用单目深度信息提升跟踪精度，无需训练即可实现最佳效果
Depth-Aware Scoring and Hierarchical Alignment for Multiple Object Tracking
- 引入零样本深度估计作为独立关联特征
- 提出分层对齐评分，融合框级与像素级匹配，提升准确率
- 无需训练，适合实时场景和资源受限系统
当前基于运动的多目标跟踪（MOT）方法严重依赖交并比（IoU）进行目标关联，缺乏3D特征时在遮挡或外观相似场景下表现不佳。本文提出一种新颖的深度感知框架，通过零样本方式估计深度，并将其作为关联过程中的独立特征。同时引入分层对齐评分（Hierarchical Alignment Score），在不增加可学习参数的前提下，结合粗粒度边界框重叠与细粒度（像素级）对齐，显著提升关联精度。据我们所知，这是首个将3D特征（单目深度）作为独立决策矩阵用于关联步骤的MOT框架。该方法在多个挑战性基准上实现领先性能，且无需任何训练或微调。代码已开源：https://github.com/Milad-Khanchi/DepthMOT
原文摘要 · Abstract (English)
Current motion-based multiple object tracking (MOT) approaches rely heavily on Intersection-over-Union (IoU) for object association. Without using 3D features, they are ineffective in scenarios with occlusions or visually similar objects. To address this, our paper presents a novel depth-aware framework for MOT. We estimate depth using a zero-shot approach and incorporate it as an independent feature in the association process. Additionally, we introduce a Hierarchical Alignment Score that refines IoU by integrating both coarse bounding box overlap and fine-grained (pixel-level) alignment to improve association accuracy without requiring additional learnable parameters. To our knowledge, this is the first MOT framework to incorporate 3D features (monocular depth) as an independent decision matrix in the association step. Our framework achieves state-of-the-art results on challenging benchmarks without any training nor fine-tuning. The code is available at https://github.com/Milad-Khanchi/DepthMOT
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。