3dStool
收藏资源简介：
The 3D surgical tool dataset (3dStool) has been constructed with the aim of assisting the development of computer vision techniques that address the operating room. Note, functions for visualisation, processing, and splitting the dataset can be found in the relevant github repository. Specifically, even though laparoscopic scenes have received a lot of attention in terms of labelled images, surgical tools that are used at initial stages of an operation, such as scalpels and scissors, have not had any such datasets developed. 3dStool includes 5370 images, accompanied by manually drawn polygon labels, as well as information on the 3D pose of these tools in operation. The tools were recorded while operating on a cadaveric knee. A RealSense D415 was used for image collection, while an optical tracker was employed for the purpose of 3D pose recording. Four surgical tools have been collected for now: Scalpel Scissors Forceps Electric Burr An annotation json file (in the format of COCO) exists for the images, containing the masks, boxes, and other relevant information. Furthermore, pose information is provided in two different manners. Firstly, a csv in the following format: CSV Structure Column 1 2 3 4 5 6 7 8 9 Value X (m) Y (m) Z (m) qi qj qk ql Class Image Name Position and orientation are both provided in the coordinate axes of the camera used to obtain the data (Realsense D415, Intel, USA). Pose is provided in the form of quaternions, however it is possible to convert this format into other available notations. The pose data can also be combined with the masks in the form of a final json file, in order to obtain a final COCO-format json with object poses as well. In the data provided, each of the test, train and validation subsets have their own COCO-like json files with the poses fused within, although the "orignal_jsons" only provide the image masks. The files and directories are structured as follows. Note that this example is based on the "train" directory, but a similar structure has been created for the test and val sets: Train manual_json - Contains the json created when manually annotating, the images, therefore no pose data included pose - Contains the CSV file with the poses of the relevant images, explained in the table above pose_json - Contains the fused json that includes both the annotations and the pose data for each image surgical2020 - Contains the images in jpg format
3D手术工具数据集（3dStool）的构建目标是助力适配手术室场景的计算机视觉技术研发。请注意，该数据集的可视化、处理与拆分相关功能可在对应GitHub仓库中获取。尽管腹腔镜场景的标注图像研究已受到广泛关注，但针对手术初期使用的手术器械（如手术刀、剪刀），目前尚无同类数据集问世。3dStool数据集共包含5370张图像，配套有手动绘制的多边形标注，以及手术器械在操作中的3D位姿信息。 该数据集采集自尸体膝关节手术场景。图像采集使用RealSense D415相机，3D位姿记录则借助光学追踪器完成。目前已收录四类手术器械：手术刀（Scalpel）、剪刀（Scissors）、持针器（Forceps）、电动骨钻（Electric Burr）。 数据集配有COCO（Common Objects in Context）格式的标注JSON文件，涵盖掩码、边界框及其他相关信息。此外，位姿信息以两种不同形式提供：其一为遵循如下格式的CSV（逗号分隔值，Comma-Separated Values）文件： CSV结构 列号 1 2 3 4 5 6 7 8 9 字段 X（米） Y（米） Z（米） qi qj qk ql 类别 图像文件名 位姿信息与空间位置均采用采集图像所用相机（英特尔RealSense D415，美国英特尔公司）的坐标系。位姿以四元数形式给出，也可转换为其他通用表示格式。 此外，位姿数据也可与掩码结合，生成包含目标位姿信息的最终COCO格式JSON文件。在本次发布的数据中，测试集、训练集与验证集均各自配备融合了位姿信息的类COCO JSON文件，而"original_jsons"仅提供图像掩码标注。 以下为文件与目录的组织形式。本示例基于"train"训练集目录，测试集与验证集采用相同的目录结构： Train ├─ manual_json：包含手动标注生成的JSON文件与图像，不包含位姿数据 ├─ pose：存放前文说明的图像位姿CSV文件 ├─ pose_json：包含融合了标注信息与每幅图像位姿数据的整合JSON文件 └─ surgical2020：存放JPG格式的手术图像
