.png){kind=icon}
返回
Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking
.png){kind=icon}
OA
AI
DOI：10.1109/TMM.2024.3394683.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multi-Object Tracking (MOT) remains a vital component of intelligent video analysis, which aims to locate targets and maintain a consistent identity for each target throughout a video sequence. Existing works usually learn a discriminative feature representation, such as motion and appearance, to associate the detections across frames, which are easily affected by mutual occlusion and background clutter in practice. In this paper, we propose a simple yet effective two-stage feature learning paradigm to jointly learn single-shot and multi-shot features for different targets, so as to achieve robust data association in the tracking process. For the detections without being associated, we design a novel single-shot feature learning module to extract discriminative features of each detection, which can efficiently associate targets between adjacent frames. For the tracklets being lost several frames, we design a novel multi-shot feature learning module to extract discriminative features of each tracklet, which can accurately refind these lost targets after a long period. Once equipped with a simple data association logic, the resulting VisualTracker can perform robust MOT based on the single-shot and multi-shot feature representations. Extensive experimental results demonstrate that our method has achieved significant improvements on MOT17 and MOT20 datasets while reaching state-of-the-art performance on DanceTrack dataset.
Keyword:
Target tracking
Feature extraction
Tracking
Representation learning
Object detection
Visualization
Task analysis
Multi-object tracking
discriminative feature learning
data association
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
A Simple but Effective Method for Balancing Detection and Re-Identification in Multi-Object Tracking
PREAI
分享收藏
查看更多内容