Dense citrus number detection method, equipment, storage medium and device

Abstract

The invention discloses a dense citrus number detection method, equipment, a storage medium and a device, and the method comprises the steps: carrying out the feature extraction of a preprocessed citrus image based on a deformable convolutional network in a preset DS-YOLO network model, and carrying out the feature fusion of a feature map according to a preset SimAM attention mechanism, and determining the coordinate and the size of a target prediction frame according to the candidate frame adjustment parameters corresponding to the target feature maps of different scales, and performing citrus number detection through the target prediction frame. According to the method, the number of the citrus in the to-be-identified citrus image is detected based on the deformable convolutional network and the preset SimAM attention mechanism in the preset DS-YOLO network model, and compared with the prior art that the detection effect on dense citrus is not ideal and the detection precision is low, the detection precision of the model is improved, and the detection efficiency is improved. High-reliability dense citrus number detection is achieved, and the defects in the prior art are overcome.

Description

technical field [0001] The invention relates to the field of citrus detection, in particular to a method, equipment, storage medium and device for detecting the quantity of dense citrus. Background technique [0002] With the rise and development of deep learning, more and more attention has been paid to smart agriculture and agricultural automation, and the use of deep learning for target detection has become a current research hotspot. The identification of overlapping and occluded citrus, the identification of citrus with texture and color similar to the environment, and the identification of citrus in multi-angle images that lead to double counting have become difficult problems in dense citrus detection. How to accurately locate dense fruits has become a problem. It is an important prerequisite for realizing the early estimation of fruit yield, and it also provides effective technical support for picking robots. [0003] At present, the mainstream deep learning-based t...

AI Technical Summary

Problems solved by technology

[0009] The main purpose of the present invention is to provide a method, equipment, storage medium and device for detecting the number of dense citrus, aiming to solve the technical problem of low detection accuracy caused by the unsatisfactory detection effect on dense citrus in the prior art

Images