A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
IEEE Transactions on Pattern Analysis and Machine Intelligence
Stereo Ranging with Verging Cameras
IEEE Transactions on Pattern Analysis and Machine Intelligence
Active fixation for scene exploration
International Journal of Computer Vision - Special issue: machine vision research at the Royal Institute of Technology
Dynamic Vergence Using Log-Polar Images
International Journal of Computer Vision
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Disparity estimation on log-polar images and vergence control
Computer Vision and Image Understanding
Active Depth Estimation with Gaze and Vergence Control Using Gabor Filters
ICPR '96 Proceedings of the 1996 International Conference on Pattern Recognition (ICPR '96) Volume I - Volume 7270
Digital Image Processing (3rd Edition)
Digital Image Processing (3rd Edition)
Version and vergence control of a stereo camera head by fitting the movement into the Hering's law
CRV '07 Proceedings of the Fourth Canadian Conference on Computer and Robot Vision
IEEE Transactions on Neural Networks
A spatial variant approach for vergence control in complex scenes
Image and Vision Computing
Hi-index | 0.02 |
The human naturally possesses a robust and effective visual system that utilizes saccade and vergence eye movements to explore the visual environment. This article presents a system that provides the functional biological equivalent which consists of a pair of cameras that provide for saccade and vergence eye movements. Included in this article is a detailed description of a simplified equivalent of the saccade generation module (typically from the superior colliculus (SC)) based on a FLANN image segmentation method and a visual cortex (VC) equivalent model based on a hierarchical disparity estimation model for vergence control. These two models cooperate to provide the systematic means for the autonomous exploration of the scene. Combining saccade and vergence movements, we are able to selectively reconstruct the 3D relative positions of objects in the scene and segment the image of the object under vergence.