five

SurgT

收藏
arXiv2025-09-30 收录
下载链接:
https://github.com/cartucho/surgt_benchmarking
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集名为SurgT,首次为评估软组织追踪方法提供了标准化的基准,包含了具有校准参数的立体内镜视频。该数据集分为训练集、验证集和测试集,其中训练集包含来自12个病例的125个视频,验证集包含来自3个病例的12个视频,测试集包含来自5个病例的20个视频。值得注意的是,只有验证集和测试集的视频被标注了边界框。整个数据集规模达到了157个立体内镜视频,其任务是进行软组织追踪评估。

This dataset, named SurgT, constitutes the first standardized benchmark for evaluating soft tissue tracking approaches, and comprises stereoscopic endoscopic videos equipped with calibration parameters. The dataset is split into three subsets: training set, validation set, and test set. The training set contains 125 videos from 12 clinical cases, the validation set includes 12 videos from 3 cases, and the test set holds 20 videos from 5 cases. It is worth noting that only the videos in the validation and test sets are annotated with bounding boxes. The overall dataset totals 157 stereoscopic endoscopic videos, and its dedicated task is soft tissue tracking evaluation.
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作