ProgTrack：一种基于渐进匹配策略的多目标跟踪算法
ProgTrack: A Multi-Object Tracking Algorithm with Progressive Matching Strategy
针对无人机视角下的多尺度目标、遮挡、镜头抖动和高相似度目标等挑战，提出分阶段渐进匹配策略，可复用于其他跟踪场景中的困难样本匹配与外观-运动融合。
原文依据 we propose a multi-object tracking algorithm, ProgTrack, based on a multi-stage progressive matching mechanism
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于无人机的多目标跟踪（MOT）旨在识别并持续跟踪无人机飞行过程中多个地面目标的位置。当前主流方法利用外观匹配和运动匹配来匹配连续帧中的目标。然而，这些方法在以下场景中常常失效：第一，多尺度目标场景，其中小目标的外观特征较弱且边界框较小；第二，复杂背景或遮挡场景，其中背景或遮挡物干扰外观特征并改变目标的边界框尺寸；第三，无人机镜头抖动、旋转或缩放场景，导致连续帧之间出现错位；第四，目标高相似度场景，其中目标之间的外观特征难以区分，例如道路上的车辆。为解决这些问题，我们提出了一种基于多阶段渐进匹配机制的多目标跟踪算法ProgTrack。该算法模拟人眼跟踪策略，采用“先匹配容易匹配的大目标，再匹配难以匹配的小目标，最后匹配剩余的混合尺度目标”的渐进过程。类似地，ProgTrack针对不同尺度和外观的目标采用三种匹配策略：针对大目标的简单局部运动信息（LMI）匹配策略、针对小目标的复杂上下文增强特征（CE-Feature）匹配策略，以及针对多尺度目标的全局运动信息（GMI）匹配策略，从而实现目标匹配。在VisDrone2019无人机跟踪数据集上，ProgTrack的MOTA、MOTP和IDF1分数分别达到40.2、77.5和52.8，在十种方法中展现出最优性能。
英文原文摘要 1872 字符
Multi-object tracking (MOT) based on unmanned aerial vehicle (UAV) aims to identify and continuously track the positions of multiple ground targets during UAV flight. Current mainstream methods utilize appearance matching and motion matching to match targets in consecutive frames. However, these methods often fail in the following scenarios: First, scenarios with multi-scale targets, where small targets have weak appearance features and small bounding boxes; second, scenarios with complex backgrounds or occlusions, where the background or occlusions interfere with the appearance features and change the bounding box size of targets; third, scenarios where the UAV lens shakes, rotates, or zooms, leading to misalignment between consecutive frames; and fourth, scenarios with high targets similarity, where the appearance features between targets are difficult to distinguish, such as vehicles on a road. To address these issues, we propose a multi-object tracking algorithm, ProgTrack, based on a multi-stage progressive matching mechanism. This algorithm simulates human eye tracking strategies, employing a progressive process of "first matching easily matched large targets, then matching difficult-to-match small targets, and finally matching the remaining mixed-scale targets." Similarly, ProgTrack employs three strategies for target matching at different scales and appearances: a simple Local Motion Information (LMI) matching strategy for large targets, a complex Context Enhancement Feature (CE-Feature) matching strategy for small targets, and a Global Motion Information (GMI) matching strategy for multi-scale targets matching, thereby achieving target matching. On the VisDrone2019 UAV tracking dataset, ProgTrack achieves MOTA, MOTP, and IDF1 scores of 40.2, 77.5, and 52.8, respectively, demonstrating state-of-the-art performance among ten methods.