AUTHOR=Luo Yuanyin , Liu Yang , Wang Haorui , Chen Haifei , Liao Kai , Li Lijun TITLE=YOLO-CFruit: a robust object detection method for Camellia oleifera fruit in complex environments JOURNAL=Frontiers in Plant Science VOLUME=Volume 15 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2024.1389961 DOI=10.3389/fpls.2024.1389961 ISSN=1664-462X ABSTRACT=In the field of agriculture, automated harvesting of Camellia oleifera fruit has become an important research area. However, accurately detecting Camellia oleifera fruit in a natural environment is a challenging task. Traditional target detection techniques have poor generalization ability in large-scale production and often struggle to achieve the desired results. In addition, complex natural environments are characterized by environmental factors such as shadows, which can significantly reduce the accuracy of Camellia oleifera fruit recognition.To address these problems, we propose an efficient deep learning method called YOLO-CFruit, which is specifically designed to accurately detect Camellia oleifera fruits in challenging natural environments.First, we collected images of Camellia oleifera fruits and created a dataset, and then used a data enhancement method to further enhance the diversity of the dataset. Our YOLO-CFruit model combines a CBAM module for identifying regions of interest in landscapes with Camellia oleifera fruit and a CSP module with Transformer for capturing global information. In addition, we improve YOLO-CFruit by replacing the CIoU Loss with the EIoU Loss in the original YOLOv5. By testing the training network, we find that the method performs well, achieving an average precision of 98.2%, a recall of 94.5%, an accuracy of 98%, an F1 score of 96.2, and a frame rate of 19.02 ms. The experimental results show that our method improves the average precision by 1.2% and achieves the highest accuracy and higher F1 score among all state-of-the-art networks compared to the conventional YOLOv5s network.In addition, we evaluated the detection ability of Camellia oleifera fruit under different scenarios, such as the effects of light variations and shading levels.The experimental results show that our method has high reliability in real-world environments and provides a solid foundation for the development of automated harvesting equipment.