# Real-Time Human Motion Capture with Multiple Depth Cameras

arXiv: https://arxiv.org/abs/1605.08068 · HTML: https://mlsanity.com/paper/1605.08068/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2016.

## Built on by (most cited first, 4 of 4)

- [Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances](https://mlsanity.com/paper/2303.10280/) (2023)
- [A Novel Two Stream Decision Level Fusion of Vision and Inertial Sensors Data for Automatic Multimodal Human Activity Recognition System](https://mlsanity.com/paper/2306.15765/) (2023)
- [DeepMoCap: Deep Optical Motion Capture Using Multiple Depth Sensors and Retro-Reflectors](https://mlsanity.com/paper/2110.07283/) (2021)
- [A Mixture of Experts Approach to 3D Human Motion Prediction](https://mlsanity.com/paper/2405.06088/) (2024)

## Abstract (arXiv)

Commonly used human motion capture systems require intrusive attachment of markers that are visually tracked with multiple cameras. In this work we present an efficient and inexpensive solution to markerless motion capture using only a few Kinect sensors. Unlike the previous work on 3d pose estimation using a single depth camera, we relax constraints on the camera location and do not assume a co-operative user. We apply recent image segmentation techniques to depth images and use curriculum learning to train our system on purely synthetic data. Our method accurately localizes body parts without requiring an explicit shape model. The body joint locations are then recovered by combining evidence from multiple views in real-time. We also introduce a dataset of ~6 million synthetic depth frames for pose estimation from multiple cameras and exceed state-of-the-art results on the Berkeley MHAD dataset.