Vehicle Guidance Parameter Determination from Crop Row Images using Principal Component Analysis

An image recognition algorithm has been developed as part of a vision-based guidance system for row crops. Each combination of the vehicle guidance parameters, offset and heading angle, was treated as a `poseʹ of the interested object, the crop rows. Whilst several pose recognition algorithms have previously been developed, the proposed algorithm is capable of determining the heading angle and the offset of a vehicle relative to the crop rows. A set of poses was collected and used as a training set. The training stage of the algorithm used the principal component analysis (Hotelling transform) to produce a low-dimensional eigenspace on which each pose was represented by its projections. Given a new image, the pose (heading angle and offset) recognition was done by projecting the image onto the eigenspace and determining the closest training image projection. Another set of poses was used to test the performance of the algorithm. Using different region of interest to train and test the algorithm, it presented the least average absolute error of 4·47 cm and 1·26° for offset and heading angle, respectively, when using the central part of images for pose determination.