Computer Vision and Image Understanding 81, 269–284 (2001) doi:10.1006/cviu.2000.0888, available online at http://www.idealibrary.com on Estimating Anthropometry and Pose from a Single Uncalibrated Image Carlos Barr´ on and Ioannis A. Kakadiaris Department of Computer Science, University of Houston, 4800 Calhoun, Houston, Texas 77204-3475 E-mail: cbarron@uh.edu, ioannisk@uh.edu Accepted July 29, 2000 In this paper, we present a four-step technique for simultaneously estimating a hu- man’s anthropometric measurements (up to a scale parameter) and pose from a single uncalibrated image. The user initially selects a set of image points that constitute the projection of selected landmarks. Using this information, along with a priori statis- tical information about the human body, a set of plausible segment length estimates is produced. In the third step, a set of plausible poses is inferred using a geometric method based on joint limit constraints. In the fourth step, pose and anthropometric measurements are obtained by minimizing an appropriate cost function subject to the associated constraints. The novelty of our approach is the use of anthropometric statistics to constrain the estimation process that allows the simultaneous estima- tion of both anthropometry and pose. We demonstrate the accuracy, advantages, and limitations of our method for various classes of both synthetic and real input data. c 2001 Academic Press 1. INTRODUCTION Video-based three-dimensional human motion tracking is an important and challenging research problem. Its importance stems from numerous applications such as: (1) perfor- mance measurement for human factors engineering, (2) posture and gait analysis for train- ing athletes and physically challenged persons, (3) human body, hands, and face animation, and (4) automatic annotation of human activities in video databases. The challenges toward the general applicability of a vision-based three-dimensional tracking system on real data include the following: • Data from one camera only: There are several applications for which the video recordings from only one view are available (e.g., for analyzing the motion of famous artists in historical recordings). In addition, the camera might be moving, possibly zooming in and out. 269 1077-3142/01 $35.00 Copyright c 2001 by Academic Press All rights of reproduction in any form reserved.