Rice tillering stage weed segmentation identification method based on improved coding and decoding network

Abstract

The invention discloses a rice tillering stage weed segmentation identification method based on an improved coding and decoding network. The method comprises the following steps: (1) collecting a rice farmland image in a tillering stage; (2) carrying out image preprocessing, image enhancement and semantic annotation on the collected rice farmland image; (3) inputting the image subjected to preprocessing enhancement and semantic annotation into the improved coding and decoding U-Net network, and training the improved coding and decoding U-Net network to obtain a rice weed segmentation model; and (4) performing identification detection on a to-be-detected rice farmland image in a tillering stage by using the rice weed segmentation model, and outputting an identification detection result to obtain segmentation conditions of rice and weeds in the rice farmland image. According to the invention, accurate identification and accurate positioning of the weed-dense area in the paddy field are realized by adopting the improved coding and decoding network, so that the accurate herbicide spraying operation in the weed-dense area in the paddy field can be guided, and the pesticide dosage is reduced.

Description

technical field [0001] The invention relates to a method for identifying rice weeds, in particular to a method for segmenting and identifying weeds in rice tillering stage based on an improved codec network. Background technique [0002] Weeds in rice fields have brought great harm to rice growth. Weeds compete with rice for nutrients, water, and light, which affects rice growth and reduces the quality and yield of rice grains. In order to prevent or control field weeds, the common method is to evenly spray and weed the entire operation area, which will inevitably lead to excessive application of pesticides, and will also cause increased weed resistance, waste of pesticides and environmental pollution And other issues. Precision spraying technology is one of the new technologies in modern agriculture. In the control of farmland weeds, how to achieve precise spraying is of great significance to reduce the use of pesticides and reduce the pollution to the agricultural ecologi...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, the weed identification and analysis method based on remote sensing spectrum technology requires high optical equipment for data collection, resulting in a significant increase in cost, which is not conducive to maintenance and has low practicability. Most of the research is limited to laboratory research, which is not conducive to practical Popularization of farmland weed identification technology

However, traditional machine learning-based methods for identifying farmland weeds require artificial design of weed color, shape, texture and other features as the feature learning basis for machine learning algorithms; this method of selecting features mainly relies on human experience to judge and screen , not only the efficiency is low, but also the recognition results are subjective and unstable, and the recognition effect is often related to the quality of the selected features, which leads to the poor robustness of the constructed classifier and the low recognition accuracy of crop weeds

Images