SearchTrack: Multiple Object Tracking with Object-Customized Search and Motion-Aware Features
ZHONG MIN TSAI (National Taiwan University), YU-JU TSAI (National Taiwan University),* Chien-Yao Wang (Institute of Information Science, Academia Sinica), Hong-Yuan Mark Liao (Institute of Information Science, Academia Sinica, Taiwan), Youn-Long Lin (National Tsing Hua University), Yung-Yu Chuang (National Taiwan University)
The 33rd British Machine Vision Conference
Abstract
The paper presents a new method, SearchTrack, for multiple object tracking and segmentation (MOTS). To address the association problem between detected objects, SearchTrack proposes object-customized search and motion-aware features. By maintaining a Kalman filter for each object, we encode the predicted motion into the motion-aware feature, which includes both motion and appearance cues. For each object, a customized fully convolutional search engine is created by SearchTrack by learning a set of weights for dynamic convolutions specific to the object. Experiments demonstrate that our SearchTrack method outperforms competitive methods on both MOTS and MOT tasks, particularly in terms of association accuracy. Our method achieves 71.5 HOTA (car) and 57.6 HOTA (pedestrian) on the KITTI MOTS and 53.4 HOTA on MOT17. In terms of association accuracy, our method achieves state-of-the-art performance among 2D online methods on the KITTI MOTS. Our code is available at https://github.com/qa276390/SearchTrack.Video
Citation
@inproceedings{TSAI_2022_BMVC,
author = {ZHONG MIN TSAI and YU-JU TSAI and Chien-Yao Wang and Hong-Yuan Mark Liao and Youn-Long Lin and Yung-Yu Chuang},
title = {SearchTrack: Multiple Object Tracking with Object-Customized Search and Motion-Aware Features},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0055.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by