Study on the Image Segmentation of Field Crops Based on the Fusion of Infrared and Visible-Light Images

Efficient and reliable image segmentation & identification is the basis of scientific crop management and a key technology for precision agriculture. This paper introduces an image segmentation algorithm based on the fusion of infrared and visible images. First of all, the fusion algorithm, which is based on the second-generation Curvelet transformation, was used to fuse the infrared and visible images, and then a cross validation was conducted on the areas of interest on the images to eliminate the interference of background and finally, by taking the estimated contour of the treated target as the initial growth curve, the dynamic edge evolution technology was employed to fix the edge of the target and complete the segmentation. According to the experimental results, this algorithm can effectively fuse the important information in the visible and infrared images without damaging the shape characteristics of crops, thus achieving better segmentation results.