Facility tomato farming decision-making auxiliary method and device

Abstract

The invention provides a facility tomato farming decision-making auxiliary method and device. The method comprises the following steps: acquiring a crop image in a facility through intelligent glasses; inputting the crop image into an improved SSD network model pre-stored in the intelligent glasses, outputting a part needing farming decision, and displaying the part in the intelligent glasses, wherein the improved SSD network model is obtained by performing training on a feature extraction network structure based on a MobileNet V3 network instead of an SSD network and based on a sample image with a determined farming decision part as a label, and the farming decision comprises any one or more of pruning, flower thinning, fruit thinning, leaf picking and ripe fruit picking. According to the method, images of parts such as fruits, flowers, branches and leaves of tomatoes in different periods are obtained in a lossless image mode, and recognition is performed through a lightweight classification model suitable for a mobile environment, so that the influence of equipment factors such as processing speed and storage scale of small mobile equipment on a recognition result is greatly reduced.

Description

technical field [0001] The invention relates to the technical field of agricultural informatization, in particular to a method and device for assisting decision-making in facility tomato farming. Background technique [0002] The tomato industry, the largest and most characteristic facility among solanaceous vegetables, is of great significance to increasing the income of vegetable farmers and the development of the vegetable industry. Flower thinning, fruit thinning, leaf beating, vine falling, wrapping around seedlings, pruning and cutting, and harvesting are important to ensure tomato production and An important measure of quality can ensure nutrient supply, coordinate the balanced growth of plants, improve the commerciality of fruits, and have a wide range of application values. In the process of traditional agricultural production, relevant agricultural operations mostly depend on the experience accumulation of agricultural workers, and the labor intensity is high, whic...

AI Technical Summary

Problems solved by technology

[0004] The current partial convolutional network realizes the parameter monitoring of different crops and has a good recognition effect. However, there are constraints such as complex models, large parameter calculations, and high hardware requirements, making it difficult to operate in a mobile environment. In actual production, it is necessary to Quick online decision-making in the mobile environment to facilitate users to quickly operate

Images