Multiple Object Tracking by Trajectory Map Regression with Temporal Priors Embedding

Xingyu Wan, Sanping Zhou, Jinjun Wang, Rongye MengACM Multimedia 2021 · OpenReview

Abstract

Prevailing Multiple Object Tracking (MOT) works following the Tracking-by-Detection (TBD) paradigm pay most attention to either object detection in a first step or data association in a second step. In this paper, we approach the MOT problem from a different perspective by directly obtaining the embedded spatial-temporal information of trajectories from raw video data. For the purpose we propose a joint trajectory locating and attributes encoding framework for real-time, on-line MOT. We firstly introduce a trajectory attribute representation scheme designed for each tracked target (instead of object) where the extracted Trajectory Map (TM) encodes the spatial-temporal attributes of a trajectory across a window of consecutive video frames. Next we present a Temporal Priors Embedding (TPE) methodology to infer these attributes with a logical reasoning strategy based on long-term feature dynamics. The proposed MOT framework projects multiple attributes of tracked targets, e.g., presence, enter/exit, location, scale, motion, etc. into a continuous TM to perform one-shot regression for real-time MOT. Experimental results show that, our proposed video-based method runs at 33 FPS and is more accurate and robust as compared to the detection-based tracking methods and a few other State-of-the- Art (SOTA) approaches on MOT16/17/20 benchmarks.
BibTeX
@inproceedings{wan2021multiple,
  author = {Xingyu Wan and Sanping Zhou and Jinjun Wang and Rongye Meng},
  title = {{Multiple Object Tracking by Trajectory Map Regression with Temporal Priors Embedding}},
  booktitle = {ACM Multimedia},
  year = {2021},
  url = {https://openreview.net/forum?id=4jl2MQWUNPw},
}

Loading related content...

Figure