Abstract
Image analysis for an autonomous agricultural vehicle was studied, and the TV camera direction to the furrow and crop row was identified from the field images. The boundary of furrow and crop row was approximated by two lines using Hough transform and the camera position was identified from the parameter of these two lines by perspective transformation. The boundary was identified by two ways, and the horizontal scanning method was used in the early stage of growth, and the largest area method was used in the later stage. The results showed that the estimeted position was in good agreement with the actual position.
