Citrus recognition method based on improved YOLOv4

Abstract

The invention discloses a citrus recognition method based on improved YOLOv4. According to the method, a YOLOv4 network model structure is improved, an up-sampling module and a detection feature map sensitive to a small target are added, and citruses with relatively small individuals can be better identified; sparse training, channel pruning and layer pruning are carried out on a network model obtained through training, the defects of large memory consumption, long recognition time and the like caused by module addition are overcome, clustering is carried out by using a Canopy algorithm and ak-means + + algorithm, and a user can obtain an anchor frame parameter value more suitable for a data set of the user. When citrus recognition is carried out, an improved YOLOv4 network structure is adopted to train a citrus data set, and the obtained model can recognize a target with a small individual more accurately; before a network model is trained, through combination of layer pruning and channel pruning, the depth and the width of the model are compressed, and the training speed is improved on the premise that the precision is not lost; citrus on trees in different periods is recognized, the recognition precision is high, the speed is high, and the requirement for real-time recognition can be met.

Description

Technical field [0001] The invention relates to the technical field of image recognition, in particular to a citrus recognition method based on improved YOLOv4. Background technique [0002] Citrus is currently the fruit with the largest cultivation area, the highest yield and the largest consumption in my country. For a long time, the production of citrus in my country has mainly relied on human labor. Therefore, the application and development of computer vision recognition systems have very important practical significance. In addition, in agricultural scientific research, many researchers use computer vision recognition technology to assist in fruit yield analysis, picking, and disease prevention and control. Among them, the computer vision recognition system is one of the key technologies that restrict the current mechanization of citrus production and the application of automation technology. Accurate and rapid identification of citrus under the natural environmental condi...

AI Technical Summary

Problems solved by technology

[0004] In the existing citrus fruit identification method based on convolutional neural network, one shortcoming is that when identifying citrus fruit, it pays too much attention to the recognition accuracy of small targets, without considering the depth and detection speed of convolutional neural network; another deficiency is in optimizing When the network structure is used, the recognition accuracy is often reduced, and the recognition information for the specified target is lacking.

[0005] The main disadvantage of identifying citrus based on image calculation or region segmentation methods is the lack of recognition of smaller citrus in complex environments, which can only roughly segment the outline or characteristic description of citrus, and lose some details of citrus. to higher recognition accuracy

Images