Markerless Outdoor Human Motion Capture Using Multiple Autonomous Micro Aerial Vehicles
Nitin Saini, Eric Price, Rahul Tallamraju, Raffi Enficiaud, Roman Ludwig, Igor Martinovic, Aamir Ahmad, Michael J. Black
摘要
Capturing human motion in natural scenarios means moving motion capture out of the lab and into the wild. Typical approaches rely on fixed, calibrated, cameras and reflective markers on the body, significantly limiting the motions that can be captured. To make motion capture truly unconstrained, we describe the first fully autonomous outdoor capture system based on flying vehicles. We use multiple micro-aerial-vehicles(MAVs), each equipped with a monocular RGB camera, an IMU, and a GPS receiver module. These detect the person, optimize their position, and localize themselves approximately. We then develop a markerless motion capture method that is suitable for this challenging scenario with a distant subject, viewed from above, with approximately calibrated and moving cameras. We combine multiple state-of-the-art 2D joint detectors with a 3D human body model and a powerful prior on human pose. We jointly optimize for 3D body pose and camera pose to robustly fit the 2D measurements. To our knowledge, this is the first successful demonstration of outdoor, full-body, markerless motion capture from autonomous flying vehicles.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- Learning Motion Priors for 4D Human Body Capture in 3D ScenesSiwei Zhang, Yan Zhang, Federica Bogo, Marc Pollefeys 等ICCV 2021 · 被引用 117 次
- M3D-VTON: A Monocular-to-3D Virtual Try-On NetworkFuwei Zhao, Zhenyu Xie, Michael Kampffmeyer, Haoye Dong 等ICCV 2021 · 被引用 81 次
- Proactive Multi-Camera Collaboration for 3D Human Pose EstimationHai Ci, Mickel Liu, Xuehai Pan, Fangwei Zhong 等ICLR 2023 · 被引用 6 次
- Pedestrian Motion Reconstruction: A Large-scale Benchmark via Mixed Reality Rendering with Multiple Perspectives and ModalitiesYichen Wang, Yiyi Zhang, Xinhao Hu, Li Niu 等ICLR 2025
- ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion CaptureSena Kiciroglu, Helge Rhodin, Sudipta N. Sinha, Mathieu Salzmann 等CVPR 2020
相关 Paper
- Towards Unstructured Unlabeled Optical Mocap: A Video Helps!Nicholas Milef, John Keyser, Shu KongSIGGRAPH 2024 · 被引用 2 次
- Gravity-Aware Monocular 3D Human-Object ReconstructionRishabh Dabral, Soshi Shimada, Arjun Jain, Christian Theobalt 等ICCV 2021 · 被引用 34 次
- Neural monocular 3D human motion capture with physical awarenessSoshi Shimada, Vladislav Golyanik, Weipeng Xu, Patrick Pérez 等SIGGRAPH 2021 · 被引用 107 次
- Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-Localization in Large Scenes From Body-Mounted SensorsVladimir Guzov, Aymen Mir, Torsten Sattler, Gerard Pons-MollCVPR 2021
- CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the WildBastian Wandt, Marco Rudolph, Petrissa Zell, Helge Rhodin 等CVPR 2021
