Focus of Attention control is one of the key research topics in the active vision field. Roughly speeking, the previous approaches in the literature can be divided into 2 categories, i.e., the top-down approach and the down-top approach ( or context guided approach and context free approach). This project is intended to use Hough transform and neural Net as primary means to

• select the robot's interest regions ;
• determine the robot's next-look point;
• realize a varying resolution virtual camera by software means. ( i.e., a uniform CCD camera is in fact used, however the resolutions for the interest region can be increased, and those for the periphiral part can be reduced through transformation means. )

 
• EHT (Extended Hough Transform) is used in this project to simulate the spacial varification of visual acuity of human eyes.

Return to Pojects' Web Page