We propose an intelligent vision-based Automated Guided Vehicle (AGV)\r\nsystem using fiduciary markers. In this paper, we explore a low-cost, efficient vehicle\r\nguiding method using a consumer grade web camera and fiduciary markers. In the\r\nproposed method, the system uses fiduciary markers with a capital letter or triangle\r\nindicating direction in it. The markers are very easy to produce, manipulate, and maintain.\r\nThe marker information is used to guide a vehicle. We use hue and saturation values in the\r\nimage to extract marker candidates. When the known size fiduciary marker is detected by\r\nusing a bird�s eye view and Hough transform, the positional relation between the marker\r\nand the vehicle can be calculated. To recognize the character in the marker, a distance\r\ntransform is used. The probability of feature matching was calculated by using a distance\r\ntransform, and a feature having high probability is selected as a captured marker. Four\r\ndirectional signals and 10 alphabet features are defined and used as markers. A 98.87%\r\nrecognition rate was achieved in the testing phase. The experimental results with the\r\nfiduciary marker show that the proposed method is a solution for an indoor AGV system.
Loading....