Journal
IEEE SIGNAL PROCESSING LETTERS
Volume 26, Issue 11, Pages 1613-1617Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSP.2019.2940922
Keywords
Target tracking; Trajectory; Feature extraction; Aggregates; Training; Benchmark testing; Multi-object tracking; tracklet association; appearance model; spatial-temporal attention
Categories
Funding
- Natural Science Foundation of China [61521002]
Ask authors/readers for more resources
Multi-object tracking (MOT) has wide applications in the fields of video analysis and signal processing. A major challenge in MOT is how to associate the noisy detections into long and continuous trajectories. In this letter, we address the association problem at the tracklet-level, and mainly focus on the appearance representation designed for tracklets. A multitask convolutional neural network is proposed to learn the discriminative features and spatial-temporal attentions jointly. In particular, we decompose an object in a static image with spatial attentions, and then aggregate multiple features in a tracklet based on the temporal attentions. Appearance misalignment that caused by occlusion and inaccurate bounding is then mitigated by multi-feature aggregation. Experimental results on two challenging MOT benchmarks have demonstrated the effectiveness of the proposed method and shown significant improvement on the quality of tracking identities.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available