Model-Based Tracking of Multiple Worms and Fish

This paper addresses the problem of tracking multiple undulating creatures through interactions and partial occlusions from a top view. Detailed posture estimation of biological model organisms is essential for a wide variety of research. We present a visual tracking algorithm that incorporates both a contour model and a region model based on level sets. Both visual cues are naturally integrated into the observation model of an Iterated Kalman Filter (IKF). We use generative geometric models to parameterize the animal’s shape deformations and motion. The priors provided by these parametrized models improve tracking accuracy in the presence of incorrect foreground segmentation and partial occlusions, while allowing us to measure physical quantities directly relevant to experimental goals. For illustration, the method is used to track the position and shape of multiple nematodes and larval zebrafish.

[1]  John M. Snyder,et al.  Generative modeling: a symbolic system for geometric modeling , 1992, SIGGRAPH.

[2]  Richard Szeliski,et al.  Tracking with Kalman snakes , 1993 .

[3]  F. W. Cathey,et al.  The iterated Kalman filter update as a Gauss-Newton method , 1993, IEEE Trans. Autom. Control..

[4]  Michael Isard,et al.  Active Contours , 2000, Springer London.

[5]  Andrew Blake,et al.  A Probabilistic Exclusion Principle for Tracking Multiple Objects , 2000, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[6]  W. Eric L. Grimson,et al.  Model-based curve evolution technique for image segmentation , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[8]  J. Eisen,et al.  Headwaters of the zebrafish — emergence of a new model vertebrate , 2002, Nature Reviews Genetics.

[9]  Ronald Fedkiw,et al.  Level set methods and dynamic implicit surfaces , 2002, Applied mathematical sciences.

[10]  Stefano Soatto,et al.  Tracking deformable moving objects under severe occlusions , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[11]  A. Tannenbaum,et al.  Dynamic geodesic snakes for visual tracking , 2004, CVPR 2004.

[12]  F. Dellaert,et al.  A Rao-Blackwellized particle filter for EigenTracking , 2004, CVPR 2004.

[13]  Rudolph van der Merwe,et al.  Sigma-point kalman filters for probabilistic inference in dynamic state-space models , 2004 .

[14]  Namrata Vaswani,et al.  Particle filtering for geometric active contours with application to tracking moving and deforming objects , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  Michael O. Hengartner,et al.  Finding function in novel targets: C. elegans as a model organism , 2006, Nature Reviews Drug Discovery.

[16]  A. Tannenbaum,et al.  Tracking deformable objects with unscented Kalman filtering and geometric active contours , 2006, 2006 American Control Conference.

[17]  Gaurav S. Sukhatme,et al.  The Iterated Sigma Point Kalman Filter with Applications to Long Range Stereo , 2006, Robotics: Science and Systems.

[18]  Daniel Cremers,et al.  Dynamical statistical shape priors for level set-based tracking , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Joel Burdick,et al.  Automated Tracking of Multiple C. Elegans , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[20]  Pamela C. Cosman,et al.  AUTOMATED TRACKING OF MULTIPLE C. ELEGANS WITH ARTICULATED MODELS , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[21]  Nicolas Roussel,et al.  A Computational Model for C. elegans Locomotory Behavior: Application to Multiworm Tracking , 2007, IEEE Transactions on Biomedical Engineering.

[22]  David Lentink,et al.  Automated visual tracking for studying the ontogeny of zebrafish swimming , 2008, Journal of Experimental Biology.