Identification and location of grapevine sucker based on information fusion of 2D laser scanner and machine vision

Chemical sucker control has been proven to be a more efficient method than manual and mechanical removals. The quick and effective identification and location of suckers are key technologies for targeted spray that can reduce chemical applications and alleviate potential problems. The goal of this research was to improve the accuracy of identification and location algorithm of grapevine suckers for real-time mobile targeted spray based on information fusion of two dimensional (2D) laser scanner and camera machine vision. A triangle white calibration board was used to determine the invisible laser scanning line. The positions of the terminated points of the scanning line on the calibration board in the laser scanner’s coordinates were calculated. Suckers size and center location were obtained by ExGExR segmentation, then the relative position between the suckers and triangle calibration board was determined in the image coordinates. Eventually, the actual size and relative position between the identified suckers and the platform were calculated by integrating the laser line and image information. The results of the field trials showed that the consumed time of the developed algorithm was 0.787 s, the width recognition rate 91.8%, height recognition rate 88.2%, and the relative position accuracies 92.0%, 87.3%, which could meet the requirement of grapevine sucker precision targeted spray.