Associative affinity network learning for multi-object tracking
Liang MA , Qiaoyong ZHONG , Yingying ZHANG , Di XIE , Shiliang PU
Front. Inform. Technol. Electron. Eng ›› 2021, Vol. 22 ›› Issue (9) : 1194 -1206.
Associative affinity network learning for multi-object tracking
We propose a joint feature and metric learning deep neural network architecture, called the associative affinity network (AAN), as an affinity model for multi-object tracking (MOT) in videos. The AAN learns the associative affinity between tracks and detections across frames in an end-to-end manner. Considering flawed detections, the AAN jointly learns bounding box regression, classification, and affinity regression via the proposed multi-task loss. Contrary to networks that are trained with ranking loss, we directly train a binary classifier to learn the associative affinity of each track-detection pair and use a matching cardinality loss to capture information among candidate pairs. The AAN learns a discriminative affinity model for data association to tackle MOT, and can also perform single-object tracking. Based on the AAN, we propose a simple multi-object tracker that achieves competitive performance on the public MOT16 and MOT17 test datasets.
Multi-object tracking / Deep neural network / Affinity learning
Zhejiang University Press
/
| 〈 |
|
〉 |
PDF
(12632KB)
