Wheat ear detection and counting method based on deep learning point supervision idea

Abstract

The invention discloses a wheat ear detection and counting method based on a deep learning point supervision idea, and the method comprises the steps: carrying out the pre-collection of a field wheatear image of a specific region, and obtaining an input image; inputting the input image into a network structure and obtaining output parameters; and obtaining each wheat ear patch and predicting thenumber of wheat ears. According to the network structure, firstly, features are extracted through a down-sampling network, and then the extracted features are subjected to up-sampling through an up-sampling path, so that the size of output is consistent with that of an input image, the probability of each pixel in the output image is obtained, and plaques of wheat ears are obtained based on the probability. The method provided by the invention can effectively overcome noise in a field environment, and realizes rapid detection and accurate counting of wheat ears. The reliability of the method is verified through various pictures of different field environments, different illumination intensities, different growth conditions and different shooting lens distances of two cities.

Description

technical field [0001] The invention relates to wheat ear detection, in particular to a wheat ear detection and counting method based on the idea of ​​deep learning point supervision. Background technique [0002] The research and development and application of artificial intelligence in the field of agriculture have begun as early as the beginning of this century. There are not only intelligent robots such as farming, sowing and picking, but also intelligent identification systems such as intelligent soil detection, detection of diseases and insect pests, and early warning of climate disasters. Livestock smart wearable products used in the livestock breeding industry. These applications are helping us increase output and increase efficiency while reducing pesticide and fertilizer use. However, there are still many problems and difficulties in the application of artificial intelligence in my country's agricultural field. Different from the degree of industrial automation, ...

AI Technical Summary

Problems solved by technology

[0010] In view of the problems existing in the current technology, especially the inability to effectively adapt to various growth stages and the environmental problems of wheat spikes with different light intensities, the accuracy rate is insufficient, it cannot be counted well, and the processing method is complicated, which requires multi-step design for processing, and cannot be end-to-end The problems such as prediction and speed at the terminal are relatively slow, the present invention improves, researches and designs a convolutional neural network model based on point supervision, and realizes the recognition and counting of ears of wheat based on image processing and deep learning technology, thereby solving the problem of There are at least some technical problems in the prior art

Images