Author:
Chen Junyang,Liu Hui,Zhang Yating,Zhang Daike,Ouyang Hongkun,Chen Xiaoyan
Abstract
With the gradual increase in the annual production of citrus, the efficiency of human labor has become the bottleneck limiting production. To achieve an unmanned citrus picking technology, the detection accuracy, prediction speed, and lightweight deployment of the model are important issues. Traditional object detection methods often fail to achieve balanced effects in all aspects. Therefore, an improved YOLOv7 network model is proposed, which introduces a small object detection layer, lightweight convolution, and a CBAM (Convolutional Block Attention Module) attention mechanism to achieve multi-scale feature extraction and fusion and reduce the number of parameters of the model. The performance of the model was tested on the test set of citrus fruit. The average accuracy (mAP@0.5) reached 97.29%, the average prediction time was 69.38 ms, and the number of parameters and computation costs were reduced by 11.21 M and 28.71 G compared with the original YOLOv7. At the same time, the Citrus-YOLOv7 model’s results show that it performs better compared with the current state-of-the-art network models. Therefore, the proposed Citrus-YOLOv7 model can contribute to solving the problem of citrus detection.
Funder
Innovation and entrepreneurship training program for College Students
Subject
Plant Science,Ecology,Ecology, Evolution, Behavior and Systematics
Reference42 articles.
1. Talon, M., Caruso, M., and Gmitter, F.G. (2020). The Genus Citrus, Woodhead Publishing.
2. 15. Food and Agriculture Organization of the United Nations (FAO);Mekouar;Yearb. Int. Environ. Law,2017
3. Sebastian, K. (2014). IFPRI Books.
4. (2022, July 10). World Production of Citrus Fruits in 2020, by Region. Available online: https://www.statista.com/statistics/264002/production-of-citrus-fruits-worldwide-by-region/.
5. A review of key techniques of vision-based control for harvesting robot;Zhao;Comput. Electron. Agric.,2016
Cited by
40 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献