来源
红外和可见光的联合任务相关数据集 - 知乎
LLVIP Dataset(RGB-T Pedestrian Detection)
Jia X, Zhu C, Li M, et al. LLVIP: A visible-infrared paired dataset for low-light vision[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 3496-3504.
bupt-ai-cz/LLVIP: LLVIP: A Visible-infrared Paired Dataset for Low-light Vision (github.com)github.com/bupt-ai-cz/LLVIP
https://link.zhihu.com/?target=https%3A//github.com/bupt-ai-cz/LLVIP
适用方向：热红外和可见光行人检测
LLVIP数据集是在时间和空间上严格对齐的数据对。用于暗光条件下的红外和可见光的行人检测算法。
M3FD Dataset(RGB-T Object Detection)
Jinyuan Liu, Xin Fan*, Zhangbo Huang, Guanyao Wu, Risheng Liu , Wei Zhong, Zhongxuan Luo,“Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection”, IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), 2022.(Oral)
dlut-dimt/TarDAL: CVPR 2022 | Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection. (github.com)github.com/dlut-dimt/TarDALhttps://link.zhihu.com/?target=https%3A//github.com/dlut-dimt/TarDAL
适用方向：热红外和可见光图像目标检测
DUT-VTUAV Dataset(Visble-thermal UAV Tracking)
Zhang P, Zhao J, Wang D, et al. Visible-thermal UAV tracking: A large-scale benchmark and new baseline[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 8886-8895.
zhang-pengyu/DUT-VTUAV: Visible-Thermal UAV Tracking: A Large-Scale Benchmark (CVPR2022) (github.com)github.com/zhang-pengyu/DUT-VTUAVhttps://link.zhihu.com/?target=https%3A//github.com/zhang-pengyu/DUT-VTUAV
适用方向：Visble-thermal UAV Tracking
一个新的数据集，用于无人机的单目标跟踪。基于热红外和可见光图像。
KAIST Dataset(RGB-T Pedestrian Detection)
S. Hwang, J. Park, N. Kim, Y. Choi and I. S. Kweon, "Multispectral pedestrian detection: Benchmark dataset and baseline," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 1037-1045, doi: 10.1109/CVPR.2015.7298706.
SoonminHwang/rgbt-ped-detection: KAIST Multispectral Pedestrian Detection Benchmark [CVPR '15] (github.com)github.com/SoonminHwang/rgbt-ped-detectionhttps://link.zhihu.com/?target=https%3A//github.com/SoonminHwang/rgbt-ped-detection
适用方向：热红外和可见光的联合行人检测
FLIR Dataset(RGB-T object detection)
FREE - FLIR Thermal Dataset for Algorithm Trainingwww.flir.com/oem/adas/adas-dataset-form/正在上传…重新上传取消https://link.zhihu.com/?target=https%3A//www.flir.com/oem/adas/adas-dataset-form/
适用方向：热红外和可见光的联合目标检测
10k张可将光-红外图像对，但是没有对准，进行融合前需校正。
RoadScene Dataset(aligned infrared and visible images)
frostcza/RoadScene: Datasets: road-scene-infrared-visible-images, for feature matching, image registration, and image fusion (github.com)github.com/frostcza/RoadScenehttps://link.zhihu.com/?target=https%3A//github.com/frostcza/RoadScene
适用方向：红外和可见光图像融合
数据来源：从FLIR数据集中选取出，经过精细配准得到。
该数据集为对齐的图片，没有语义标签。
Freiburg Thermal Dataset(仅有数据，没有标注)
J. Vertens, J. Zürn and W. Burgard, "HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images," 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, 2020, pp. 8461-8468, doi: 10.1109/IROS45743.2020.9341192.
http://thermal.cs.uni-freiburg.de/thermal.cs.uni-freiburg.de/https://link.zhihu.com/?target=http%3A//thermal.cs.uni-freiburg.de/
LSOTB-TIR(Thermal Infrared Object Tracking)
LSOTB-TIR: A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark
QiaoLiuHit/LSOTB-TIR: LSOTB-TIR: A Large-Scale High-Diversity Thermal Infrared Object Tracking Benchmark (ACM MM2020) (github.com)github.com/QiaoLiuHit/LSOTB-TIR
适用方向：Thermal Infrared Object Tracking
