通过估算相机角度实现更准的多目标跟踪，解决遮挡与深度误判问题。
CAMOT: Camera Angle-aware Multi-Object Tracking
- 基于物体检测估计相机视角，结合平面假设推算深度。
- 在MOT17上使ByteTrack达到63.8% HOTA、80.6% MOTA，性能领先。
- 轻量级设计，计算开销远低于现有深度估计算法，适合实时应用。
本文提出CAMOT，一种用于多目标跟踪的简单相机角度估计方法，旨在解决遮挡和深度方向估计不准的问题。在假设视频帧中多个目标位于同一平面上的前提下，CAMOT利用物体检测结果估计相机角度，并推算各目标的深度，实现伪3D多目标跟踪。我们在MOT17和MOT20数据集上将CAMOT集成到多种2D多目标跟踪方法中进行评估，验证了其有效性。将CAMOT应用于ByteTrack，在MOT17上获得63.8% HOTA、80.6% MOTA和78.5% IDF1，达到当前最优水平。该方法计算成本显著低于现有的基于深度学习的跟踪深度估计算法。
原文摘要 · Abstract (English)
This paper proposes CAMOT, a simple camera angle estimator for multi-object tracking to tackle two problems: 1) occlusion and 2) inaccurate distance estimation in the depth direction. Under the assumption that multiple objects are located on a flat plane in each video frame, CAMOT estimates the camera angle using object detection. In addition, it gives the depth of each object, enabling pseudo-3D MOT. We evaluated its performance by adding it to various 2D MOT methods on the MOT17 and MOT20 datasets and confirmed its effectiveness. Applying CAMOT to ByteTrack, we obtained 63.8% HOTA, 80.6% MOTA, and 78.5% IDF1 in MOT17, which are state-of-the-art results. Its computational cost is significantly lower than the existing deep-learning-based depth estimators for tracking.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。