Spatio-temporal shape building from image sequences using lateral interaction in accumulative computation

To be able to understand the motion of non-rigid objects, techniques in image processing and computer vision are essential for motion analysis. Lateral interaction in accumulative computation for extracting non-rigid shapes from an image sequence has recently been presented, as well as its application to segmentation from motion. In this paper, we introduce a modi4ed version of the 4rst multi-layer architecture. This version uses the basic parameters of the LIAC model to spatio-temporally build up to the desired extent the shapes of all moving objects present in a sequence of images. The in5uences of LIAC model parameters are explained in this paper, and we 4nally show some examples of the usefulness of the model proposed. ? 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

[1]  Randal C. Nelson,et al.  Detecting activities , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[2]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[3]  Jake K. Aggarwal,et al.  On the computation of motion from sequences of images-A review , 1988, Proc. IEEE.

[4]  Narendra Ahuja,et al.  A Transform for Multiscale Image Segmentation by Integrated Edge and Region Detection , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Thomas S. Huang,et al.  Motion and Structure from Image Sequences , 1992 .

[6]  José Mira,et al.  Aplicación de las transformaciones integrales al proceso de datos en la retina , 1969 .

[7]  James W. Davis,et al.  The representation and recognition of human movement using temporal templates , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  James W. Davis,et al.  Real-time recognition of activity using temporal templates , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.

[9]  Antonio Fernández-Caballero,et al.  Segmentation from motion of non-rigid objects by neuronal lateral interaction , 2001, Pattern Recognit. Lett..

[10]  Laurenz Wiskott,et al.  Segmentation from motion: combining Gabor- and Mallat-wavelets to overcome the aperture and correspondence problems , 1999, Pattern Recognit..

[11]  Antonio Fernández Caballero.  Modelos de interacción lateral en computación acumulativa para la obtención de siluetas , 2001 .

[12]  James W. Davis,et al.  An appearance-based representation of action , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[13]  Gösta H. Granlund,et al.  Image Sequence Analysis , 1993, DAGM-Symposium.

[14]  J. Little,et al.  Recognizing People by Their Gait: The Shape of Motion , 1998 .

[15]  Larry S. Davis,et al.  W/sup 4/: Who? When? Where? What? A real time system for detecting and tracking people , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[16]  Narendra Ahuja,et al.  Extracting gestural motion trajectories , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[17]  José Mira Mira,et al.  Permanence Memory: A System for Real Time Motion Analysis in Image Sequences , 1992, MVA.

[18]  José R. Álvarez,et al.  Towards More Realistic Self Contained Models of Neurons: High-Order, Recurrence and Local Learning , 1993, IWANN.

[19]  Roberto Moreno-Díaz,et al.  A Neurocybernetic Model of Modal Co‐operative Decisions in the Kilmer‐McCulloch Space , 1989 .

[20]  Senén Barro,et al.  Local Accumulation of Persistent Activity at Synaptic Level: Application to Motion Analysis , 1995, IWANN.