Extraction method of small agricultural AGV navigation baseline based on crop row characteristics
1. School of Mechanical Engineering, Shandong University of Technology, Zibo， Shandong 255049, China; 2. School of Agricultural Engineering and Food Science, Shandong University of Technology, Zibo， Shandong 255049, China
Abstract：To solve the problem that agricultural robots based on visual navigation were easily disturbed by weeds and lack of seedlings during the navigation baseline extraction process， a method was proposed to quickly and accurately extract the center line of corn row as navigation baseline of the small agricultural AGV under the field environment of corn in 35 leaf stage. The ultragreen gray method and Otsu method were used to achieve realtime acquisition of crop information. The characteristics of crop row length, pixels and direction were simulated by parallelograms to achieve preliminary positioning of crop row positions. The shape feature of crop row in the image was simulated by trapezoid, which was narrow and wide at the bottom to achieve the final positioning of the crop row position. According to the statistical characteristics of Hough transform， the crop line detection was realized. The angle deviation comparison between the current frame navigation baseline and the previous frame navigation baseline was conducted without comparing the first frame image, and the deviation beyond a certain range should inherit the previous frame navigation baseline line. The test data shows that it takes average time of 78 ms to process a frame of 640×480 pixels, and the accuracy of the navigation baseline extraction is about 94%.
