Crop Covering Algorithm for Convolution Neural Network Based on Prior Threshold Optimization

The growth of crops is an important part of agricultural meteorological observations. Crop coverage reflects the results of the environmental impact on the crop. The traditional threshold segmentation method may resulting in misclassification which influences by sundries, light and shadows, fertilization and rain in the crop image. In this paper, to solve the light, shelter, shadow and other effects, we obtain Crop image segmentation and extraction coverage method based on convolution neural network optimized by RGB and HSI relation threshold method (RGB-HIS-CNN). An average 98.3% model accuracy and a pixel error of 97.53% were obtained. It provides strong support for the monitoring of growth status and the identification and monitoring of crop diseases and insects.