BuildCrack
收藏资源简介:
BuildCrack是由海得拉巴国际信息技术学院创建的一个新的建筑裂缝数据集,旨在提高建筑结构裂缝分割的准确性。该数据集通过无人机搭载的相机从不同角度和距离拍摄建筑立面图像,包含358张图像,具有低对比度、遮挡和阴影等挑战性特征。数据集的创建过程结合了无人机技术和图像处理技术,确保了数据的质量和多样性。BuildCrack主要应用于建筑结构的裂缝检测和分割,旨在解决现有算法在不同数据集上泛化能力不足的问题。
BuildCrack is a novel building crack dataset developed by the International Institute of Information Technology, Hyderabad, aimed at improving the accuracy of building structural crack segmentation. This dataset comprises 358 images of building facades captured by drone-mounted cameras from diverse angles and distances, featuring challenging characteristics such as low contrast, occlusions, and shadows. The dataset was constructed by integrating drone technology and image processing techniques to ensure high data quality and diversity. Primarily applied to crack detection and segmentation of building structures, BuildCrack aims to address the issue of insufficient generalization capability of existing algorithms across different datasets.




