A novel action recognition strategy in a video-surveillance context is herein presented. The method starts by computing a multiscale dense optical flow, from which spatial apparent movement regions are clustered as Regions of Interest (RoIs). Each ROI is summarized at each time by an orientation histogram. Then, a multilayer structure dynamically stores the orientation histograms associated to any of the found RoI in the scene and a set of cumulated temporal statistics is used to label that RoI using a previously trained support vector machine model. The method is evaluated using classic human action and public surveillance datasets, with two different tasks: (1) classification of short sequences containing individual actions, and (2) Frame-level recognition of human action in long sequences containing simultaneous actions. The accuracy measurements are: 96:7% (sequence rate) for the classification task, and 95:3% (frame rate) for recognition in surveillance scenes.

Date Published: 5 March 2014
PDF: 6 pages
Proc. SPIE 9026, Video Surveillance and Transportation Imaging Applications 2014, 90260G (5 March 2014); doi: 10.1117/12.2042588

Published in SPIE Proceedings Vol. 9026:
Video Surveillance and Transportation Imaging Applications 2014
Robert P. Loce; Eli Saber; Ned Lecky, Editor(s)