https://doi.org/10.4081/jae.2024.1654 AC-YOLO: citrus detection in the natural environment of orchards
Published:27 December 2024
Abstract Views: 114
PDF: 52
HTML: 0
HTML: 0
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
Authors
In the natural environment, the shape and color of fruits can vary greatly due to various factors, and the growth of fruits is irregular, shaded by leaves and branches, and there are phenomena such as overlapping fruits. The complex background causes the difficulty of fruit recognition by the picking robot to increase, which affects the positioning of subsequent picking points, greatly increasing the difficulty of picking, and even causing damage to the end effector. To address such issues, this study adopts panoramic photography to capture images of citrus fruit trees, and proposes an AC-YOLO based citrus recognition method in the natural environment of orchards. Firstly, in the Resblock module of the YOLOv4 backbone feature extraction network, the AC network structure is integrated with different levels of feature mapping to fuse context information as small targets. At the same time, a self-attention mechanism is introduced to suppress the impact of complex backgrounds and underlying noise, improving the detection ability of small target citrus; Finally, the Mish activation function is used to replace Leaky Re LU, improving the generalization ability of the model and improving the accuracy of citrus detection. The panorama image is divided into sub images, and an improved YOLOV4 model is used for recognition. By comparing the orange recognition effects of different network models such as Fast R-CNN, Center Net, YOLOV4 series algorithms, and YOLOV5 series algorithms on the panorama image, the improved YOLOV4 network model has an accuracy rate of 96.19%, a recall rate of 95.47%, and an average accuracy of 97.27%, Compared with the original YOLOv4 model, it has increased by 1.07, 2.59, and 2.02 percentage points respectively. This method has a good recognition effect for citrus in the natural environment of orchards.
Alaaudeen, K.M., Selvarajan, S., Manoharan, H., Jhaveri, R.H. 2024. Intelligent robotics harvesting system process for fruits grasping prediction. Sci. Rep. 14:2820. DOI: https://doi.org/10.1038/s41598-024-52743-8
Bac, C.W., Roorda, T., Reshef, R., Berman, S., Hemming, J., van Henten E.J. 2016. Analysis of a motion planning problem for sweet-pepper harvesting in a dense obstacle environment. Biosyst. Eng. 146:85-97. DOI: https://doi.org/10.1016/j.biosystemseng.2015.07.004
Bai, Y., Zhang, B., Xu, N., Zhou, J., Shi, J., Diao, Z. 2023. Vision-based navigation and guidance for agricultural autonomous vehicles and robots: A review. Comput. Electron. Agr. 205:107-124. DOI: https://doi.org/10.1016/j.compag.2022.107584
Barbashov, N.N., Shanygin, S.V., Barkova, A.A. 2022. Agricultural robots for fruit harvesting in horticulture application. IOP C. Ser. Earth Environ. 981:9-32. DOI: https://doi.org/10.1088/1755-1315/981/3/032009
Chen, C., Lu, J., Zhou, M., Yi, J., Liao, M. Gao, Z. 2022. A YOLOv3-based computer vision system for identification of tea buds and the picking point. Comput. Electron. Agr. 198:107-116. DOI: https://doi.org/10.1016/j.compag.2022.107116
Du, X., Han, X., Shen, T., Meng, Z., Chen, K., Yao, X., et al. 2024. Natural frequency identification model based on BP neural network for Camellia oleifera fruit harvesting. Biosyst. Eng. 237:8-49. DOI: https://doi.org/10.1016/j.biosystemseng.2023.11.012
Fang, Z., Liang, X. 2022. Intelligent obstacle avoidance path planning method for picking manipulator combined with artificial potential field method. Ind. Robot 49:835-850. DOI: https://doi.org/10.1108/IR-09-2021-0194
Guo, Y., Dong, H., Wang, G., Ke, Y. 2018. A robotic boring system for intersection holes in aircraft assembly. Ind. Robot 4:28-336. DOI: https://doi.org/10.1108/IR-09-2017-0176
Guo, Z., Shi, Y., Ahmad, I. 2024. Design of smart citrus picking model based on Mask RCNN and adaptive threshold segmentation. PeerJ Comput. Sci. 10:e1865. DOI: https://doi.org/10.7717/peerj-cs.1865
Hannan, M.W., Burks, T.F., Bulanon, D.M. 2009. A machine vision algorithm combining adaptive segmentation and shape analysis for orange fruit detection. CIGR J. 6:1-17.
Jana, S., Basak, S., Parekh, R. 2017. Automatic fruit recognition from natural images using color and texture features. IEEE Conf. Devices for Integrated Circuit, Kalyani. pp. 620-624. DOI: https://doi.org/10.1109/DEVIC.2017.8074025
Ju, C., Kim, J., Seol, J., Son, H.I., 2022. A review on multirobot systems in agriculture. Comput. Electron. Agr. 202:107-136. DOI: https://doi.org/10.1016/j.compag.2022.107336
Krizhevsky, A., Sutskever, I., Hinton, G.E. 2012. ImageNet classification with deep convolutional neural networks. Proc. Advances in Neural Information Processing Systems 25:1097-1105.
Liu, J., Liu, Z. 2024. The vision-based target recognition, localization, and control for harvesting robots: a review. Int. J. Precis. Eng. Manuf. 25:409-428. DOI: https://doi.org/10.1007/s12541-023-00911-7
Liu, M., Bian, Y., Liu, Q., Wang, X., Wang, Y. 2024a. Weakly supervised tracklet association learning with video labels for person re-identification. IEEE Trans. Pattern. Anal. Mach. Intell. 46:3595-3607. DOI: https://doi.org/10.1109/TPAMI.2023.3346168
Liu, M., Wang, F., Wang, X., Wang, Y., Roy-Chowdhury, A.K. 2024b. A two-stage noise-tolerant paradigm for label corrupted person re-identification. IEEE Trans. Pattern. Anal. Mach. Intell. 46:4944-4956. DOI: https://doi.org/10.1109/TPAMI.2024.3361491
Luo, K., Zhang, X., Cao, C., Wu, Z., Qin, K., et al. 2023. Continuous identification of the tea shoot tip and accurate positioning of picking points for a harvesting from standard plantations. Front. Plant Sci. 14:1211279. DOI: https://doi.org/10.3389/fpls.2023.1211279
Lv, J., Xu, H., Xu, L., Zou, L., Rong, H., Yang, B., et al. 2022. Recognition of fruits and vegetables with similar‐color background in natural environment: A survey. J. Field Robot. 39:888-904. DOI: https://doi.org/10.1002/rob.22074
Mai, X., Zhang, H., Jia, X., Meng, M.Q-H., 2020. Faster R-CNN with classifier fusion for automatic detection of small fruits. IEEE T. Autom. Sci. Eng. 17:1555-1569. DOI: https://doi.org/10.1109/TASE.2020.2964289
Nehme, H., Aubry, C., Solatges, T., Savatier, X., Rossi, R., Boutteau, R. 2021. Lidar-based structure tracking for agricultural robots: Application to autonomous navigation in vineyards. J. Intell. Robot. Syst. 103:61. DOI: https://doi.org/10.1007/s10846-021-01519-7
Vasconez, J.P, Kantor, G.A, Cheein, F.A.A. 2019. Human-robot interaction in agriculture: A survey and current challenges. Biosyst. Eng. 179:35-48. DOI: https://doi.org/10.1016/j.biosystemseng.2018.12.005
Wan, S., Goudos, S. 2020. Faster R-CNN for multi-class fruit detection using a robotic vision system. Comput. Netw. 168:107-126. DOI: https://doi.org/10.1016/j.comnet.2019.107036
Wang, L., Wang, Z., Liu, M., Ying, Z., Xu, N., Mdeng, Q. 2022. Full coverage path planning methods of harvesting robot with multi-objective constraints. J. Intell. Robot. Syst. 106:17. DOI: https://doi.org/10.1007/s10846-022-01722-0
Wang, Y., He, Z., Cao, D., Ma, L., Li, K., Jia, L., Cui, Y. 2023a. Coverage path planning for kiwifruit picking robots based on deep reinforcement learning. Comput. Electron. Agr. 205:107593. DOI: https://doi.org/10.1016/j.compag.2022.107593
Wang, Y., Wu, H., Zhu, Z., Ye, Y., Qian, M. 2023b. Continuous picking of yellow peaches with recognition and collision-free path. Comput. Electron. Agr. 214:108273. DOI: https://doi.org/10.1016/j.compag.2023.108273
Xiao, X., Huang, J., Li, M., Xu, Y., Zhang, H., Wen, C., Dai, S. 2022. Fast recognition method for citrus under complex environments based on improved YOLOv3. J. Eng. 2022:148-159. DOI: https://doi.org/10.1049/tje2.12097
Xiao, X., Jiang, Y., Wang, Y. 2024. A method of robot picking citrus based on 3D detection. IEEE Instru. Meas. Mag. 27:50-58. DOI: https://doi.org/10.1109/MIM.2024.10505191
Xu, R., Li, C. 2022. A modular agricultural robotic system (MARS) for precision farming: concept and implementation. J. Field Robot. 39:387-409. DOI: https://doi.org/10.1002/rob.22056
Zhang, Q, Su, H-W. 2023. Real-time recognition and localization of apples for robotic picking based on structural light and deep learning. Smart Cities (Basel) 6:3393-3410. DOI: https://doi.org/10.3390/smartcities6060150
Zheng, X., Rong, J., Zhang, Z., Yang, Y., Li, W., Yuan, T. 2024. Fruit growing direction recognition and nesting grasping strategies for tomato harvesting robots. J. Field Robot. 41:300-313. DOI: https://doi.org/10.1002/rob.22263
Zhuang, J.J, Luo, S.M., Hou, C.J., Tang, Y., He, Y., Zue, X.Y. 2018. Detection of orchard citrus fruits using a monocular machine vision-based method for automatic fruit picking applications. Comput. Electron. Agr. 152:64-73. DOI: https://doi.org/10.1016/j.compag.2018.07.004
Supporting Agencies
National Key Research and Development Program of China, National Natural Science Foundation of China, National Natural Science Foundation of Hunan Province, China Postdoctoral Science Foundation, China Scholarship CouncilHow to Cite
Xiao, X. (2024) “AC-YOLO: citrus detection in the natural environment of orchards”, Journal of Agricultural Engineering, 55(4). doi: 10.4081/jae.2024.1654.
Copyright (c) 2024 the Author(s) 
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
PAGEPress has chosen to apply the Creative Commons Attribution NonCommercial 4.0 International License (CC BY-NC 4.0) to all manuscripts to be published.
Similar Articles
- Kamalesh Kanna S, Kumaraperumal Ramalingam, Pazhanivelan P, Jagadeeswaran R, Prabu P.C., YOLO deep learning algorithm for object detection in agriculture: a review , Journal of Agricultural Engineering: Vol. 55 No. 4 (2024)
- Francesca Valenti, Simona M.C. Porto, Giovanni Cascone, Claudia Arcidiacono, Potential biogas production from agricultural by-products in Sicily. A case study of citrus pulp and olive pomace , Journal of Agricultural Engineering: Vol. 48 No. 4 (2017)
- Xiwang Du, Xia Li, Fangtao Duan, Jiawei Hua, Mengchao Hu, Static laser weeding system based on improved YOLOv8 and image fusion , Journal of Agricultural Engineering: Vol. 55 No. 4 (2024)
- Meng Junjie, Cao Ziang, Guo Dandan, Wang Yuwei, Zhang Dashan, Liu Bingyou, Hou Wenhui, Grape detection in natural environment based on improved YOLOv8 network , Journal of Agricultural Engineering: Vol. 55 No. 4 (2024)
- Raffaele Cavalli, Stefano Grigolato, Marco Pellegrini, The evolution of a mountain road network from its original use during the First World War to meeting today’s forestry needs: current management , Journal of Agricultural Engineering: Vol. 43 No. 3 (2012)
- Marzia Quattrone, Giovanna Tomaselli, Lara Riguccio, Patrizia Russo, Assessment of the territorial suitability for the creation of the greenways networks: Methodological application in the Sicilian landscape context , Journal of Agricultural Engineering: Vol. 48 No. 4 (2017)
- Yun Zhu, Shuwen Liu, Xiaojun Wu, Lianfeng Gao, Youyun Xu, Multi-class segmentation of navel orange surface defects based on improved DeepLabv3+ , Journal of Agricultural Engineering: Vol. 55 No. 2 (2024)
- Thanaporn Singhpoo, Khwantri Saengprachatanarug, Seree Wongpichet, Jetsada Posom, Kanda Runapongsa Saikaew, Cassava stalk detection for a cassava harvesting robot based on YOLO v4 and Mask R-CNN , Journal of Agricultural Engineering: Vol. 54 No. 2 (2023)
- Xiong Bi, Hongchun Wang, Double-branch deep convolutional neural network-based rice leaf diseases recognition and classification , Journal of Agricultural Engineering: Vol. 55 No. 1 (2024)
- Juquan Ruan, Shuo Liu, Wanjing Mao, Shan Zeng, Zhuoyi Zhang, Guangsun Yin, Fine-grained recognition algorithm of crop pests based on cross-layer bilinear aggregation and multi-task learning , Journal of Agricultural Engineering: Vol. 55 No. 3 (2024)
You may also start an advanced similarity search for this article.
