Title :
Incremental recognition of pedestrians from image sequences
Author_Institution :
FB Inf., Hamburg Univ., Germany
Abstract :
An approach that uses a volume model consisting of cylinders for model-based recognition of pedestrians in real-world images is presented. The human body is represented by a volume model, and medical motion data are used for simulating the movement of walking. This knowledge is exploited to determine the 3-D position, as well as the posture of an observed person. By applying a Kalman filter, the model parameters in consecutive images are incrementally estimated. The approach is tested on real image data
Keywords :
Kalman filters; biomechanics; filtering theory; image recognition; image sequences; parameter estimation; 3-D position; Kalman filter; cylinders; gait analysis; image sequences; incremental recognition; medical motion data; model-based recognition; parameter estimation; pedestrian recognition; real-world images; volume model; walking; Biological system modeling; Biomedical imaging; Clothing; Humans; Image recognition; Image sequences; Joints; Legged locomotion; Medical diagnostic imaging; Medical simulation; Parameter estimation; Testing;
Conference_Titel :
Computer Vision and Pattern Recognition, 1993. Proceedings CVPR '93., 1993 IEEE Computer Society Conference on
Conference_Location :
New York, NY
Print_ISBN :
0-8186-3880-X
DOI :
10.1109/CVPR.1993.341008
