Summary: | 碩士 === 國立臺灣師範大學 === 應用電子科技學系 === 100 === Unlike traditional Binocular vision measurement method, this thesis presents a single-webcam-based measurement method developed from a proposed Parallel Lines Distance Measurement System (PLDMS). PLDMS can create the identical ruler for all measured objects. Not only can the proposed measurement method reduce production cost, but also the experimental environment is easy to set up because only three parameters need to decide, the maximum pixel, perspective, and optical distance. Because the locations of webcams are fixed, we use the simple background subtraction method to extract the prospects to improve the problem of computational burden. Furthermore, we use the low-pass filter and on-line background update method to reduce background noise, and adopt the image morphology to complete prospect information and to remove the slight noise. In our indoor experiments, webcams are located several places on where we can clearly monitor the move of a robot in the fifth floor of the Science and Technology building of Nation Taiwan Normal University. Finally, through the switching mechanism and the predefined coordinate system, we can get the location of the robot when it is moving.
|