BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking
This addresses the challenge of accurate human motion tracking in dynamic, real-world video sequences for applications like robotics or AR, representing a novel integration but incremental in combining existing SLAM and human modeling techniques.
The paper tackles the problem of estimating human motion from video captured by a moving camera, which complicates the separation of camera and human motion, by presenting BodySLAM, a monocular SLAM system that jointly estimates human body parameters and camera trajectory, and demonstrates improved estimates compared to separate methods.
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.