Anomaly Detection with Laser Heat Treatment Thermal Videos

This data set comprises 4223 videos from a laser surface heat treatment process (also called laser heat treatment) applied to cylindrical workpieces made of steel. The purpose of the dataset is to detect anomalies in the laser heat treatment learning a model from a set of non-anomalous videos.In the laser heat treatment, the laser beam is following a pattern similar to an "eight" with a frequency of 100 Hz. This pattern is sometimes modified to avoid obstacles in the workpieces.The videos are recorded at a frequency of 1000 frames per second with a thermal camera. The thermal camera pixel values range from 0 to 1024, where higher values means higher temperatures. The thermal camera has a resolution of 32x32 pixels, but a region of interest (ROI) is applied to the videos, so only the laser heat treatment is shown in the videos.

本数据集包含4223段激光表面热处理（laser surface heat treatment，亦称激光热处理）工艺视频，处理对象为钢制圆柱工件。本数据集旨在通过一批无异常视频样本训练模型，以实现激光热处理过程的异常检测。在该激光热处理流程中，激光束以100Hz的频率沿类似“8”字形的路径运动；为避让工件上的障碍物，该运动路径有时会被调整。本数据集的视频均由热成像相机以1000帧/秒的帧率录制。热成像相机的像素值取值范围为0至1024，像素值越高代表工件温度越高。该相机的原始分辨率为32×32像素，但视频已应用感兴趣区域（region of interest，ROI）裁剪，最终仅保留激光热处理区域的画面。