LEAST SQUARES MATCHING TRACKING ALGORITHM FOR HUMAN BODY MODELING

In this paper we present a method to extract 3-D information of the shape and movement of the human body using video sequences acquired with three CCD cameras. This work is part of a project aimed at developing a highly automated system to model most realistically human bodies from video sequences. Our image acquisition system is currently composed of three synchronized CCD cameras and a frame grabber which acquires a sequence of triplet images. From the video sequences, we extract two kinds of 3-D information: a three dimensional surface measurement of the visible body parts for each triplet and 3-D trajectories of points on the body. Our approach to surface measurement is based on multi-image matching, using the adaptive least squares method. A semi automated matching process determines a dense set of corresponding points in the triplets, starting from few manually selected seed points. The tracking process is also based on least squares matching techniques, thus the name LSMTA (Least Squares Matching Tracking Algorithm). The spatial correspondences between the three images of the different views and the temporal correspondences between subsequent frames are determined with a least squares matching algorithm. The advantage of this tracking process is twofold: firstly, it can track natural points, without using markers; secondly, it can also track entire surface parts on the human body. In the last case, the tracking process is applied to all the points matched in the region of interest. The result can be seen as a vector field of trajectories (position, velocity and acceleration) which can be checked with thresholds and neighborhood-based filters. The 3-D information extracted from the video sequences can be used to reconstruct the animation model of the original sequence.

[1]  Norman I. Badler,et al.  Animation control for real-time virtual humans , 1999, CACM.

[2]  Nicola D'Apuzzo.  Automated photogrammetric measurement of human faces , 1998 .

[3]  Duane C. Brown,et al.  Close-Range Camera Calibration , 1971 .

[4]  Kathleen M. Robinette,et al.  The CAESAR project: a 3-D surface anthropometry survey , 1999, Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062).

[5]  Michael W. Vannier,et al.  Design of a multisensor optical surface scanner , 1994, Other Conferences.

[6]  Werner Stuetzle,et al.  Automatic body measurement for mass customization of garments , 1999, Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062).

[7]  Norman I. Badler,et al.  Animation 2000++ , 2000, IEEE Computer Graphics and Applications.

[8]  Bruce Bradtmiller,et al.  3D whole-body scans: Measurement extraction software validation , 1999 .

[9]  Pascal Fua,et al.  Human Body Modeling and Motion Analysis From Video Sequences , 1998 .

[10]  J William,et al.  IEEE Computer Graphics and Applications , 2019, Computer.

[11]  Daniel Thalmann,et al.  An animation interface designed for motion capture , 1997, Proceedings. Computer Animation '97 (Cat. No.97TB100120).

[12]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[13]  Y. Ge,et al.  Noncontact 3D biological shape measurement from multiple views , 1994 .

[14]  Dennis Burnsides.  Software for visualization, analysis, and manipulation of laser scan images , 1997, Electronic Imaging.

[15]  Hans-Gerd Maas.  Image sequence based automatic multi-camera system calibration techniques 1 Revised version of a pap , 1999 .

[16]  Hideo Saito,et al.  Modeling, Combining, and Rendering Dynamic Real-World Events From Image Sequences , 1998 .

[17]  Larry S. Davis,et al.  3-D model-based tracking of humans in action: a multi-view approach , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Marc Rioux,et al.  Nefertiti: a query by content system for three-dimensional model and image databases management , 1999, Image Vis. Comput..

[19]  A. Gruen.  ADAPTIVE LEAST SQUARES CORRELATION: A POWERFUL IMAGE MATCHING TECHNIQUE , 1985 .

[20]  D. Thalmann,et al.  An Anatomic Human Body For Motion Capture , 1998 .

[21]  Hein A. M. Daanen,et al.  Absolute accuracy of the Cyberware WB4 whole-body scanner , 1997, Electronic Imaging.

[22]  M.A. Brunsman,et al.  Optimal postures and positioning for human body scanning , 1997, Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134).

[23]  Henning G.E. Wolf.  Structured lighting for upgrading 2D vision systems to 3D , 1996, Other Conferences.

[24]  R. Plankers,et al.  Automated body modeling from video sequences , 1999, Proceedings IEEE International Workshop on Modelling People. MPeople'99.