Because Taiwan is located in a subtropical zone, it is suitable for crop growth. However, it is also susceptible to plant disease and natural calamity. Through the establishment of facilities agriculture, we can monitor the production environment, automate the process and reduce the impact of plant disease and natural calamity. Agricultural activities often require the use of vehicles to carry related equipment, facilities or crops. Following the intelligent agriculture 4.0 concept, this paper aims to establish an agricultural vehicle positioning system to assist path planning and obstacle avoidance systems. In this paper, the positioning method combines SLAM with visual orientation. For visual orientation, two different methods are proposed to set up the monitoring camera. The first method is to set up the camera and place the monitoring image parallel to the ground. The second method is non-parallel. The former is simple and stable for object tracking, but the monitoring range is limited by the camera angle. The latter needs to use the deep learning method to achieve object tracking. The monitoring range is wider, but the error is larger than that of the former. This paper also compares two methods of converting image coordinates into world coordinates: one is the bird-eye view transformation method and the other is the fully-connected layer transformation method. Among the three different setup positions, the average error distance of the former is 0.10734 meters, and that of the latter is 0.033525 meter. Finally, by combining SLAM with visual orientation, more accurate positioning information can be obtained than in the original, with an optimization ratio of about 3% to 5%.