Personalization and Evaluation of a Real-time Depth-based Full Body Tracker

Thomas Helten¹ Andreas Baak¹ Gaurav Bharaj² Meinard Muller³ Hans-Peter Seidel¹ Christian Theobalt¹
¹MPI Informatik ²Harvard University ³ International Audio Laboratories Erlangen

3D Vision (3DV), 2013

(From left to right): Actor standing in the front of a single Kinect camera. Color coded depth data (red is near, blue is far) as obtained from the Kinect. Automatically estimated body shape of the actor. Two complex poses reliably tracked with our algorithm (left: input depth, right: estimated pose).

Abstract

Reconstructing a three-dimensional representation of human motion in real-time constitutes an important re- search topic with applications in sports sciences, human- computer-interaction, and the movie industry. In this paper, we contribute with a robust algorithm for estimating a personalized human body model from just two sequentially captured depth images that is more accurate and runs an order of magnitude faster than the current state-of- the-art procedure. Then, we employ the estimated body model to track the pose in real-time from a stream of depth images using a tracking algorithm that combines local pose optimization and a stabilizing database look- up. Together, this enables accurate pose tracking that is more accurate than previous approaches. As a further contribution, we evaluate and compare our algorithm to previous work on a comprehensive benchmark dataset containing more than 15 minutes of challenging motions. This dataset comprises calibrated marker-based motion capture data, depth data, as well as ground truth tracking results and is publicly available for research purposes.