.png){kind=icon}
返回
Multi-object Tracking with Spatial-Temporal Tracklet Association
.png){kind=icon}
PRE
AI
DOI：10.1145/3635155.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, the tracking-by-detection methods have achieved excellent performance in Multi-Object Tracking (MOT), which focuses on obtaining a robust feature for each object and generating tracklets based on feature similarity. However, they are confronted with two issues: (1) unstable features in short-term occlusion and (2) insufficient matching in long-term occlusion. Specifically, the unstable feature is caused by the appearance variation under occlusion, and the association with the current unstable feature will lead to insufficient matching in long-term occlusion. To address the above issues, we propose a two-stage tracklet-level association method, Spatial-Temporal Tracklet Association (STTA), to effectively combine spatial-temporal context between feature extraction and data association. In the first stage, we propose the Tracklet-guided Spatial-Temporal Attention network (TSTA) to generate robust and stable features. Specifically, TSTA captures spatial-temporal context to obtain the most salient regions between the current and previous clips. In the second stage, we design the Bi-Tracklet Spatial-Temporal association (BTST) module to fully exploit the spatial-temporal context in data association. Specifically, we leverage BTST to merge different tracklets into long-term trajectories by jointly learning visual feature and spatial-temporal context and designing a bidirectional interpolation to recover the missed objects between matched tracklets. Extensive experiments of public and private detections on four benchmarks demonstrate the robustness of STTA. Furthermore, the proposed method is a model-agnostic method, which can be plugged and played with existing methods to boost their performance, e.g., obtain 11.0%, 10.1%, 2.9%, 3.2%, and 7.8% improvement on IDF1 in the MOT16 validation dataset for Tracktor, CenterTrack, Deepsort, JDE, and CTracker, respectively.
Keyword:
Multi-object tracking
spatial-temporal tracklet association
tracklet-guided spatial-temporal attention network
bi-tracklet spatial-temporal association
期刊
IF:
6
论文数:
2.0K
被引数:
5.4K
机构
引用论文
.png){kind=icon}
PANet: An End-to-end Network Based on Relative Motion for Online Multi-object TrackingPANet: 一种基于相对运动的在线多目标跟踪端到端网络
OAAI
OAAI分享收藏
查看更多内容