VT-Tiny-MOT

该数据集是首个针对融合了RGB和热成像技术的小型多目标追踪的基准测试，它评估了在可见光和热成像模态下的追踪性能。该数据集包含了用于评估的多种指标，如MOTA、IDF1和HOTA，专为评估RGBT视频中的多目标追踪器的性能而设计。该任务专注于多目标追踪。

This dataset is the first benchmark for small-scale multi-object tracking (MOT) that integrates RGB and thermal imaging technologies. It evaluates tracking performance under both visible light and thermal imaging modalities. Equipped with multiple evaluation metrics including MOTA, IDF1 and HOTA, this dataset is specifically designed to assess the performance of multi-object trackers in RGB-Thermal (RGBT) videos. This task focuses on multi-object tracking.

搜集汇总

背景与挑战

背景概述

VT-Tiny-MOT是一个用于RGB-T视频中多小目标跟踪的数据集，属于HGTMT项目的一部分，可通过百度云下载。该数据集支持论文《Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos》的研究。