Summary of Ultra Inertial Poser: Scalable Motion Capture and Tracking From Sparse Inertial Sensors and Ultra-wideband Ranging, by Rayan Armani et al.
Ultra Inertial Poser: Scalable Motion Capture and Tracking from Sparse Inertial Sensors and Ultra-Wideband Ranging
by Rayan Armani, Changlin Qian, Jiaxi Jiang, Christian Holz
First submitted to arxiv on: 30 Apr 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Graphics (cs.GR); Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel machine learning-based method for 3D full-body pose estimation, Ultra Inertial Poser, is proposed to constrain drift and jitter in inertial tracking via inter-sensor distances. The approach uses a lightweight embedded tracker that combines inexpensive off-the-shelf 6D inertial measurement units with ultra-wideband radio-based ranging, without requiring stationary reference anchors. A graph-based machine learning model processes the 3D states and distances to estimate a person’s pose and translation. The method is trained on synthesized data from the AMASS motion capture database and evaluated using a novel dataset of 10 participants performing 25 motion types, captured by 6 wearable IMU+UWB trackers and an optical motion capture system. Compared to PIP and TIP, Ultra Inertial Poser achieves state-of-the-art performance, reducing position error by 22% and jitter by 97%. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way is found to make better 3D body pose estimates using cheap wearable sensors and radio signals. The sensors can get lost or jump around, but this method uses the distance between them to help keep track of where they are in space. A special computer program then combines this information with how each sensor sees the world to figure out the person’s pose and movement. This is tested on a lot of people doing different movements, and it does better than other methods at getting the correct answer. |
Keywords
» Artificial intelligence » Machine learning » Pose estimation » Tracking » Translation
