.png){kind=icon}
返回
NCT:noise-control multi-object tracking
.png){kind=icon}
OA
AI
DOI：10.1007/s40747-022-00946-9.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) is an important topic in computer vision. Recent MOT methods based on the anchor-free paradigm trade complicated hierarchical structures for tracking performance. However, existing anchor-free MOT methods ignore the noise in detection, data association, and trajectory reconnection stages, which results in serious problems, such as missing detection of small objects, insufficient motion information, and trajectory drifting. To solve these problems, this paper proposes Noise-Control Tracker (NCT), which focuses on the noise-control design of detection, association, and reconnection. First, a prior depth denoise method is introduced to suppress the fusion feature redundant noise, which can recover the gradient information of the heatmap fusion features. Then, the Smoothing Gain Kalman filter is designed, which combines the Gaussian function with the adaptive observation coefficient matrix to stabilize the mutation noise of Kalman gain. Finally, to address the drift noise issue, the gradient boosting reconnection context mechanism is designed, which realizes adaptive trajectory reconnection to effectively fill the gaps in trajectories. With the assistance of the plug-and-play noise-control method, the experimental results on MOTChallenge 16 & 17 datasets indicate that the NCT can achieve better performance than other state-of-the-art trackers.
Keyword:
Multi-object tracking
Fusion feature denoiser
Kalman filter
Trajectory reconnection
期刊
IF:
4.6
论文数:
2.1K
被引数:
6.6K
机构
引用论文
.png){kind=icon}
分享收藏分享收藏Structure, content, unsafe abbreviations, and completeness of discharge summaries: A retrospective analysis in a University Hospital in Austria出院小结的结构、内容、不安全缩写及完整性：奥地利一所大学医院的回顾性分析
OAAI
OAAI分享收藏分享收藏
查看更多内容