Vision as Process

ISBN-13: 9783540581437 / Angielski / Twarda / 1994 / 435 str.

Andrew Marston; Maryse Hostettmann; James L. Crowley

Opis

There is growing interest in the use of active control of image formation to simplify and accelerate scene understanding. AI research on machine vision emphasizes the use of declarative knowledge and explicit representation of goals to control the perceptual process. This book describes the first implemented vision system anywhere to integrate robotic camera control, ocular reflexes, reactive fixation, real-time image processing, image tracking, perceptual grouping, active 3D modeling, and object recognition. The book presents the results of the ESPRIT project BG 3038/7108 "Vision as Process" initiated in 1989. The presentation is organized as five parts which reflect the components developed for the resulting experimental test-bed system.

Spis treści

I Integration and Control of Perception.- 1. System Integration and Control.- 2. The SAVA Skeleton System.- 3. KTH Software Integration in the VAP Project.- 4. A Vision Programmers Workbench.- II Image Processing and Description.- 5. Image Processing in the SAVA System.- 6. Building a Pyramid of Low-Pass Images.- 7. One-pass Polygonal Approximation of a Contour Image.- 8. Tracking and Description of Image Structures.- 9. Contextual Junction Finder.- III Advanced Image Processing.- 10. Introduction and Background.- 11. Phase-based Disparity Estimation.- 12. Low Level Focus of Attention Mechanisms.- 13. Tensor Based Spatio-temporal Signal Analysis.- 14. Line Extraction Using Tensors.- IV Active Gaze Control and 3D Scene Description.- 15. The KTH Head-Eye System.- 16. Hierarchical Control of a Binocular Camera Head.- 17. Active 3D Scene Description in Object Reference Frames.- 18. Geometric Description and Maintenance of 3D Objects in an Active Vision System.- V Active Scene Interpretation.- 19. Control of Perception.- 20. Control of Scene Interpretation.- 21. Recognition of Polyhedral Objects Using Triangle-pair Features.- 22. Recognition of 3D Cylinders in 2D Images by Top-Down Model Imposition.- 23. Camera Control for Establishing the Current and Next-Look Direction in an Active Vision Object Recognition System.- VI Lessons Learned.