A Multi-Resolution Image Understanding System Based on Multi-agent Architecture for High-Resolution Images

SUMMARY Recently a high-resolution image that has more than one million pixels is available easily. However, such an image requires much processing time and memory for an image understanding system. In this paper, we propose an integrated image understanding system ofmulti-resolution analysis and multiagent-based architecture for high-resolution images. The system we propose in this paper has capability to treat with a highresolution image effectively without much extra cost. We implemented an experimental system for images of indoor scenes.

[1]  Koichiro Deguchi,et al.  An architecture of object recognition system for various images based on multi-agents , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[2]  Y. Aloimonos,et al.  Preface of special issue on purposive, qualitative, active vision , 1992 .

[3]  C. L. TAN,et al.  An analysis of a distributed multiresolution vision system , 1989, Pattern Recognit..

[4]  Ramakant Nevatia,et al.  Recognition and localization of generic objects for indoor navigation using functionality , 1998, Image Vis. Comput..

[5]  Koichiro Deguchi,et al.  Recognition of indoor images employing qualitative model fitting and supporting relation between objects , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[6]  Ze-Nian Li,et al.  Pyramid Vision Using Key Features to Integrate Image-Driven Bottom-Up and Model-Driven Top-Down Processes , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[7]  Louise Stark Functionality in Object Recognition: Guest Editor's Introduction , 1995, Comput. Vis. Image Underst..

[8]  Takashi Matsuyama,et al.  SIGMA: A Knowledge-Based Aerial Image Understanding System , 1990 .

[9]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.