The successful development of a vision guidance system for agriculture

Abstract In a project which has lasted 3 years, a vision guidance system has been developed to the stage where commercial availability is imminent. Six prototypes have been field tested by farmers and two more are on trial in the United States. There have been several changes of technology but the fundamental principles have remained consistent. The system derives its guidance signal from a video camera image of the rows of a crop such as cotton. It is relatively insensitive to additional visual ‘noise’ from weeds, while tolerating the fading out of one or more rows in a barren patch of the field. The software integrates data from several crop rows, and tests each row for image quality. Colour components of the image signal can be selected to improve discrimination between crop and detritus. Experimental results are presented showing that the system is capable of maintaining an accuracy of 2 cm. Some farmer responses from the extensive field trials are also included.