Research On The Insect-pest Detection Method Of Cabbage Based On Machine Vision And Visible Spectrum Information

The spray object recognition and localization is one of the core technology of automatic spray mechanization research. For precision spraying pesticide plant diseases and insect pests of cabbage, the accurate and automatic identification of plant diseases and insect pests of cabbage becomes the key. Therefore, this paper introduces using machine vision automatic identification of the Euclidean distance of cabbage moth pests detection system, combined with spectral imaging system composed of qualityspec spectrometer, Cabbage normal blade and suffer from the Cabbage pests of cabbage leaf color features and spectral characteristics were analyzed. The main research work and achievements are as follows.1 This paper designs sampling system and method applicable to the accurate identification of cabbage leaves pests, based on the current status spray machinery can't realize the accurate identification of target pests.2 On the basis of the test, this paper determines the pretreatment method which is suitable for the machine vision system, using software programming. The images of cabbage pests captured by. camera are pre-treated according to several means, such as B-channel grayscale, median filter and edges detection.3 According to the insect pest image feature information of cabbage leaves, this paper puts forward the algorithm based on Euclidean distance to detect pests and kale. Set the discriminant threshold Using the method of Euclidean distance, detect whether there is a pest invasion in the cabbage leaves and process morphology to pest defects detected, mark pests detected, finally.4 This paper does smooth and average processing to cabbage leaves spectrum collected being in three kinds of health status, using spectral analysis software and, extract spectral feature of cabbage moth pests blades, caterpillar pests blades and healthy cabbage leaves, adopting adaptive band selection method.5 Clustering analysis was made of the test sample feature bands by using Euclidean distance metric in this article. The results of cluster analysis showed these wavelengths of 425nm,470nm,510nm.550 nm 625nm and 675nm are as the optimal characteristic wavelengths of cabbage leaves impregnated by the cabbage moths, these wavelengths of 465nm,525nm,555nm,590 nm 680nm and 695nm are as the optimal characteristic wavelengths of cabbage leaves impregnated by the cabbage worms, these wavelengths of' 545 nm,645 nm,650 nm and 655 nm are as the optimal characteristic wavelengths of healthy cabbage leaves, is completely correct.The results show technology compositing image processing with spectrum realize automatic and accurate identification of cabbage moth pests. Some data also suggest that this method has high recognition rate, accuracy, and other advantages.It can lay the foundation for the development of the automatic control of spray robot, in order to achieve the purpose of crop diseases and pests identification and real-time treatment.