Robot Obstacle Detection and Setup of Vision System Platform

• Main Authors: Chuan-Siang Wang, 汪川翔
• Other Authors: Tsong-Yao Huang
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/26501947392280184980

碩士 === 國立臺北教育大學 === 資訊科學系碩士班 === 98 === There are many methods in tracking or avoidance obstacle, but those never can achieve that get to change any condition. We use 3D vision and image recognizable match, those are different from most infrared and ultrasound method that are used to detect the distance between targets. In order to reduce the less important of the situation which will affect tracking or avoidance obstacle, the pairs of CCD are used to catch the real-time images. And then, we try to image processing, determine moving target and build up target center. The purpose of this part is to calculate the distance from the CCD base to the target object. Finally, we match samples to control the CCD to track the moving object immediately. Also, an image tracking system will be setup. It will follow the data of images, and calculate the center of the target object. Then, we can drive the vision system to lock the 2-CCDs in the center of the target object.