8 November 1999 Trajectory guided recognition of actions
Author Affiliations +
A computer vision method is presented for recognizing the non-rigid motion observed in objects moving in a 3D environment. This method is embedded in a more complete mechanism that integrates low-level (image processing), mid- level (recursive 3D trajectory estimation), and high-level (action recognition) processes. Multiple moving objects are observed via a single, uncalibrated video camera. A Kalman filter formulation is used in estimating the relative 3D motion trajectories. The recursive estimation process provides a prediction and error measure that is exploited in higher-level stages. In this paper we concentrate in the action recognition stage. The 3D trajectory, occlusion, and segmentation information are utilized in extracting stabilized views of the moving object. Trajectory-guided recognition (TGR) is then proposed as an efficient method for adaptive classification of action. The TGR approach is demonstrated using 'motion history images' that are then recognized via a mixture of Gaussian classifier. The system was tested in recognizing various dynamic human outdoor activities; e.g., running, walking, roller blading, and cycling.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Romer Rosales, Romer Rosales, Stan Sclaroff, Stan Sclaroff, } "Trajectory guided recognition of actions", Proc. SPIE 3840, Telemanipulator and Telepresence Technologies VI, (8 November 1999); doi: 10.1117/12.369285; https://doi.org/10.1117/12.369285


Back to Top