Crop leaf abnormal image extraction method based on video monitoring

Abstract

The invention discloses a crop leaf abnormal image extraction method based on video monitoring. The method is characterized by including the steps that 1, a crop growth video is collected, and frame processing is conducted on the crop growth video; 2, a crop growth key frame image is extracted through a self-defined similarity clustering method; 3, a binary image of a salient region of the crop growth key frame image is extracted through a self-defined image binaryzation method; 4, an RGB image in which the complicated background is removed and a crop leaf abnormal region is contained is extracted through an improved image complicated background removing method. The method is capable of rapidly extracting a key frame image with few redundancies from a large number of crop growth frame images and accurately extracting crop leaf abnormal images, and therefore a scientific and effective basis is provided for automatic identification and prevention of follow-up pest and disease damage.

Description

technical field [0001] The invention belongs to the field of agricultural video monitoring, in particular to a method for extracting abnormal images of crop leaves based on video monitoring. Background technique [0002] The combination of video and image processing to extract crop abnormal information has a good application prospect in crop growth monitoring and crop scientific planting. Using computer vision technology to collect crop growth videos, extract crop pest information, and achieve timely and effective feedback on crop growth status, which has great guiding significance for the identification and control of plant diseases and pests. In the existing monitoring and information extraction methods, it is more common to use CCD cameras and Android mobile phone cameras to collect crop pictures, and to extract crop disease and insect pest information through image enhancement and segmentation. Patent ("Dang Hongshe, Zhang Fang, Tian Lina, etc. A method for detecting cr...

AI Technical Summary

Problems solved by technology

[0003] (1) In the existing crop growth image collection methods, most of the crop growth period images are collected by CCD cameras or other photographic facilities. Exception information is incomplete;

[0004] (2) In the existing crop growth key frame extraction methods, the crop growth key frames extracted by the frame difference method and online clustering method are redundant; for the key frame extraction with long crop growth cycle and insignificant feature changes, The number of redundant frames is not controlled;

[0005] (3) In the existing methods for obtaining binary images of salient regions, in terms of extracting crop growth key frame binary images with complete outlines, there are insignificant outlines of binary images and incomplete extraction of crop leaf information;

[0006] (4) In the existing methods of removing the complex background of crop growth key frames and obtaining abnormal images containing abnormal leaf regions, the abnormal leaf images cannot be effectively separated for greenhouse or field crops with dense growth and complex backgrounds

Images