多目标跟踪中的检测跟踪范式：综述与实验

中文摘要 AI 辅助

多目标跟踪（MOT）是一项重要的计算机视觉任务，它同时跟踪视频序列中的多个目标，在监控、自主导航和人机交互等领域有着广泛的应用。检测跟踪（TBD）范式将目标检测与时间关联相结合，在创新算法的推动下已成为主流方法。尽管近年来取得了进展，但对基于TBD的方法进行公平评估仍然是一个挑战。许多研究引入了相似度度量、数据关联策略或运动模型等模块，但这些模块往往在不一致的协议下进行评估，使用了不同的基线跟踪器、超参数和数据集。这种不一致性掩盖了每个模块的真实贡献，并阻碍了客观比较。本综述系统地回顾了基于TBD的MOT技术，包括相似度度量、数据关联、相机运动补偿和插值策略。从最简基线跟踪器出发，我们在不同数据集上公平地评估了每种方法的贡献，并积累了均衡良好的方法。我们的研究结果建立了一个强基线跟踪器，并为设计适用于实际部署的鲁棒且通用的MOT系统提供了原则性基础。

英文摘要

Multi-object tracking (MOT) is an essential computer vision task that simultaneously tracks multiple objects in video sequences, with various applications in surveillance, autonomous navigation, and human-computer interaction. The tracking-by-detection (TBD) paradigm, which combines object detection with temporal association, has emerged as a leading approach, driven by innovative algorithms. Despite recent progress, fair evaluation of TBD-based methods remains a challenge. Many studies introduce modules such as similarity metrics, data association strategies, or motion models, but they are often evaluated under inconsistent protocols, with different baseline trackers, hyperparameters, and datasets. Such inconsistencies obscure the genuine contribution of each module and hinder objective comparison. This survey systematically reviews TBD-based MOT techniques, including similarity measurements, data association, camera motion compensation, and interpolation strategies. Starting from a minimal baseline tracker, we fairly evaluate the contributions of each method across diverse datasets and accumulate well-balanced methods. Our findings establish a strong baseline tracker and provide a foundation for the principled design of robust and versatile MOT systems suitable for real-world deployment.

发表机构

• Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））

机构由 AI 辅助整理，请以论文原文为准。