Chapter

Spatial Coherence for Visual Motion Analysis

Volume 3667 of the series Lecture Notes in Computer Science pp 91-103

Local Descriptors for Spatio-temporal Recognition

  • Ivan LaptevAffiliated withComputational Vision and Active Perception Laboratory (CVAP), Dept. of Numerical Analysis and Computing Science, KTH
  • , Tony LindebergAffiliated withComputational Vision and Active Perception Laboratory (CVAP), Dept. of Numerical Analysis and Computing Science, KTH

Abstract

This paper presents and investigates a set of local space-time descriptors for representing and recognizing motion patterns in video. Following the idea of local features in the spatial domain, we use the notion of space-time interest points and represent video data in terms of local space-time events. To describe such events, we define several types of image descriptors over local spatio-temporal neighborhoods and evaluate these descriptors in the context of recognizing human activities. In particular, we compare motion representations in terms of spatio-temporal jets, position dependent histograms, position independent histograms, and principal component analysis computed for either spatio-temporal gradients or optic flow. An experimental evaluation on a video database with human actions shows that high classification performance can be achieved, and that there is a clear advantage of using local position dependent histograms, consistent with previously reported findings regarding spatial recognition.