UVT20K
收藏资源简介:
UVT20K是由安徽大学智能计算与信号处理教育部重点实验室创建的大规模非对齐RGB-T显著目标检测数据集,包含20,000对未对齐的可见光和热成像图像,覆盖407个场景和1256个对象类别。数据集通过真实场景采集,包含多种挑战,如低光照、图像杂乱和复杂显著对象等。每个样本都经过详细的标注,包括显著性掩码、涂鸦、边界和挑战属性。数据集的创建旨在推动非对齐RGB-T显著目标检测的研究,解决复杂场景下的目标检测问题。
UVT20K is a large-scale unaligned RGB-T salient object detection dataset developed by the Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education, Anhui University. It consists of 20,000 pairs of unaligned visible and thermal imaging images, covering 407 scenarios and 1256 object categories. The dataset is collected from real-world environments, and encompasses various challenges including low-light conditions, cluttered scenes, and complex salient objects. Each sample is equipped with detailed annotations, namely saliency masks, scribbles, bounding boxes, and challenge attributes. The dataset is constructed to advance research on unaligned RGB-T salient object detection and address target detection problems in complex scenarios.

- 1Alignment-Free RGB-T Salient Object Detection: A Large-scale Dataset and Progressive Correlation Network智能计算与信号处理教育部重点实验室,安徽多模态认知计算省级重点实验室,安徽大学计算机科学与技术学院 · 2024年



