LIB-HSI: RGB and Hyperspectral images of Building Facades

The LIB-HSI dataset contains hyperspectral reflectance images and their corresponding RGB images of building façades in a light industrial environment. The dataset also contains pixel-level annotated images for each hyperspectral/RGB image. The LIB-HSI dataset was created to develop deep learning methods for segmenting building facade materials. The images were captured using a Specim IQ hyperspectral camera. The hyperspectral images are in the ENVI format. There are 393 training images, 45 validation images and 75 test images. If you use this data, please cite the following paper: Habili, Nariman, Ernest Kwan, Weihao Li, Christfried Webers, Jeremy Oorloff, Mohammad Ali Armin, and Lars Petersson. "A Hyperspectral and RGB Dataset for Building Façade Segmentation." In Computer Vision–ECCV 2022 Workshops: Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part VII, pp. 258-267. Cham: Springer Nature Switzerland, 2023. @inproceedings{habili2023hyperspectral, title={A Hyperspectral and RGB Dataset for Building Fa{\c{c}}ade Segmentation}, author={Habili, Nariman and Kwan, Ernest and Li, Weihao and Webers, Christfried and Oorloff, Jeremy and Armin, Mohammad Ali and Petersson, Lars}, booktitle={Computer Vision--ECCV 2022 Workshops: Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part VII}, pages={258--267}, year={2023}, organization={Springer} }LIB-HSI数据集包含轻工业环境下建筑立面的高光谱反射率图像（hyperspectral reflectance image）及其对应的RGB图像。该数据集还为每一张高光谱/RGB图像配套提供了像素级标注图像。本数据集旨在研发用于建筑立面材料分割的深度学习方法。所有图像均由Specim IQ高光谱相机采集。高光谱图像采用ENVI格式存储。数据集划分为393张训练集图像、45张验证集图像与75张测试集图像。若使用本数据集，请引用以下论文：Habili, Nariman、Ernest Kwan、Weihao Li、Christfried Webers、Jeremy Oorloff、Mohammad Ali Armin及Lars Petersson所著《用于建筑立面分割的高光谱与RGB数据集》，收录于《计算机视觉——ECCV 2022研讨会：2022年10月23日至27日，以色列特拉维夫，会议论文集 第七部分》，第258-267页，瑞士施普林格自然（Springer Nature Switzerland），2023年。对应的BibTeX引用格式为：@inproceedings{habili2023hyperspectral, title={A Hyperspectral and RGB Dataset for Building Façade Segmentation}, author={Habili, Nariman and Kwan, Ernest and Li, Weihao and Webers, Christfried and Oorloff, Jeremy and Armin, Mohammad Ali and Petersson, Lars}, booktitle={Computer Vision--ECCV 2022 Workshops: Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part VII}, pages={258--267}, year={2023}, organization={Springer} }

搜集汇总

背景与挑战

背景概述

LIB-HSI数据集是一个专注于建筑立面材料分割的高光谱和RGB图像数据集，包含高光谱反射率图像及其对应的RGB图像，总计513张图像（393张训练、45张验证、75张测试），并附带像素级标注。该数据集旨在支持深度学习方法的开发，用于自动化建筑立面材料分类，适用于计算机视觉和机器学习研究领域，数据以ENVI格式存储，拍摄于轻工业环境。