Share Email Print
cover

Proceedings Paper

Trajectory guided recognition of actions
Author(s): Romer Rosales; Stan Sclaroff
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

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.

Paper Details

Date Published: 8 November 1999
PDF: 12 pages
Proc. SPIE 3840, Telemanipulator and Telepresence Technologies VI, (8 November 1999); doi: 10.1117/12.369285
Show Author Affiliations
Romer Rosales, Boston Univ. (United States)
Stan Sclaroff, Boston Univ. (United States)


Published in SPIE Proceedings Vol. 3840:
Telemanipulator and Telepresence Technologies VI
Matthew R. Stein, Editor(s)

© SPIE. Terms of Use
Back to Top