Synthetic Pavement Crack Dataset for Object Detection

A dataset containing 3,346 synthetically generated RGB images of road segments with cracks. Road segments and crack formations created in Blender, data collected in Microsoft AirSim. Data is split into train (~70%), test (~15%), and validation (~15%) folders. Contains ground truth bounding boxes labelling cracks in both YOLO and COCO JSON format.

本数据集包含3346张合成生成的带裂缝道路片段的RGB图像。道路片段与裂缝形态均通过Blender创建，数据采集自Microsoft AirSim。数据集被划分为训练集（约70%）、测试集（约15%）与验证集（约15%）三个文件夹。数据集包含用于标注裂缝的真值边界框，支持YOLO与COCO JSON两种格式。