Wheat ear counting method and device

Abstract

The embodiment of the invention provides a wheat ear counting method and device, and belongs to the technical field of deep learning. The method comprises the steps that an image shot in a wheat fieldenvironment is input into an image recognition model, a label of the image is output, and the image recognition model is obtained through training based on a sample label image and a label corresponding to the sample label image; and if the tag is a wheat ear image, determining the number of wheat ears in the image based on a non-maximum inhibition algorithm. The wheat ear quantity can be automatically calculated; Therefore, the automation degree is high, the recognition efficiency is high, the subjective influence caused by manual intervention can be effectively reduced, the application costand the complexity of the detection process are reduced, the accuracy and the real-time performance of wheat ear detection can be effectively improved, and a reliable and accurate data basis is provided for relevant research of wheat yield prediction.

Description

technical field [0001] The embodiments of the present invention relate to the field of deep learning technology, and in particular to a method and device for counting ears of wheat. Background technique [0002] Yield prediction is one of the important links in wheat production management, and the number of ears per unit area is one of the commonly used indicators to characterize wheat yield. Therefore, it is of great significance to quickly and accurately identify wheat ears and detect the number of ears per unit area for yield estimation. The traditional manual counting method is not only time-consuming and labor-intensive, but also highly subjective, and lacks a unified standard for counting ears of wheat. Therefore, there is an urgent need for an effective ear counting method to predict the yield of winter wheat. [0003] Computer vision is currently the main technical means for wheat ear recognition, detection and counting. It uses wheat RGB images to obtain the color...

AI Technical Summary

Problems solved by technology

Although these methods have achieved certain results, they need to manually set image features, and wheat ears at different growth stages have different characteristics, and the color of wheat ears at the mature stage is not much different from the color of wheat plants, so it is difficult to identify them simply by using color features ears of wheat

These methods are not robust enough to noise such as uneven illumination and complex background in the field environment, and it is difficult to expand their applications.

Images