Corn plant type identification method, device, electronic device and storage medium

Abstract

The invention provides a corn plant type identification method, device, electronic equipment and storage medium. The method includes: acquiring a field corn plant image, obtaining an edge image based on the field corn plant image; and disconnecting the annular path of the edge image based on the edge image , obtain the initial path set; based on the initial path set, remove the multi-path connection points corresponding to the field corn plant image to obtain the path end point set; perform quadratic curve fitting on each pair of end points in the path end point set to obtain the target path set ; Based on the target path set, determine the angle between the center line of the corn stalk and the straight line fitting the corn leaf veins, and determine the corn plant type based on the angle. The method provided by the invention can automatically determine the maize plant type through the field maize plant image, without manual identification, greatly improves the efficiency of plant type data collection, and the accuracy of the maize plant type judgment, and is the development of automatic variety evaluation and commercial breeding. Provide support.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a corn plant type recognition method, device, electronic equipment and storage medium. Background technique [0002] Corn is the most important food crop in the world, and its plant types are divided into three types: compact type, semi-compact type and flat type. It is of great significance for the selection and evaluation of maize varieties. [0003] The plant type of corn varieties is judged by the angle between the leaves and the stalk. Currently, it mainly relies on methods such as manual measurement, background setting photography, 3D point cloud scanning or subjective judgment. The manual measurement method requires a lot of labor in the field, and it is difficult for one person to complete it; to set the background to take pictures, it is necessary to set a background curtain behind the corn plants, then take pictures, and then perform graphic segmentation and ...

AI Technical Summary

Problems solved by technology

The manual measurement method requires a lot of labor in the field, and it is difficult for one person to complete it; setting up the background to take pictures requires setting up a background curtain behind the corn plants, then taking pictures, and then performing graphic segmentation and plant type judgment. The background setting is cumbersome; 3D point cloud scanning requires A single corn plant is placed in a 3D scanning environment, which is costly and complicated to leave the field, and can only be used in a laboratory environment; subjective judgment is currently the most commonly used method, and observers directly give plant type judgments based on their own experience. large deviation between

Images