Velocity-adapted spatio-temporal receptive fields for direct recognition of activities
2002 (English)In: Proc. ECCV’02 Workshop on Statistical Methods in Video Processing, 2002, 61-66 p.Conference paper (Refereed)
This article presents an experimental study of the influence of velocity adaptation when recognizing spatio-temporal patterns using a histogram-based statistical framework. The basic idea consists of adapting the shapes of the filter kernels to the local direction of motion, so as to allow the computation of image descriptors that are invariant to the relative motion in the image plane between the camera and the objects or events that are studied. Based on a framework of recursive spatio-temporal scale-space, we first outline how a straightforward mechanism for local velocity adaptation can be expressed. Then, for a test problem of recognizing activities, we present an experimental evaluation, which shows the advantages of using velocity-adapted spatio-temporal receptive fields, compared to directional derivatives or regular partial derivatives for which the filter kernels have not been adapted to the local image motion.
Place, publisher, year, edition, pages
2002. 61-66 p.
Computer Science Computer Vision and Robotics (Autonomous Systems) Mathematics
IdentifiersURN: urn:nbn:se:kth:diva-40195OAI: oai:DiVA.org:kth-40195DiVA: diva2:442100
ECCV’02 Workshop on Statistical Methods in Video Processing,Copenhagen,Denmark, May 2002
QC 201109202011-09-202011-09-132015-07-16Bibliographically approved