Parsing human skeletons in an operating room
Parsing human skeletons in an operating room
复制标题
DOI：
10.1007/s00138-016-0792-4
复制
发表时间：
2016-10-01
影响因子：
3.3
通讯作者：
Navab, Nassir
中科院分区：
文献类型：
--
作者：
Belagiannis, Vasileios;Wang, Xinchao;Navab, Nassir
多人姿态估计是一个重要而又具有挑战性的问题。在手术室(OR)环境中，外科医生和医务人员的3D身体姿势可以为手术工作流程分析提供重要线索。为此，我们提出了一种在多摄像机设置的OR环境中定位和恢复多个人的身体姿势的算法。我们的模型建立在3D图片结构和2D身体部位定位的基础上，使用卷积神经网络(ConvNets)。为了评估我们的算法，我们引入了一个在真实的OR环境中捕获的数据集。我们的数据集是独一无二的，具有挑战性，并公开提供带注释的基本事实。我们提出的算法在这个数据集上得到了有希望的位姿估计结果。
Multiple human pose estimation is an important yet challenging problem. In an operating room (OR) environment, the 3D body poses of surgeons and medical staff can provide important clues for surgical workflow analysis. For that purpose, we propose an algorithm for localizing and recovering body poses of multiple human in an OR environment under a multi-camera setup. Our model builds on 3D Pictorial Structures and 2D body part localization across all camera views, using convolutional neural networks (ConvNets). To evaluate our algorithm, we introduce a dataset captured in a real OR environment. Our dataset is unique, challenging and publicly available with annotated ground truths. Our proposed algorithm yields to promising pose estimation results on this dataset.