Image processing and analysis for autonomous grapevine pruning

Abstract

In recent years, methods have been developed to automate vineyard operations to address the ever increased labor cost. One operation that has not been completely automated is grapevine pruning. A robotic machine for grapevine pruning needs to respond to the changing physical characteristics of the environment, and to date, no algorithm can accurately identified appropriate positions for grapevine pruning in a variety of environmental conditions. This paper presents the development of an image processing and image analysis algorithm to determine pruning position. Ten images full of canes were analyzed, and an 85% success rate for pruning positions was achieved.