Trujillo-Jiménez Magda Alexandra, Navarro Pablo, Pazos Bruno, Morales Leonardo, Ramallo Virginia, Paschetta Carolina, De Azevedo Soledad, Ruderman Anahí, Pérez Orlando, Delrieux Claudio, Gonzalez-José Rolando
Laboratorio de Ciencias de las Imágenes, Departamento de Ingeniería Eléctrica y Computadoras, Universidad Nacional del Sur, and CONICET, Bahía Blanca B8000, Argentina.
Instituto Patagónico de Ciencias Sociales y Humanas, Centro Nacional Patagónico, CONICET, Puerto Madryn U9120, Argentina.
J Imaging. 2020 Sep 11;6(9):94. doi: 10.3390/jimaging6090094.
Current point cloud extraction methods based on photogrammetry generate large amounts of spurious detections that hamper useful 3D mesh reconstructions or, even worse, the possibility of adequate measurements. Moreover, noise removal methods for point clouds are complex, slow and incapable to cope with semantic noise. In this work, we present body2vec, a model-based body segmentation tool that uses a specifically trained Neural Network architecture. Body2vec is capable to perform human body point cloud reconstruction from videos taken on hand-held devices (smartphones or tablets), achieving high quality anthropometric measurements. The main contribution of the proposed workflow is to perform a background removal step, thus avoiding the spurious points generation that is usual in photogrammetric reconstruction. A group of 60 persons were taped with a smartphone, and the corresponding point clouds were obtained automatically with standard photogrammetric methods. We used as a 3D silver standard the clean meshes obtained at the same time with LiDAR sensors post-processed and noise-filtered by expert anthropological biologists. Finally, we used as gold standard anthropometric measurements of the waist and hip of the same people, taken by expert anthropometrists. Applying our method to the raw videos significantly enhanced the quality of the results of the point cloud as compared with the LiDAR-based mesh, and of the anthropometric measurements as compared with the actual hip and waist perimeter measured by the anthropometrists. In both contexts, the resulting quality of body2vec is equivalent to the LiDAR reconstruction.
当前基于摄影测量的点云提取方法会产生大量虚假检测结果，这会妨碍有用的三维网格重建，甚至更糟的是，会影响进行充分测量的可能性。此外，点云的噪声去除方法复杂、速度慢且无法处理语义噪声。在这项工作中，我们提出了body2vec，这是一种基于模型的人体分割工具，它使用经过专门训练的神经网络架构。Body2vec能够从手持设备（智能手机或平板电脑）拍摄的视频中进行人体点云重建，实现高质量的人体测量。所提出的工作流程的主要贡献在于执行背景去除步骤，从而避免摄影测量重建中常见的虚假点生成。一组60人用智能手机进行了拍摄，并使用标准摄影测量方法自动获取了相应的点云。我们将同时使用激光雷达传感器获取并由专业人类学生物学家进行后处理和噪声过滤得到的干净网格用作三维银标准。最后，我们将由专业人体测量师对同一批人的腰围和臀围进行的人体测量用作金标准。将我们的方法应用于原始视频，与基于激光雷达的网格相比，显著提高了点云结果的质量，与人体测量师实际测量的臀围和腰围相比，也提高了人体测量的质量。在这两种情况下，body2vec的最终质量与激光雷达重建相当。
