https://doi.org/10.4081/jae.2024.1588
Fast identification of tomatoes in natural environments by improved YOLOv5s
Published: 9 July 2024
Abstract Views: 114
PDF: 63
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
Real time recognition and detection of tomato fruit maturity is a key function of tomato picking robots. Existing recognition and detection algorithms have slow speed and low recognition accuracy for small tomatoes. Here, a tomato fruit maturity detection model YOLOv5s3 based on improved YOLOv5s was proposed and its accuracy was verified through comparative experiments. On the basis of YOLOv5s, an SC module was proposed based on channel shuffle packet convolution. Then, A C3S module is constructed, which replaced the original C3 module with this C3S module to reduce the number of parameters while maintaining the feature expression ability of the original network. And a 3-feature fusion FF module was put forward, which accepted inputs from three feature layers. The FF module fused two feature maps from the backbone network. The C2 layer of the backbone was integrated, and the large target detection head was removed to use dual head detection to enhance the detection ability of small targets. The experimental results showed that the improved model has a detection accuracy of 94.8%, a recall rate of 96%, a parameter quantity of 3.02M, and an average accuracy (mAP0.5) of 93.3% for an intersection over union (IoU) of 0.5. The detection speed reaches 9.4ms. It can quickly and accurately identify the maturity of tomato fruits, and the detection speed is 22.95%, 33.33%, 48.91%, 68.35%, 15%, and 25.98% higher than the original YOLOv5s, YOLOv5m, YOLOv5l, YOLOv5x, YOLOv5n, and YOLOv4, respectively. The real-time testing visualization results of different models indicated that the improved model can effectively improve detection speed and solve the problem of low recognition rate for small tomatoes, which can provide reference for the development of picking robots.
Cámara-Zapata J.M., Brotons-Martínez J.M., Simón-Grao S., Martinez-Nicolás J.J., García-Sánchez F. 2019. Cost–benefit analysis of tomato in soilless culture systems with saline water under greenhouse conditions. J. Sci. Food Agric. 99:5842-5851.
DOI: https://doi.org/10.1002/jsfa.9857
Chen K.Y., Zhu L.F., Song P., Tian X.M., Huang C.L., Nie X.H., Xiao A.L., He L.R. 2021. Recognition of cotton terminal bud in field using improved Faster R-CNN by integrating dynamic mechanism. Transactions of the Chinese Society of Agricultural Engineering. 37(16):161-168.
Chen M.Q, Yu L.J., Zhi C., Sun R.J., Zhu S.W., Gao Z.Y., Ke Z.X., Zhu M.Q., Zhang Y.M. 2022. Improved faster R-CNN for fabric defect detection based on Gabor filter with Genetic Algorithm optimization. Computers in Industry. 134:103551.
DOI: https://doi.org/10.1016/j.compind.2021.103551
Du F.J., Jiao S.J. 2022. Improvement of lightweight convolutional neural network model based on YOLO algorithm and its research in pavement defect detection. Sensors. 22:3537.
DOI: https://doi.org/10.3390/s22093537
Jiang B.R., Luo R.X., Mao J.Y., Xiao T.T., Jiang Y.N. 2018. Acquisition of localization confidence for accurate object detection. European Conference on Computer Vision (ECCV) 2018. 1807.11590.
DOI: https://doi.org/10.1007/978-3-030-01264-9_48
Jiang T., Li C., Yang M., Wang Z. 2022. An improved YOLOv5s algorithm for object detection with an attention mechanism. Electronics. 11:2494.
DOI: https://doi.org/10.3390/electronics11162494
Liu X.G., Fan C., Li J.N., Gao Y.L., Zhang Y.Y., Yang Q.L. 2020. Identification method of strawberry based on convolutional neural network. Transactions of the Chinese Society for Agricultural Machinery. 51(2):237-244.
Lü S.L., Lu S.H., Li Z., Hong T.S., Xue Y.J., Wu B.L. 2019. Orange recognition method using improved YOLOv3-LITE lightweight neural network. Transactions of the Chinese Society of Agricultural Engineering. 35(17):205-214.
Ma L., Guo X.L., Zhao S.K., Yin D.D., Fu Y.Y., Duan, P.Q., Wang B.B., Zhang L. 2021. Algorithm of strawberry disease recognition based on deep convolutional neural network. Complexity. 2021:6683255.
DOI: https://doi.org/10.1155/2021/6683255
Qi J.T., Liu X.N., Liu K., Xu F.R., Guo H., Tian X.L., Li M., Bao Z.Y., Li Y. 2022. An improved YOLOv5 model based on visual attention mechanism: Application to recognition of tomato virus disease. Computers and Electronics in Agriculture. 194:106780.
DOI: https://doi.org/10.1016/j.compag.2022.106780
Qiao Y., Hu Y., Zheng Z., Yang H., Zhang K., Hou J., Guo J. 2022. A counting method of red jujube based on improved YOLOv5s. Agriculture. 12:2071.
DOI: https://doi.org/10.3390/agriculture12122071
Redmon J., Divvala S., Girshick R., Farhadi A. 2016. You only look once: unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016:779-788.
DOI: https://doi.org/10.1109/CVPR.2016.91
Seo D., Cho B-H., Kim K-C. 2021. Development of monitoring robot system for tomato fruits in hydroponic greenhouses. Agronomy. 11:2211.
DOI: https://doi.org/10.3390/agronomy11112211
Shang Y.Y., Zhang Q.R., Song H.B. 2022. Application of deep learning using YOLOv5s to apple flower detection in natural scenes. Transactions of the Chinese Society of Agricultural Engineering. 38(9): 222-229.
Sun F.G., Wang Y.L., Lan P., Zhang X.D., Chen X.D., Wang Z.J. 2022. Identification of apple fruit diseases using improved YOLOv5s and transfer learning. Transactions of the Chinese Society of Agricultural Engineering. 38(11):171-179.
Wang F., Sun Z., Chen Y., Zheng H., Jiang J. 2022. Xiaomila green pepper target detection method under complex environment based on improved YOLOv5s. Agronomy. 12:1477.
DOI: https://doi.org/10.3390/agronomy12061477
Wang L.S., Qin M.X., Lei J.Y., Wang X.F., Tan K.Z. 2021. Blueberry maturity recognition method based on improved YOLOv4-Tiny. Transactions of the Chinese Society of Agricultural Engineering 37(18):170-178.
Xiao Q.M., Niu W.D., Zhang H. 2015. Predicting fruit maturity stage dynamically based on fuzzy recognition and color feature. Proceedings of 2015 IEEE 6th International Conference on Software Engineering and Service Science. 2015:968-972.
DOI: https://doi.org/10.1109/ICSESS.2015.7339210
Xu W.C., Yan Z. 2022. Research on strawberry disease diagnosis based on improved residual network recognition model. Mathematical Problems in Engineering. 2022:6431942.
DOI: https://doi.org/10.1155/2022/6431942
Yang J., Qian Z., Zhang Y.J., Qin Y., Miao H. 2022. Real-time recognition of tomatoes in complex environments based on improved YOLOv4-tiny. Transactions of the Chinese Society of Agricultural Engineering. 38(9):215-221.
Yang R.L., Hu Y.W., Yao Y., Gao M., Liu R.M. 2022. Fruit target detection based on BCo-YOLOv5 model. Mobile Information Systems. 2022:8457173
DOI: https://doi.org/10.1155/2022/8457173
Yao Q., Gu J.L., Lv J., Guo L.J., Tang J., Yang B.J, Xu W.G. 2020. Automatic detection model for pest damage symptoms on rice canopy based on improved RetinaNet. Transactions of the Chinese Society of Agricultural Engineering. 36(15):182-188.
Yu X.H., Kong D.Y., Xie X.X., Wang Q., Bai X.W. 2022. Deep learning-based target recognition and detection for tomato pollination robots. Transactions of the Chinese Society of Agricultural Engineering. 38(24):129-137.
Yu Y., Zhao J., Gong Q., Huang C., Zheng G., Ma J. 2021. Real-time underwater maritime object detection in side-scan sonar images based on transformer-YOLOv5. Remote Sens. 13:3555.
DOI: https://doi.org/10.3390/rs13183555
Zhang F., Chen Z.J., Bao R.F., Zhang C.C., Wang Z.H. 2021. Recognition of dense cherry tomatoes based on improved YOLOv4-LITE lightweight neural network. Transactions of the Chinese Society of Agricultural Engineering. 37(16):270-27
Zhang Y.Q., Xiao D.Q., Chen H.K., Liu Y.F. 2021. Rice panicle detection method based on improved faster R-CNN. Transactions of the Chinese Society for Agricultural Machinery. 52(8):231-240.
Zhou G.H., Ma S., Liang F.F. 2022. Recognition of the apple in panoramic images based on improved YOLOv4 model. Transactions of the Chinese Society of Agricultural Engineering. 38(21):159-168.
How to Cite
Wang, H. (2024) “Fast identification of tomatoes in natural environments by improved YOLOv5s”, Journal of Agricultural Engineering, 55(3). doi: 10.4081/jae.2024.1588.
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
- Alessio Cislaghi, Gian Battista Bischetti, Best practices in post-flood surveys: The study case of Pioverna torrent , Journal of Agricultural Engineering: Vol. 53 No. 2 (2022)
- Lucio Brunetti, Ferruccio Giametta, Pasquale Catalano, Francesco Villani, Jonathan Fioralba, Flavio Fucci, Giovanna La Fianza, Energy consumption and analysis of industrial drying plants for fresh pasta process , Journal of Agricultural Engineering: Vol. 46 No. 4 (2015)
- Giuliano Vox, Pierfrancesco Losito, Fabio Valente, Rinaldo Consoletti, Giacomo Scarascia-Mugnozza, Evelia Schettini, Cristoforo Marzocca, Francesco Corsi, A wireless telecommunications network for real-time monitoring of greenhouse microclimate , Journal of Agricultural Engineering: Vol. 45 No. 2 (2014)
- Francesco Barreca, Pasquale Praticò, Giuseppe Davide Cardinali, A low-energy storage container for food and agriculture products , Journal of Agricultural Engineering: Vol. 52 No. 3 (2021)
- Fang Huimin, Niu Mengmeng, Zhu Zhengbo, Zhang Qingyi, Experimental and numerical investigations of the impacts of separating board and anti-blocking mechanism on maize seeding , Journal of Agricultural Engineering: Vol. 53 No. 1 (2022)
- Raffaele Cavalli, Stefano Grigolato, Andrea Sgarbossa, Productivity and quality performance of an innovative firewood processor , Journal of Agricultural Engineering: Vol. 45 No. 1 (2014)
- Rania Majdoubi, Lhoussaine Masmoudi, Abderrahmane Elharif, Soil profile analysis based on the identification of the bevametric parameters using a cone penetrometer , Journal of Agricultural Engineering: Vol. 53 No. 4 (2022)
- Daniela Lovarelli, Elisabetta Riva, Gabriele Mattachini, Marcella Guarino, Giorgio Provolo, Assessing the effect of barns structures and environmental conditions in dairy cattle farms monitored in Northern Italy , Journal of Agricultural Engineering: Vol. 52 No. 4 (2021)
- Eleonora Iaccheri, Chiara Cevoli, Santina Romani, Marco Dalla Rosa, Giovanni Molari, Angelo Fabbri, Simple and efficient approach for shelf-life test on frozen spinach and parsley , Journal of Agricultural Engineering: Vol. 52 No. 3 (2021)
- Giacomo Scarascia-Mugnozza, Silvana Fuina, Sergio Castellano, Structural design and experimental tests on a model of tensegrity greenhouse prototype , Journal of Agricultural Engineering: Vol. 52 No. 3 (2021)
<< < 7 8 9 10 11 12 13 14 15 16 > >>
You may also start an advanced similarity search for this article.
