Reality Capture Technologies (LiDAR, RGB-D, Vision)
Reality Capture Technologies (LiDAR, RGB-D, Vision)
复制标题
现实捕捉技术（LiDAR、RGB-D、视觉）
DOI：
10.1061/9780784482438.019
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Kamat, Vineet R.
中科院分区：
文献类型：
--
作者：
Liang, Ci-Jyun;Lundeen, Kurt M.;McGee, Wes;Menassa, Carol C.;Lee, SangHyun;Kamat, Vineet R.
撞击事故是建筑工地上的潜在安全问题，需要可靠的机器姿态估计。深度学习方法的发展增强了人类姿势估计，可适用于关节式机器。这些方法需要大量的数据集进行训练，这是具有挑战性和耗时的现场获得。提出了一种快速数据采集方法来建立挖掘机位姿估计数据集。它使用两个工业机器人手臂作为挖掘机和摄像机单脚架来收集不同的挖掘机位姿数据。可以从机器人的嵌入式编码器获得3D注释。手动注释2D姿势。为了进行评估，收集了2，500个姿势图像，并使用堆叠沙漏网络进行训练。结果表明，该数据集适合在受控环境下进行挖掘机位姿估计网络训练，这使得该数据集具有用真实的施工现场图像增强的潜力。
Struck-by accidents are potential safety concerns on construction sites and require a robust machine pose estimation. The development of deep learning methods has enhanced the human pose estimation that can be adapted for articulated machines. These methods require abundant dataset for training, which is challenging and time-consuming to obtain on-site. This paper proposes a fast data collection approach to build the dataset for excavator pose estimation. It uses two industrial robot arms as the excavator and the camera monopod to collect different excavator pose data. The 3D annotation can be obtained from the robot's embedded encoders. The 2D pose is annotated manually. For evaluation, 2,500 pose images were collected and trained with the stacked hourglass network. The results showed that the dataset is suitable for the excavator pose estimation network training in a controlled environment, which leads to the potential of the dataset augmenting with real construction site images.