Lightweight detection method for lotus seedpod in natural environment

Tao Tang, Xu Wang, Zenghong Ma, Weiwei Hong, Gaohong Yu, Bingliang Ye

Abstract


In order to solve the problems of the current target detection algorithms, such as poor discrimination of occluded targets, multiple parameters, complex networks, large amounts of computation, and not conducive to the deployment of mobile terminals, a lightweight lotus seedpod detection method based on YOLOv5s model was proposed in this study. First, the dataset was augmented by using a combination of offline and online augmentation, which improved the adaptability and robustness of the model in complex environments. Then, a lightweight Ghost convolution module was introduced to replace the original convolution, and a lightweight bidirectional feature pyramid network was designed, which could enhance the feature extraction and fusion capability of the network and reduce the amount of calculation and model size; On this basis, the combination of WIoU loss function and Mish activation function was adopted to improve the accuracy of feature extraction. Finally, the knowledge distillation training strategy was used to ensure the proposed lightweight model has the learning ability of a complex network model, improving the recall and precision of model detection. The results of the ablation study show that the proposed method effectively improves the detection performance of the YOLOv5s model for lotus seedpods. The mean average precision of the improved model was 89.7%, compared with the original YOLOv5s model increased by 2.8%, and the parameters and FLOPs were reduced by 2.36M and 7.3G, respectively. Compared with other detection algorithm models, the proposed algorithm model has the advantages of less computation, smaller model size, and higher detection precision. Therefore, the proposed improved optimization method based on the YOLOv5s model can effectively detect lotus seedpods, which provides theoretical research and technical support for intelligent picking of lotus seedpods in the actual operating environment.
Keywords: lotus seedpod detection, deep Learning, data augmentation, lightweight, knowledge distillation, natural environment
DOI: 10.25165/j.ijabe.20231606.8281

Citation: Tang T, Wang X, Ma Z H, Hong W W, Yu G H, Ye B L. Lightweight detection method for lotus seedpod in natural environment. Int J Agric & Biol Eng, 2023; 16(6): 197–206.

Keywords


lotus seedpod detection, deep Learning, data augmentation, lightweight, knowledge distillation, natural environment

Full Text:

PDF

References


Zhu F L, Sun H, Wang J, Zheng X W, Wang T, Diao Y, et al. Differential expression involved in starch synthesis pathway genes reveal various starch characteristics of seed and rhizome in lotus （ Nelumbo nucifera）. Journal of Food Science, 2022; 87（9）: 4250–4263.

Bangar S P, Dunno K, Kumar M, Mostafa H, Maqsood S. A comprehensive review on lotus seeds （Nelumbo nucifera Gaertn.）: Nutritional composition, health-related bioactive properties, and industrial applications. Journal of Functional Foods, 2022; 89: 104937.

Chen C J, Li G T, Zhu F. A novel starch from lotus （ Nelumbo nucifera） seeds: Composition, structure, properties and modifications. Food Hydrocolloid, 2021; 120: 106899.

Zhang X, He L, Majeed Y, Whiting M D, Karkee M, Zhang Q. A precision pruning strategy for improving efficiency of vibratory mechanical harvesting of apples. Transactions of the ASABE, 2018; 61（5）: 1565–1576.

Lytridis C, Kaburlasos V G, Pachidis T, Manios M, Vrochidou E, Kalampokas T, et al. An overview of cooperative robotics in agriculture. Agronomy, 2021; 11（9）: 1818.

Rose D C, Lyon J, de Boon A, Hanheide M, Pearson S. Responsible development of autonomous robotics in agriculture. Nature Food, 2021; 2（5）: 306–309.

Li H P, Li C Y, Li G B, Chen L X. A real-time table grape detection method based on improved YOLOv4-tiny network in complex background. Biosystems Engineering, 2021; 212: 347–359.

Zhang X H, Toudeshki A, Ehsani R, Li H L, Zhang W F, Ma R J. Yield estimation of citrus fruit using rapid image processing in natural background. Smart Agricultural Technology, 2022; 2: 100027.

Koirala A, Walsh K B, Wang Z, Mccarthy C. Deep learning for real-time fruit detection and orchard fruit load estimation: Benchmarking of ' Mangoyolo′. Precision Agriculture, 2019; 20（6）: 1107–1135.

Lu Y Z, Young S. A survey of public datasets for computer vision tasks in precision agriculture. Computers and Electronics in Agriculture, 2020; 178: 105760.

Sultana F, Sufian A, Dutta P. A review of object detection models based on convolutional neural network. Intelligent Computing: Image Processing Based Applications, 2019; pp.1-16.

Zhou Z, Majeed Y, Naranjo G D, Gambacorta E M T. Assessment for crop water stress with infrared thermal imagery in precision agriculture: a review and future prospects for deep learning applications. Computers and Electronics in Agriculture, 2021; 182: 106019.

Pathak H, Igathinathane C, Howatt K, Zhang Z. Machine learning and handcrafted image processing methods for classifying common weeds in corn field. Smart Agricultural Technology, 2023; 5: 100249.

Zhang Z, Igathinathane C, Flores P, Ampatzidis Y, Liu H, Mathew J, et al. Time effect after initial wheat lodging on plot lodging ratio detection using UAV imagery and deep learning. Unmanned Aerial Systems in Precision Agriculture, 2022; pp.50-72.

Jiao L C, Zhang F, Liu F, Yang S Y, Li L L, Feng Z X, et al. A survey of deep learning-based object detection. IEEE Access, 2019; 7: 128837–128868.

Din A, Ismail M Y, Shah B B, Babar M, Ali F, Baig S U. A deep reinforcement learning-based multi-agent area coverage control for smart agriculture. Computers and Electrical Engineering, 2022; 101: 108089.

Zhang Z, Flores P, Friskop A, Liu, Z H, Igathinathane, C, Han, X, et al. Enhancing wheat disease diagnosis in a greenhouse using image deep features and parallel feature fusion. Front Plant Sci, 2022; 13: 834447.

Lu Y Z, Lu R F, Zhang Z. Detection of subsurface bruising in fresh pickling cucumbers using structured-illumination reflectance imaging. Postharvest Biol Tec, 2021; 180: 111624.

Flores P, Zhang Z, Igathinathane C, Jithin M, Naik D, Stenger J, et al. Distinguishing seedling volunteer corn from soybean through greenhouse color, color-infrared, and fused images using machine and deep learning - ScienceDirect. Ind Crop Prod, 2020; 161: 113223.

Wang P, Niu T, Mao Y R, Zhang, Z, Liu, B, He, D J. Identification of apple leaf diseases by improved deep convolutional neural networks with an attention mechanism. Frontiers Plant Science, 2021; 12: 723294.

Kang H W, Chen C. Fruit detection, segmentation and 3d visualisation of environments in apple orchards. Computers and Electronics in Agrulture, 2020; 171: 105302.

Tian Y N, Yang G D, Wang Z, Wang H, Li E, Liang Z Z. Apple detection during different growth stages in orchards using the improved yolo-v3 model. Computers and Electronics in Agriculture, 2019; 157: 417–426.

Ma J, Lu A E, Chen C, Ma X D, Ma Q C. YOLOv5-lotus an efficient object detection method for lotus seedpod in a natural environment. Computers and Electronics in Agriculture, 2023; 206: 107635.

Bhagat S, Kokare M, Haswani V, Hambarde P, Kamble R. WheatNet-lite: A novel light weight network for wheat head detection. In: 2021 IEEE/CVF International Conference on Computer Vision Workshops （ICCVW）, Montreal: IEEE, 2021; pp.1332–1341.

Zha M F, Qian W B, Yi W L, Hua J. A lightweight yolov4-based forestry pest detection method using coordinate attention and feature fusion. Entropy, 2021; 23（12）: 1587.

Cui M D, Lou Y Y, Ge Y L, Wang K Q. LES-YOLO: A lightweight pinecone detection algorithm based on improved YOLOv4-Tiny network. Computers and Electronics in Agriculture, 2023; 205: 107613.

Zhang Y, He S P, Wa S Y, Zong Z Q, Liu Y L. Using generative module and pruning inference for the fast and accurate detection of apple flower in natural environments. Information, 2021; 12（12）: 495.

Jiang P Y, Ergu D, Liu F Y, Cai Y, Ma B. A review of yolo algorithm developments. Procedia Computer Science, 2022; 199: 1066–1073.

Hu W X, Xiong J T, Liang J H, Xie Z M, Liu Z Y, Huang Q Y, et al. A method of citrus epidermis defects detection based on an improved YOLOv5. Biosystems Engineering, 2023; 227: 19–35.

Ji S J, Ling Q H, Han F. An improved algorithm for small object detection based on YOLO v4 and multi-scale contextual information. Computers and Electrical Engineering, 2023; 105: 108490.

Lu Z H, Zhao M F, Luo J, Wang G H, Wang D C. Design of a winter-jujube grading robot based on machine vision. Computers and Electronics in Agriculture, 2021; 186: 106170.




Copyright (c) 2023 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office