We propose an online multiple object tracking algorithm that exploits optical flow and convolutional features to handle noisy detections as well as frequent occlusion. To achieve robust tracking, we develop a data association method that deals with tracking scenarios of increasing difficulty. For easy scenarios, we use motion affinity to associate detections with objects. For ambiguous situations, we propose to use an appearance model based on convolutional features and correlation filters to complement template matching methods. For difficult cases where objects are under heavy occlusion, we carry out occlusion analysis, which exploits the relationship between targets and occluders to predict potential object locations. To deal with noisy detections, false positives are detected and removed on both raw detection and tracklet levels, while missing and inaccurate detections are recovered or corrected via short-term tracking. Experimental results on two benchmark datasets demonstrate that the proposed online algorithm performs favorably against the state-of-the-art methods.
|Title of host publication||2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings|
|Publisher||IEEE Computer Society|
|Number of pages||5|
|Publication status||Published - 2018 Feb 20|
|Event||24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China|
Duration: 2017 Sep 17 → 2017 Sep 20
|Name||Proceedings - International Conference on Image Processing, ICIP|
|Other||24th IEEE International Conference on Image Processing, ICIP 2017|
|Period||17/9/17 → 17/9/20|
Bibliographical noteFunding Information:
In this paper, we propose an online multiple object tracking algorithm. The proposed data association scheme uses motion, appearance affinities and occlusion analysis to solve object-detection assignments for different cases of increasing difficulty. To ensure reliable association, a convolutional correlation filter is adopted to compliment the template matching module based on optical flow. The CCF is also used to analyze visual tracking results to handle missing and inaccurate detections, as well as for robust association in occlusion analysis. Experimental results on two challenging benchmark datasets show that the proposed online algorithm performs favorably against the state-of-the-art methods. Acknowledgement Lu Wang is supported in part by Chinese Scholarship Council, in part by NSFC #61202258, and in part by NSF of Liaoning, China #20170540312 .
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Signal Processing