Abstract:The perceptual completion problem of 3D scene within the framework of stereovision is discussed in this paper. An electrostatic completing field based model is presented, which refers to the laws of Gestalt psychology, the rules of visual organization and the properties of electrostatic field. In the model, stimuli are defined and arranged on the breakpoints of fragments to produce the completing field. Then the completing field matches the breakpoints naturally and connects them with proper smooth curves. The completions of occluded boundaries and illusory contours agree with the human perception. The completion results can be used for reconstructing 3D information of the scene and segmenting the scene into a set of surfaces correctly from stereo images.
王,汪增福. 三维场景中被遮挡边界与错觉轮廓的感知修复*[J]. 模式识别与人工智能, 2006, 19(2): 137-142.
WANG Yan, WANG ZengFu. Perceptual Completion of Occluded Boundaries and Illusory Contours in 3D Scene. , 2006, 19(2): 137-142.
[1] Williams L R, Jacobs D W. Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience. In: Proc of the 5th International Conference on Computer Vision. Cambridge, USA, 1995, 408-415 [2] Geiger D, Pao H, Rubin N. Salient and Multiple Illusory Surfaces. In: Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Santa Barbara, USA, 1998, 118-124 [3] Saund E. Perceptual Organization of Occluding Contours of Opaque Surfaces. Computer Vision and Image Understanding, 1999, 76(1): 70-82 [4] Liu H Y, Huang S H, Hong J G. A New Model of Perceptual Completion for Occluded Smooth Boundary and Illusory Contour. Acta Automatica Sinica, 1999, 25(5): 599-605 (in Chinese) (刘海鹰, 黄胜华, 洪继光. 一种新的被遮挡的光滑边界与错觉轮廓的感知修复模型. 自动化学报, 1999, 25(5): 599-605) [5] Wang Z F, Ohnishi N. A Multi-Layered Model for Stereo Vision: Depth Perception and Surface Completion. Technical Report of IEICE, 1996, 96(247): 55-62 [6] Koffka K. The Principle of Gestalt Psychology. New York, USA: Harcourt Brace, 1935 [7] Wang Z F, Ohnishi N. Stereo Matching as a Multistage Grouping Process. In: Proc of IEEE/SICE/RSJ International Conference on Multi-Sensor Fusion and Integration for Intelligent Systems. Washington, USA, 1996, 329-336