A Saccadic Camera Movement System for Object Recognition

We propose an active vision system for saccadic camera movement and scene analysis as a new integral approach to image understanding. The model consists of several subsystems for preattentive foveal texel analysis and salient feature detection, image recognition by hypercolumnar representation, scanpath based object recognition with sparsely coded associative memories, an egocentric interest map for interaction of image induced and knowledge based targets and a camera control module.

[1]  Y H Jannen,et al.  Image Representation in Hypercolumnar Structure by Means of Associative Memory , 1990 .

[2]  Hanspeter A. Mallot,et al.  Neural mapping and space-variant image processing , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[3]  Hanspeter A. Mallot,et al.  Ortsvariante Sensoradaptation durch Kohonen-Mapping , 1990, DAGM-Symposium.

[4]  Hanspeter A. Mallot,et al.  Exploration of a natural environment , 1990 .

[5]  H. C. LONGUET-HIGGINS,et al.  Non-Holographic Associative Memory , 1969, Nature.

[6]  A. L. Yarbus,et al.  Eye Movements and Vision , 1967, Springer US.

[7]  L. Stark,et al.  Scanpaths in saccadic eye movements while viewing and recognizing patterns. , 1971, Vision research.

[8]  H. Voorhees.  Finding Texture Boundaries in Images , 1987 .

[9]  David Noton,et al.  A Theory of Visual Pattern Perception , 1970, IEEE Trans. Syst. Sci. Cybern..

[10]  A. Treisman.  Preattentive processing in vision , 1985, Comput. Vis. Graph. Image Process..

[11]  Andrea Califano,et al.  Data and model driven foveation , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[12]  Christopher M. Brown,et al.  Selective Attention as Sequential Behavior: Modeling Eye Movements with an Augmented Hidden Markov Model , 1990 .

[13]  G. Palm,et al.  On associative memory , 2004, Biological Cybernetics.