Loading...
Please wait, while we are loading the content...
Similar Documents
Multi-Object Trajectory Tracking
| Content Provider | CiteSeerX |
|---|---|
| Author | Han, Mei Xu, Wei Tao, Hai Gong, Yihong |
| Abstract | The majority of existing tracking algorithms are based on the maximum a posteriori (MAP) solution of a probabilistic framework using a Hidden Markov Model, where the distribution of the object state at the current time instance is estimated based on current and previous observations. However, this approach is prone to errors caused by distractions such as occlusions, background clutters and multi-object confusions. In this paper we propose a multiple object tracking algorithm that seeks the optimal state sequence that maximizes the joint multi-object state-observation probability. We call this algorithm trajectory tracking since it estimates the state sequence or “trajectory ” instead of the current state. The algorithm is capable of tracking unknown time-varying number of multiple objects. We also introduce a novel observation model which is composed of the original image, the fore-ground mask given by background subtraction and the object detection map generated by an object detector. The image provides the object appearance information. The foreground mask enables the likelihood computation to consider the multi-object configuration in its entirety. The detection map consists of pixel-wise object detection scores, which drives the tracking algorithm to perform joint inference on both the number of objects and their configurations efficiently. The proposed algorithm has been implemented and tested extensively in a complete CCTV video surveillance system to monitor entries and detect tailgating and piggy-backing violations at access points for over six months. The system achieved 98.3 % precision in event classification. The viola-tion detection rate is 90.4 % and the detection precision is 85.2%. The results clearly demonstrate the advantages of the proposed detection based trajectory tracking framework. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Multi-object Trajectory Tracking Multiple Object Event Classification Object Appearance Information Joint Inference Detection Map Object State Joint Multi-object State-observation Probability Original Image Background Clutter Probabilistic Framework Likelihood Computation Object Detection Map State Sequence Piggy-backing Violation Foreground Mask Access Point Novel Observation Model Background Subtraction Fore-ground Mask Detection Precision Complete Cctv Video Surveillance System Algorithm Trajectory Multi-object Confusion Previous Observation Current Time Instance Hidden Markov Model Object Detector Multi-object Configuration Optimal State Sequence Viola-tion Detection Rate Unknown Time-varying Number Pixel-wise Object Detection Score |
| Content Type | Text |
| Resource Type | Article |
