Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXIX
Computer Vision - ECCV 2022 - 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXXIX
复制标题
计算机视觉 - ECCV 2022 - 第 17 届欧洲会议，以色列特拉维夫，2022 年 10 月 23-27 日，会议记录，第 XXXIX 部分
DOI：
10.1007/978-3-031-19842-7_38
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Henning D
中科院分区：
文献类型：
--
作者：
Henning D
由于其许多潜在的应用，从视频中估计人体运动是一个活跃的研究领域。大多数最先进的方法都会预测单个图像的人体形状和姿势估计，并且不会利用视频中可用的时间信息。许多“野外”人体运动序列是由移动摄像机捕获的，这增加了混合摄像机和人体运动估计的复杂性。因此，我们提出了 BodySLAM，这是一种单目 SLAM 系统，可以联合估计人体的位置、形状和姿势以及相机轨迹。我们还引入了一种新颖的人体运动模型来约束连续的身体姿势并观察场景的规模。通过对移动单目相机捕获的人体运动视频序列进行一系列实验，我们证明了与单独估计这些参数相比，BodySLAM 改进了对所有人体参数和相机姿势的估计。
Estimating human motion from video is an active research area due to its many potential applications. Most state-of-the-art methods predict human shape and posture estimates for individual images and do not leverage the temporal information available in video. Many “in the wild" sequences of human motion are captured by a moving camera, which adds the complication of conflated camera and human motion to the estimation. We therefore present BodySLAM, a monocular SLAM system that jointly estimates the position, shape, and posture of human bodies, as well as the camera trajectory. We also introduce a novel human motion model to constrain sequential body postures and observe the scale of the scene. Through a series of experiments on video sequences of human motion captured by a moving monocular camera, we demonstrate that BodySLAM improves estimates of all human body parameters and camera poses when compared to estimating these separately.