首页|Segmentation of unhealthy leaves in cruciferous crops for early disease detection using vegetative indices and Otsu thresholding of aerial images
Segmentation of unhealthy leaves in cruciferous crops for early disease detection using vegetative indices and Otsu thresholding of aerial images
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
By using color vegetative indices and Otsu's thresholding, we develop a method for the segmentation of unhealthy leaves in cruciferous crops as a procedure of automatic early disease detection. We apply the method on aerial RGB images collected at two different sunlight conditions, both containing multiple plants of kohlrabi with bare soil and weeds in the background. By using the M-statistic, we show how the method comprising a redefine set of the vegetative index can better discriminate between healthy leaves, unhealthy leaves, and other backgrounds. Our study indicates that the vegetative indices need to be tuned according to the types of the crop for accurate identification of infectious parts of the plant through the image processing method. We discuss its implications in precision agriculture.
NSTL
Elsevier
