Identification method for stressed state of water fertilizer of greenhouse crop on basis of computer vision technology

Abstract

The invention relates to an identification method for a stressed state of a water fertilizer of a greenhouse crop on basis of a computer vision technology. According to the identification method provided by the invention, a crop under a greenhouse environment is taken as a research object; a computer vision monitoring platform is constructed; a plant image cutting method which adapts to the change in natural illumination and a complex scene is researched; an obtained plant blade image is extracted at the aspects of morphology, color, grain and the like, and sufficient characteristic sets are constructed; a heuristic search algorithm, such as a genetic algorithm, a simulated annealing algorithm, an ant colony algorithm, a particle swarm optimization, or the like, is combined with a neural network technique for searching for the optimal characteristic subset; and a BP (Back Propagation) neural network is utilized to identify a stressed characteristic of the crop. A camera is moved by using a horizontal positioning system, so that the plant image is all-dimensionally obtained; the algorithm operation is realized by using a CUDA (Compute Unified Device Architecture) hardware platform, so as to meet the real-time demand on monitoring; and the invention provides a technical method for measuring destructiveness under the stressed state of the water fertilizer of the greenhouse crop and the application prospect is wide.

Description

technical field [0001] The invention belongs to the field of greenhouse plant monitoring, and in particular relates to a method for recognizing water and fertilizer stress state of greenhouse crops based on computer vision. Background technique [0002] As a new mode of agricultural production, facility agriculture has become an important way to solve the contradictions between population, food and land. At present, low technological content, high labor intensity, low production level and low efficiency are common in my country's facility agricultural production, and there is an urgent need for technological improvement, especially the use of modern information technology to realize automatic control and intelligent management of the facility greenhouse environment, in order to improve my country's facility agriculture production technology level, to further improve economic benefits and resource utilization. To achieve precise control of the greenhouse environment, it is c...

AI Technical Summary

Problems solved by technology

[0006] Computer vision technology has made great progress in the monitoring of crop stress characteristics, but there are still some problems. (1) Due to the uneven illumination of the agricultural crop environment, large changes in natural illumination, unsatisfactory imaging conditions, complex backgrounds, and difficult segmentation, large Part of the research is carried out under laboratory conditions with controllable lighting, so that the gray level of the target crop and the background is quite different, adapting to natural lighting changes, and the problem of target segmentation of complex background images has not been effectively solved; (2) In the visual system The current image processing algorithm is customized for specific objects, lacks robustness when conditions change, and is difficult to expand and reuse in the face of different problems; (3) previous research is aimed at a single stress feature of plants (such as water or nitrogen deficiency) monitoring, and a successful visual monitoring system requires the ability to identify multiple stress features at the same time; (4) extract one or more features for identification after image segmentation, and the stress features of different crops in different states are different. How to construct a large enough feature set for identifying stress features in terms of shape, color, texture, etc. for different crops, and adaptively optimize the selection lacks an effective method; (5) image processing algorithms are time-consuming, how to choose It is also a problem to realize fast calculation on an economical, reasonable and efficient hardware platform to meet the requirements of real-time monitoring

Images