Abstract: In order to improve the adaptability of the vision navigation system in the agricultural vehicle to various environments, the path recognition method for different illumination environments was proposed in this paper. Firstly, the influence of different illumination environments on the path recognition for the vision navigation system of the agricultural vehicle was investigated. Secondly, on basis of path recognition in the ordinary environment, a new method mainly composed of histogram equalization algorithm and center line detecting algorithm was applied in the path recognition in different illumination environment. Finally, the many images of different illumination environment were used to verify proposed method. Experimental results showed that the new method was effective in various illumination environments, and could obtain the target navigation path reliably and accurately. The recognition correct rate of the vision navigation system was 92%, and the average cost time was 245 ms. The research can provide a reference for design of the vision navigation system in the agricultural vehicle.