RGB-T Object Tracking: Benchmark and Baseline

By Chenglong Li, Xinyan Liang, Yijuan Lu, Nan Zhao, Jin Tang. Pattern Recognition, 2018

585 citations recorded by the source corpus.

RGB-Thermal (RGB-T) object tracking receives more and more attention due to the strongly complementary benefits of thermal information to visible data. However, RGB-T research is limited by lacking a comprehensive evaluation platform. In this paper, we propose a large-scale video benchmark dataset for RGB-T this http URL 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 pre- or 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.

Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/1975bee228ac228df235d20777e32331bb21566d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

The Seventh Visual Object Tracking VOT2019 Challenge Results (2019, methodology): “The VOT committee decided to base the VOT-RGBT-challenge on the existing RGBT-dataset published by [60].”
LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Images (2023, background): “In recent years, several multi-modal datasets have been released: KAIST [25], RGBT-234 [26], and RoadScene [27].”
Visible and Infrared Image Fusion Using Deep Learning (2023, methodology): “Indeed, almost all existing RGB-infrared datasets, such as LasHeR [183], RGBT234 [9] and M 3 FD [115], have some issues of misalignment.”
LasHeR: A Large-Scale High-Diversity Benchmark for RGBT Tracking (2021, methodology): “[4] extend RGBT210 to a larger dataset called RGBT234, containing 234 RGBT videos, to improve annotation quality and include more challenges.”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, unknown): “Yet the pursue of time eﬃciency models is not easy to accomplish.”
MDLatLRR: A Novel Decomposition Method for Infrared and Visible Image Fusion (2018, background): “It arises in many applications, such as surveillance [41], object detection and target recognition [11], [15], [16].”
RFN-Nest: An end-to-end residual fusion network for infrared and visible images (2021, background): “It has many applications, such as object tracking [1] [2] [3], self-driving and video surveillance [4].”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, background): “1) with a broad extent of categories and applications; including self-driving cars [1]–[4], autonomous robots [5], [6], surveillance [7]– [10], augmented reality [11]–[13], unmanned aerial vehicle (UAV) tracking [14], sports [15], surgery [16], biology [17]– [19], ocean exploration [20], to name a f”