We present a system for automatic people tracking and activity recognition. Our basic approach to people-tracking is to build an appearance model for the person in the video. The video illustrates our method of using a stylized-pose detector. Our system builds a model of limb appearance from those sparse stylized detections. Our algorithm then reprocesses the video, using the learned appearance models to find people in unrestricted configuration. We can use our tracker to recover 3D configurations and activity labels. We assume we have a motion capture library where the 3D poses have been labeled offline with activity descriptions.
Tracking people and recognizing their activities
2005-01-01
291844 byte
Conference paper
Electronic Resource
English
Detecting, Tracking and Recognizing License Plates
Springer Verlag | 2007
|British Library Online Contents | 2013
|Recognizing and Tracking Airport Runway Target in Infrared Images
British Library Conference Proceedings | 1997
|Recognizing activities in multiple views with fusion of frame judgments
British Library Online Contents | 2014
|Method for recognizing object through light tracking and electronic equipment
European Patent Office | 2021
|