quadruped/biped discrimination
Author Affiliations +
Techniques such as SIFT and SURF facilitate efficient and robust image processing operations through the use of sparse and compact spatial feature descriptors and show much potential for defence and security applications. This paper considers the extension of such techniques to include information from the temporal domain, to improve utility in applications involving moving imagery within video data. In particular, the paper demonstrates how spatio-temporal descriptors can be used very effectively as the basis of a target tracking system and as target discriminators which can distinguish between bipeds and quadrupeds. Results using sequences of video imagery of walking humans and dogs are presented, and the relative merits of the approach are discussed.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Rick Rickman, Rick Rickman, Keith Copsey, Keith Copsey, David C. Bamber, David C. Bamber, Scott F. Page, Scott F. Page, "Spatio-temporal features for tracking and quadruped/biped discrimination", Proc. SPIE 8391, Automatic Target Recognition XXII, 83910I (2 May 2012); doi: 10.1117/12.919028; https://doi.org/10.1117/12.919028


Back to Top