DMCA
Trajectory Guided Tracking and Recognition of Actions (1999)
| Citations: | 13 - 2 self |
BibTeX
@MISC{Rosales99trajectoryguided,
author = {Rómer Rosales and Stan Sclaroff},
title = { Trajectory Guided Tracking and Recognition of Actions},
year = {1999}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A combined 2D, 3D approach is presented that allows for robust tracking of moving people and recognition of actions. It is assumed that the system observes multiple moving objects via a single, uncalibrated video camera. Low-level features are often insufficient for detection, segmentation, and tracking of non-rigid moving objects. Therefore, an improved mechanism is proposed that integrates low-level (image processing), mid-level (recursive 3D trajectory estimation), and high-level (action recognition) processes. A novel extended Kalman filter formulation is used in estimating the relative 3D motion trajectories up to a scale factor. The recursive estimation process provides a prediction and error measure that is exploited in higher-level stages of action recognition. Conversely, higherlevel mechanisms provide feedback that allows the system to reliably segment and maintain the tracking of moving objects before, during, and after occlusion. The 3D trajectory, occlusion, and segmentation information are utilized in extracting stabilized views of the moving object that are then used as input to action recognition modules. Trajectory-guided recognition (TGR) is proposed as a new and efficient method for adaptive classification of action. The TGR approach is demonstrated using "motion history images" that are then recognized via a mixture-of-Gaussians classifier. The system was tested in recognizing various dynamic human outdoor activities: running, walking, roller blading, and cycling. Experiments with real and synthetic data sets are used to evaluate stability of the trajectory estimator with respect to noise.
Keyphrases
action recognition motion history image scale factor tgr approach mixture-of-gaussians classifier various dynamic human outdoor activity image processing motion trajectory uncalibrated video camera roller blading higherlevel mechanism trajectory estimation trajectory-guided recognition robust tracking efficient method adaptive classification low-level feature segmentation information recursive estimation process kalman filter formulation action recognition module improved mechanism error measure higher-level stage stabilized view trajectory estimator synthetic data set
