Abstract—RGB-Thermal (RGB-T) object tracking receives more and more attention due to the…
- User
Abstract—RGB-Thermal (RGB-T) object tracking receives more and more attention due to the strongly complementary benefits of thermal information to visible data. However, RGBT research is limited by lacking a comprehensive evaluation platform. In this paper, we propose a large-scale video benchmark dataset for RGB-T tracking. It has three major advantages over existing ones: 1) Its size is sufficiently large for large-scale performance evaluation (total frame number: 234K, maximum frame per sequence: 8K). 2) The alignment between RGB-T sequence pairs is highly accurate, which does not need preor post-processing. 3) The occlusion levels are annotated for occlusion-sensitive performance analysis of different tracking algorithms. Moreover, we propose a novel graph-based approach to learn a robust object representation for RGB-T tracking. In particular, the tracked object is represented with a graph with image patches as nodes. This graph including graph structure, node weights and edge weights is dynamically learned in a unified ADMM (alternating direction method of multipliers)- based optimization framework, in which the modality weights are also incorporated for adaptive fusion of multiple source data. Extensive experiments on the large-scale dataset are executed to demonstrate the effectiveness of the proposed tracker against other state-of-the-art tracking methods. We also provide new insights and potential research directions to the field of RGB-T object tracking翻译为中文
- Assistant
摘要—由于热信息对可见光数据的强大互补效应,RGB热(RGB-T)目标跟踪越来越受到关注。然而,由于缺乏综合评估平台,RGB-T研究受到限制。在本文中,我们提出了一个用于RGB-T跟踪的大规模视频基准数据集。它相对于现有数据集有三个主要优势:1) 大小足够大,可进行大规模性能评估(总帧数:234K,每个序列的最大帧数:8K)。2) RGB-T序列对之间的对齐非常准确,不需要预处理或后处理。3) 提供了遮挡级别的注释,用于分析不同跟踪算法的遮挡敏感性能。此外,我们提出了一种基于图的方法,用于学习RGB-T跟踪的强大对象表示。特别地,跟踪对象由图表示,图的节点是图像块。该图包括图结构、节点权重和边权重,通过统一的基于ADMM(交替方向乘子法)的优化框架动态学习,在其中还融合了模态权重,以实现多源数据的自适应融合。对大规模数据集的广泛实验证明了所提方法相对于其他state-of-the-art跟踪方法的有效性。我们还为RGB-T目标跟踪领域提供了新的见解和潜在的研究方向。