Model-based object tracking in monocular image sequences of road traffic scenes

Moving vehicles are detected and tracked automatically in monocular image sequences from road traffic scenes recorded by a stationary camera. In order to exploit the a priori knowledge about shape and motion of vehicles in traffic scenes, a parameterized vehicle model is used for an intraframe matching process and a recursive estimator based on a motion model is used for motion estimation. An interpretation cycle supports the intraframe matching process with a state MAP-update step. Initial model hypotheses are generated using an image segmentation component which clusters coherently moving image features into candidate representations of images of a moving vehicle. The inclusion of an illumination model allows taking shadow edges of the vehicle into account during the matching process. Only such an elaborate combination of various techniques has enabled us to track vehicles under complex illumination conditions and over long (over 400 frames) monocular image sequences. Results on various real-world road traffic scenes are presented and open problems as well as future work are outlined.

[1]  Stephen J. Maybank,et al.  Filter based estimates of depth , 1990, BMVC.

[2]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[3]  David G. Lowe,et al.  Fitting Parameterized Three-Dimensional Models to Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Donald B. Gennery,et al.  Tracking Known Three-Dimensional Objects , 1982, AAAI.

[5]  Y. Bar-Shalom.  Tracking and data association , 1988 .

[6]  Charles R. Dyer,et al.  Real-time, parallel motion tracking of three dimensional objects from spatiotemporal sequences , 1990 .

[7]  Walterio W. Mayol-Cuevas,et al.  Proc. British Machine Vision Conference , 2002 .

[8]  W. Eric L. Grimson,et al.  The Combinatorics Of Object Recognition In Cluttered Environments Using Constrained Search , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[9]  Rama Chellappa,et al.  3-D Motion Estimation Using a Sequence of Noisy Stereo Images: Models, Estimation, and Uniqueness Results , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Roger Y. Tsai,et al.  A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses , 1987, IEEE J. Robotics Autom..

[11]  Rachid Deriche,et al.  Tracking line segments , 1990, Image Vis. Comput..

[12]  David G. Lowe,et al.  Integrated treatment of matching and measurement errors for robust model-based motion tracking , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[13]  M Mitschke,et al.  DYNAMIK DER KRAFTFAHRZEUGE - BAND C: FAHRVERHALTEN , 1990 .

[14]  Chris Harris,et al.  RAPID - a video rate object tracker , 1990, BMVC.

[15]  C.-K. Sung,et al.  Extraktion von typischen und komplexen Vorgängen aus einer langen Bildfolge einer Verkehrsszene , 1988, DAGM-Symposium.

[16]  A. Jazwinski.  Stochastic Processes and Filtering Theory , 1970 .

[17]  R. Chellappa,et al.  Recursive 3-D motion estimation from a monocular image sequence , 1990 .

[18]  Terry Caelli,et al.  Recovery of the 3-D location and motion of a rigid object through camera image (An Extended Kalman Filter Approach) , 1989, International Journal of Computer Vision.

[19]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .

[20]  Geoffrey D. Sullivan,et al.  Kalman Filters in Constrained Model Based Tracking , 1991, BMVC.

[21]  Hans-Hellmut Nagel,et al.  Algorithmic characterization of vehicle trajectories from image sequences by motion verbs , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  Arthur Gelb,et al.  Applied Optimal Estimation , 1974 .

[23]  Joseph L. Mundy,et al.  Model-based motion analysis—motion from motion , 1988 .

[24]  David W. Murray,et al.  From image sequences to recognized moving polyhedral objects , 1989, International Journal of Computer Vision.

[25]  L. E. Scales,et al.  Introduction to Non-Linear Optimization , 1985 .

[26]  Geoffrey D. Sullivan,et al.  Model-Based Tracking , 2011, BMVC.

[27]  Donald B. Gennery,et al.  Visual tracking of known three-dimensional objects , 1992, International Journal of Computer Vision.

[28]  Dieter Koller.  Detektion, Verfolgung und Klassifikation bewegter Objekte in monokularen Bildfolgen am Beispiel von Straßenverkehrsszenen , 1992, DISKI.

[29]  Hans-Hellmut Nagel,et al.  Model-Based Object Tracking in Traffic Scenes , 1992, ECCV.

[30]  Richard Evans.  Kalman filtering of pose estimates in applications of the RAPID video rate tracker , 1990, BMVC.

[31]  Olivier D. Faugeras,et al.  Three-dimensional motion computation and object segmentation in a long sequence of stereo frames , 1992, International Journal of Computer Vision.

[32]  J. Schick,et al.  Simultaneous estimation of 3D shape and motion of objects by computer vision , 1991, Proceedings of the IEEE Workshop on Visual Motion.

[33]  Axel Korn,et al.  Toward a Symbolic Representation of Intensity Changes in Images , 1988, IEEE Trans. Pattern Anal. Mach. Intell..