UXOTi_NPA_11_class dataset
收藏NIAID Data Ecosystem2026-03-14 收录
下载链接:
https://figshare.com/articles/dataset/UXOTi_NPA_11_class_dataset/21688661
下载链接
链接失效反馈官方服务:
资源简介:
Evaluation dataset UXOTi_NPA–an abbreviation that stands for UneXploded Ordnance Thermal images provided by Norwegian People's Aid–for this research was constructed as follows. The raw data was provided by the humanitarian organization Norwegian People’s Aid which collected videos about unexploded ordnances during a project in Bosnia and Herzegovina in 2019. Thermal imaging sensor was mounted on the UAV that surveyed the area at a height of 3 meters. A very small Ground Sampling Distance (GSD) was achieved with such a configuration. These videos were acquired by the thermal imager Zenmuse XT with a dimension of 720x480 pixels at 30 Hz frame rate. Pixel pitch was 17 μm, sensitivity (NEdT) <50mK at focal length f/1.0, and a field of view was 69°x56°. Videos were stored in mp4 format. Image sequences were grabbed from the full videos by using VirtualDub software. These clips were about 25 seconds long and show the UAV's flight over the targets. We annotated videos semi-automatically by using Computer Vision Annotation Tool (CVAT). Positions of objects’ annotations were manually corrected after every 5 to 6 frames. The evaluation dataset consists of 808 thermal images of dimensions of 720x480 pixels extracted from the above-described video clips, whenever at least one target (UXO) was present in the image. The number of objects per image varied between one to three.
本研究使用的评估数据集UXOTi_NPA——全称为挪威人民援助会(Norwegian People's Aid)提供的未爆炸弹药(Unexploded Ordnance, UXO)热成像数据集——构建流程如下。原始数据由人道主义组织挪威人民援助会提供,该机构于2019年在波斯尼亚和黑塞哥维那的一项项目中收集了未爆炸弹药相关视频。热成像传感器搭载于无人机(Unmanned Aerial Vehicle, UAV)平台,在3米高度开展区域勘测,该配置实现了极小的地面采样距离(Ground Sampling Distance, GSD)。所用热成像仪为Zenmuse XT,采集的视频分辨率为720×480像素,帧率30 Hz,像素间距17 μm,焦距f/1.0时的灵敏度(噪声等效温差Noise Equivalent Temperature Difference, NEdT)小于50 mK,视场角为69°×56°。视频以mp4格式存储。研究人员使用VirtualDub软件从完整视频中提取图像序列,这些剪辑片段时长约25秒,展现了无人机飞越目标区域的过程。研究团队采用计算机视觉标注工具(Computer Vision Annotation Tool, CVAT)对视频进行半自动标注,每5至6帧后手动修正目标标注位置。本评估数据集共包含808张分辨率为720×480像素的热成像图像,均从上述视频片段中提取,且每张图像中至少包含一个未爆炸弹药目标。单张图像中的目标数量介于1至3个之间。
创建时间:
2022-12-07



