Performance evaluation of video object tracking algorithm in autonomous surveillance system

Results of a performance evaluation of a video object tracking algorithm are presented. The method of moving object detection and tracking is based on background modelling with mixtures of Gaussian and Kalman filters. An emphasis is put on algorithm's efficiency with regards to its settings. Utilized methods of a performance evaluation based on a comparison of the algorithm output to manually prepared reference data are introduced. The experiments aimed at examining the performance achieved with various object detection algorithm parameter settings are presented and discussed.