Proceedings chapter
Open access

Combining multiple motion estimates for vehicle tracking

Published in4th European Conference Computer Vision - ECCV 96, Editors B. Buxton and R. Cipolla, p. 307-320
Presented at Cambridge (UK)
  • Lecture Notes in Computer Science; 1064
Publication date1996

In this paper, the problem of combining estimates provided by multiple models is considered, with application to vehicle tracking. Two tracking systems, based on the bounding-box and on the 2-D pattern of the targets, provide individual motion parameters estimates to the combining method, which in turn produces a global estimate. Two methods are proposed to combine the estimates of these tracking systems: one is based on their covariance matrix, while the other one employs a Kalman filter model. Results are provided on three image sequences taken under different viewpoints, weather conditions and varying vehicle/road contrasts. Two evaluations are made. First, the performances of individual and global estimates are compared. Second, the two global estimates are compared and the superiority of the second method is assessed over the first one.

Citation (ISO format)
GIL MILANESE, Sylvia, MILANESE, Ruggero, PUN, Thierry. Combining multiple motion estimates for vehicle tracking. In: 4th European Conference Computer Vision - ECCV 96. Cambridge (UK). [s.l.] : Springer-Verlag, 1996. p. 307–320. (Lecture Notes in Computer Science) doi: 10.1007/3-540-61123-1_149
Main files (1)
Proceedings chapter (Published version)

Technical informations

Creation03/06/2015 5:12:12 PM
First validation03/06/2015 5:12:12 PM
Update time03/14/2023 10:59:02 PM
Status update03/14/2023 10:59:02 PM
Last indexation01/16/2024 5:10:05 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack