Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Abstract. The navigation parameters can‘t be obtained correctly when the ambient light is stronger or darker if the guidance of rice transplanter is determined by machine vision. The environment will influence the reliability and stability of navigation greatly. Global positioning system(GPS) integrated with machine vision is a relatively new agricultural machinery navigation and positioning method. GPS was used to obtain informations such as location, direction and speed while machine vision can provide navigation line.Feature points extracted from the navigation line can be used as the next position of transplanter. With the advance of the transplanter, the automatic navigation of the transplanter can be realized by updating the feature points in front of the transplanter in real time. The Meanshift and Hough transform algorithm developed for rice transplanter were used in machine vision, and the centerline of seedling row was extracted effectively. This method was tested in laboratory and field conditions. The test results show that the algorithm can accurately locate the rice navigation rows in the image to realize automatic combined navigation. Compared with single navigation, combined navigation can obtain higher navigation accuracy and stability.