Detection of Independent Motion Using Directional Motion Estimation

It is shown that the problem of independent motion detection can be addressed by analyzing constraints on low-dimensional directional (projected) components of flow fields. We construct a robust algorithm, implemented as a recursive filter, to extract directional motion parameters from long image sequences. Based on this, a qualitative approach is described to detect independent motion, involving a combination of robust line-fitting and one-dimensional search. The low-dimensional projections onto subspaces facilitate efficient dynamic self-adaptation of detection thresholds to achieve good performance under changing operational conditions. The analysis is extended to long image sequences by incorporating tracking and spatio-temporal filtering. The approach is applicable to general camera motion and cluttered scenes using a wide range of camera fields of view. We demonstrate it on a variety of real image sequences.

[1]  Antonis A. Argyros,et al.  Independent 3D motion detection based on depth elimination in normal flow fields , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Marie-Odile Berger.  Resolving occlusion in augmented reality: a contour based approach without 3D reconstruction , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[4]  Stephen M. Smith,et al.  Integrated real-time motion segmentation and 3D interpretation , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[5]  John K. Tsotsos,et al.  Computing egomotion and shape from image motion using collinear points , 1992 .

[6]  W. James MacLean,et al.  Recovery of Egomotion and Segmentation of Independent Object Motion Using the EM Algorithm , 1994, BMVC.

[7]  Gilad Adiv,et al.  Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  W. Kiel,et al.  Direct Perception of Three-Dimensional Motion from Patterns of Visual Motion , 1995 .

[9]  A. Siegel.  Robust regression using repeated medians , 1982 .

[10]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[11]  José Santos-Victor,et al.  Direct egomotion estimation , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[12]  Larry S. Davis,et al.  Multiple vehicle detection and tracking in hard real-time , 1996, Proceedings of Conference on Intelligent Vehicles.

[13]  Andrew Zisserman,et al.  Detection and tracking of independent motion , 1996, Image Vis. Comput..

[14]  Larry S. DavisCenter.  Direction-selective Lters for Egomotion Estimation , 1997 .

[15]  Patrick Bouthemy,et al.  Multimodal motion estimation and segmentation using Markov random fields , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[16]  Larry S. Davis,et al.  Exploring Visual Motion Using Projections of Motion Fields , 1997 .

[17]  P. Anandan,et al.  A Unified Approach to Moving Object Detection in 2D and 3D Scenes , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Michael J. Black,et al.  The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields , 1996, Comput. Vis. Image Underst..

[19]  Y. Aloimonos,et al.  Direct Perception of Three-Dimensional Motion from Patterns of Visual Motion , 1995, Science.

[20]  Philip H. S. Torr,et al.  Stochastic Motion Clustering , 1994, ECCV.

[21]  Larry S. Davis,et al.  Detection of independently moving objects in passive video , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.

[22]  Y. Chien,et al.  Pattern classification and scene analysis , 1974 .

[23]  Peter J. Burt,et al.  Object tracking with a moving camera , 1989, [1989] Proceedings. Workshop on Visual Motion.

[24]  Wendong Wang,et al.  Recovering the Three-Dimensional Motion and Structure of Multiple Moving Objects from Binocular Image Flows , 1996, Comput. Vis. Image Underst..

[25]  Y. J. Tejwani,et al.  Robot vision , 1989, IEEE International Symposium on Circuits and Systems,.

[26]  Michal Irani,et al.  Detecting and Tracking Multiple Moving Objects Using Temporal Integration , 1992, ECCV.

[27]  Kostas Daniilidis,et al.  Decoupling the 3D Motion Space by Fixation , 1996, ECCV.

[28]  Rajeev Sharma,et al.  Early detection of independent motion from active control of normal image flow patterns , 1996, IEEE Trans. Syst. Man Cybern. Part B.