Skip to main navigation menu Skip to main content Skip to site footer
International Journal of Robotics and Automation Technology

Articles

Vol. 9 (2022)

Multi-Growth Period Tomato Fruit Detection Using Improved Yolov5

DOI
https://doi.org/10.31875/2409-9694.2022.09.06
Submitted
November 25, 2022
Published
25.11.2022

Abstract

Abstract: In agricultural mechanized production, in order to ensure the efficiency of hand-eye cooperative operation of tomato picking robot, the recognition accuracy and speed of multi-growth period tomato fruit is an important basis. Therefore, in order to improve the recognition speed of multi-growth period tomato fruit while ensuring or improving the accuracy, this paper improves the Yolov5s model by adding the architecture of the lightweight mobilenetv3 model. Firstly, the deep separable convolution is replaced in the backbone network of Yolov5s, which reduces the amount of convolution operation. Secondly, the linear bottleneck inverse residual structure is fused to obtain more features in high-dimensional space and perform convolution operation in low-dimensional space. Third, the attention mechanism is inserted into the last layer of the network to highlight features and improve accuracy. The research results show that the recognition accuracy of the improved Yolov5 model remains above 98%, the CPU recognition speed is 0.88f·s-1 faster than Yolov5s, and the GPU recognition speed is 90 frames per second faster than Yolov5s. Finally, a set of the recognition software system of multi-growth period tomato fruit is designed and developed by using RealSense D435i depth camera and PYQT. The software system further verifies the feasibility of the improved Yolov5 model, and lays a foundation for the visual software design of agricultural picking robot picking recognition.

References

  1. Nicola S, Tibaldi G, Fontana E. Tomato production systems and their application to the tropics. [J]. Acta Horticulturae, 2009; 821: 27-33. https://doi.org/10.17660/ActaHortic.2009.821.1
  2. Fao. Faostat database [EB/OL]. http://www.fao.org/faostat/en/#data/QC.
  3. TX Zheng, MZ Jiang, MC Feng. Vision based target recognition and location for picking robot: a review[J]. Chinese J. Scientific Instrument, 2021; 09(42): 28-51.
  4. Arefi A, Motlagh A. Development of an expert system based on wavelet transform and artificial neural networks for the ripe tomato harvesting robot [J]. Australian Journal of Crop Science, 2013,5(7): 699-705.
  5. C Hu, X Liu, Z Pan, P LI. Automatic Detection of Single Ripe Tomato on Plant Combining Faster R-CNN and Intuitionistic Fuzzy Set [J]. IEEE Access, 2019; 7: 154683-154696. https://doi.org/10.1109/ACCESS.2019.2949343
  6. Payne A, Walsh K, Subedi P. Estimating mango crop yield using image analysis using fruit at 'stone hardening' stage and night time imaging. [J]. Computers and Electronics in Agriculture, 2014,100:160-167. https://doi.org/10.1016/j.compag.2013.11.011
  7. Sa I, Ge Z, Dayoub F. Deep Fruits: A Fruit Detection System Using Deep Neural Networks [J]. Sensors, 2016,16(8): 1222. https://doi.org/10.3390/s16081222
  8. WK Jia, YY Tian, R Luo, ZH Zhang, J Lian, YJ Zheng. Detection and segmentation of overlapped fruits based on optimized mask R-CNN application in apple harvesting robot [J]. Computers and Electronics in Agriculture, 2020,172. https://doi.org/10.1016/j.compag.2020.105380
  9. HW Kang, C Chen. Fast implementation of real-time fruit detection in apple orchards using deep learning[J]. Computers and Electronics in Agriculture, 2020,168. https://doi.org/10.1016/j.compag.2019.105108
  10. Koirala A, Walsh KB, Wang Z. Deep learning for real-time fruit detection and orchard fruit load estimation: benchmarking of 'Mango YOLO' [J]. Precision Agriculture, 2019; 20(6): 1107-1135. https://doi.org/10.1007/s11119-019-09642-0
  11. G Liu, JC Nouaze, Mbouembe PL Touko, JH Kim. Yolo-Tomato: A Robust Algorithm for Tomato Detection Based on YOLOv3 [J]. Sensors, 2020; 7(20): 2145. https://doi.org/10.3390/s20072145
  12. Gai RCNY. A detection algorithm for cherry fruits based on the improved YOLO-v4 model [J]. Neural Comput & Applic, 2021. https://doi.org/10.1007/s00521-021-06029-z
  13. Antihus Hernández Gómez, Guixian HU, Jun Wang, Annia García Pereira. Evaluation of tomato maturity by electronic nose [J]. Computers and Electronics in Agriculture, 2006; 54(1): 44-52. https://doi.org/10.1016/j.compag.2006.07.002
  14. S Lian, L Li, W Tan, L Tan. Research on Tomato Maturity Detection Based on Machine Vision [J]. The International Conference on Image, Vision and Intelligent Systems, 2022; 813. https://doi.org/10.1007/978-981-16-6963-7_60
  15. Bargoti S, Underwood JP. Image Segmentation for Fruit Detection and Yield Estimation in Apple Orchards[J]. Journal of Field Robotics, 2017; 34(6): 1039-1060. https://doi.org/10.1002/rob.21699
  16. Joseph Redmon, Ali Farhadi. YOLOv3: An Incremental Improvement [J]. arXiv preprint arXiv, 2018;1804: 02767.
  17. A Bochkovskiy, CY Wang, H Liao. Yolov4: optimal speed and accuracy of object detection [J]. arXiv preprint arXiv, 2020,10934.
  18. Hongchun QU, Min Sun. A lightweight network for mummy berry disease recognition [J]. Smart Agricultural Technology, 2022; 100044(2). https://doi.org/10.1016/j.atech.2022.100044
  19. Howard A, Sandler M, Chu G, et al. Searching for MobileNetV3: IEEE/CVF International Conference on Computer Vision[C], Seoul, 2019. https://doi.org/10.1109/ICCV.2019.00140
  20. Sandler M, Howard A, Zhu M, et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)[C], Salt Lake City, UT, 2018. https://doi.org/10.1109/CVPR.2018.00474
  21. Wen C, Wen J, LI J, et al. Lightweight silkworm recognition based on Multi-scale feature fusion [J]. Computers and Electronics in Agriculture, 2022; 200: 107234. https://doi.org/10.1016/j.compag.2022.107234
  22. J Hu, L Shen, S Albanie, G Sun, E Wu. Squeeze-and-Excitation Networks [J]. IEEE Trans. Pattern Anal. Mach. 2022,42: 2011-2023. https://doi.org/10.1109/TPAMI.2019.2913372
  23. Andriyanov N. Intelligent System for Estimation of the Spatial Position of Apples Based on YOLOv3 and Real Sense Depth Camera D415 [J]. Symmetry, 2022; 14(1): 148. https://doi.org/10.3390/sym14010148