Deep learning pest detection on Indonesian red chili pepper plant based on fine-tuned YOLOv5

(1) * Indra Agustian Mail (Study Program of Electrical Engineering, University of Bengkulu, Indonesia)
(2) Ruvita Faurina Mail (Study Program of Informatics, University of Bengkulu, Indonesia)
(3) Sahrial Ihsani Ishak Mail (Study Program of Informatics, University of Bengkulu, Indonesia)
(4) Ferzha Putra Utama Mail (Study Program of Informatics, University of Bengkulu, Indonesia)
(5) Kusmea Dinata Dinata Mail (Agricultural Technology Study Center, Agriculture Department, Province of Bengkulu, Indonesia)
(6) Novalio Daratha Mail (Study Program of Electrical Engineering, Indonesia)
*corresponding author

Abstract


.This research developed a pest detection model for Indonesian red chili pepper based on fine-tuned YOLOv5. Indonesian red chili pepper is the third largest vegetable commodity produced in Indonesia. Pest attacks disrupt the quantity and quality of crop yields. To control pests effectively, it is necessary to detect the type of pest correctly. A viable solution is to leverage computer vision and deep learning technologies. However, no previous studies have developed a pest detection model for Indonesian red chili pepper based on this technology. YOLOv5 is a variant of the YOLO object detection algorithm, which has major advantages in terms of computation cost and execution speed. The dataset comprises 4,994 image files collected from a chili plantation in Bengkulu province, Indonesia, covering 4 different classes and a total of 10,683 pests. The image is 1216 x1216 px with the smallest, largest, and average object dimensions of 2%, 35%, and 4% of the image dimensions. The training model used is fine-tuning YOLOv5s with variations of patience as an early stop parameter of 100, 200, and 300. The evaluation of the trained model is based on train loss, validation loss, and mAP@0.5:0.95, the best-trained model is the 445th epoch on patience 100 with the best confidence value of 0.321 and the highest TF1 of 0.74. From the best-trained model testing on the test dataset, the mAP@0.5 performance for all classes is 81.3%. The model not only detected large pests but was also able to detect objects that were small in size compared to the image size. The best-trained model's best mAP@0.5 performance and speed are 82.6% and 20 ms/image, or 50 fps on NVIDIA P100 GPU.

Keywords


Deep learning; Yolo; Indonesia red chili paper; Pest detection

   

DOI

https://doi.org/10.26555/ijain.v9i3.864
      

Article metrics

Abstract views : 633 | PDF views : 227

   

Cite

   

Full Text

Download

References


[1] M. Khalil, E. Kesumawati, and S. Zakaria, “Begomoviral disease rates and the implications to the growth and yield of chili plants (Capsicum annuum L.) at different elevations in Indonesia,” J. Appl. Hortic., vol. 22, no. 1, pp. 71–75, Apr. 2020, doi: 10.37855/JAH.2020.V22I01.14.

[2] Badan Pusat Statistik Indonesia, “Statistik tanaman sayuran dan buah-buahan semusim Indonesia 2018,” BPS-Statistics Indones., pp. 1–101, 2018, Accessed: April. 23, 2023. Available at : https://www.bps.go.id/publication/2019/10/07/9c5dede09c805bc38302ea1c/statistik-tanaman-sayuran-dan-buah---buahan-semusim-indonesia-2018.html.

[3] K. Subagyono et al., Budidaya dan Pascapanen Cabai Merah (Capsicum annuum L.). BPTP Jateng / KAN, 2010. Available at: https://repository.pertanian.go.id/handle/123456789/9109.

[4] P. R. Indonesia et al., “Law of the Republic of Indonesia No. 12 of 1992 concerning: Plant Cultivation System,” vol. 2010, no. 1, pp. 1–5, 1991. Available at : https://www.dpr.go.id/dokjdih/document/uu/628.pdf.

[5] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 779-788, 2016. doi: 10.1109/CVPR.2016.91.

[6] G. Jocher et al., “ultralytics/yolov5: v7.0 - YOLOv5 SOTA Realtime Instance Segmentation.” Nov. 22, 2022. doi: 10.5281/ZENODO.7347926.

[7] J. Redmon and A. Farhadi, “YOLO9000: Better, faster, stronger,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 6517–6525, Nov. 2017, doi: 10.1109/CVPR.2017.690.

[8] J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” Comput. Vis. Pattern Recognit., pp. 1–6, Apr. 2018,. Available: https://arxiv.org/abs/1804.02767v1.

[9] A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” Comput. Vis. Pattern Recognit., pp. 1–17, Apr. 2020, Accessed: May 10, 2023. [Online]. Available: https://arxiv.org/abs/2004.10934v1.

[10] J. L. Miranda, B. D. Gerardo, and B. T. Tanguilig III, “Pest Detection and Extraction Using Image Processing Techniques,” Int. J. Comput. Commun. Eng., vol. 3, no. 3, pp. 189–192, 2014, doi: 10.7763/IJCCE.2014.V3.317.

[11] Z. Bin Husin, A. Y. Bin Md Shakaff, A. H. Bin Abdul Aziz, and R. B. S. Mohamed Farook, “Feasibility study on plant chili disease detection using image processing techniques,” Proc. - 3rd Int. Conf. Intell. Syst. Model. Simulation, ISMS 2012, pp. 291–296, 2012, doi: 10.1109/ISMS.2012.33.

[12] V. Khanaa and K. P. Thooyamani, “An Efficient Weed and Pest Detection System,” Indian J. Sci. Technol., vol. 8, no. 32, pp. 1–7, Nov. 2015, doi: 10.17485/IJST/2015/V8I32/87476.

[13] S. R. Huddar, S. Gowri, K. Keerthana, S. Vasanthi, and S. R. Rupanagudi, “Novel algorithm for segmentation and automatic identification of pests on plants using image processing,” 2012 3rd Int. Conf. Comput. Commun. Netw. Technol. ICCCNT 2012, pp. 1-5, 2012, doi: 10.1109/ICCCNT.2012.6396012.

[14] L. Deng et al., “Application of agricultural insect pest detection and control map based on image processing analysis,” J. Intell. Fuzzy Syst., vol. 38, no. 1, pp. 379–389, Jan. 2020, doi: 10.3233/JIFS-179413.

[15] K. Thenmozhi and U. S. Reddy, “Image processing techniques for insect shape detection in field crops,” Proc. Int. Conf. Inven. Comput. Informatics, ICICI 2017, pp. 699–704, May 2018, doi: 10.1109/ICICI.2017.8365226.

[16] P. Boissard, V. Martin, and S. Moisan, “A cognitive vision approach to early pest detection in greenhouse crops,” Comput. Electron. Agric., vol. 62, no. 2, pp. 81–93, Jul. 2008, doi: 10.1016/J.COMPAG.2007.11.009.

[17] Y. Li, C. Xia, and J. Lee, “Vision-based pest detection and automatic spray of greenhouse plant,” IEEE Int. Symp. Ind. Electron., pp. 920–925, 2009, doi: 10.1109/ISIE.2009.5218251.

[18] A. Ahmed, A. Ibrahim, and S. Hussein, “Detection of palm tree pests using thermal imaging: A review,” Stud. Comput. Intell., vol. 801, pp. 253–270, 2019, doi: 10.1007/978-3-030-02357-7_12.

[19] R. Pratheba, A. Sivasangari, and D. Saraswady, “Performance analysis of pest detection for agricultural field using clustering techniques,” 2014 Int. Conf. Circuits, Power Comput. Technol. ICCPCT 2014, pp. 1426–1431, Mar. 2014, doi: 10.1109/ICCPCT.2014.7054833.

[20] N. Vinushree, B. Hemalatha, and V. K. Kaliappan, “Efficient kernel-based fuzzy C-means clustering for pest detection and classification,” Proc. - 2014 World Congr. Comput. Commun. Technol. WCCCT 2014, pp. 179–181, 2014, doi: 10.1109/WCCCT.2014.61.

[21] P. Nagababu, M. R. Reddy, K. Anila, and M. Srujana, “Early Pest Detection From Crop Using Image Processing and Computational Intelligence,” Interantional J. Sci. Res. Eng. Manag., vol. 06, no. 06, pp. 1–5, 2022, doi: 10.55041/ijsrem14606.

[22] M. Bayat, Mahdi Abbasi, and Ali Yosefi, “Improvement of Pest Detection Using Histogram Adjustment Method and Gabor Wavelet,” J. Asian Sci. Res., vol. 6, no. 2, pp. 24–33, Feb. 2016, doi: 10.18488/JOURNAL.2/2016.6.2/2.2.24.33.

[23] M. A. Ebrahimi, M. H. Khoshtaghaza, S. Minaei, and B. Jamshidi, “Vision-based pest detection based on SVM classification method,” Comput. Electron. Agric., vol. 137, pp. 52–58, May 2017, doi: 10.1016/J.COMPAG.2017.03.016.

[24] P. Ashok, J. Jayachandran, S. Sankara Gomathi, and M. Jayaprakasan, “Pest detection and identification by applying color histogram and contour detectionby Svm model,” Int. J. Eng. Adv. Technol., vol. 8, no. 3 Special Issue, pp. 463–467, 2019. Available at: https://www.ijeat.org/portfolio-item/c10970283s19/.

[25] A. Dey, D. Bhoumik, and K. Dey, “Automatic Detection of Whitefly Pest using Statistical Feature Extraction and Image Classification Methods,” Int. Res. J. Eng. Technol., vol. 03, no. 06, pp. 1–10, 2016, Available at: https://www.irjet.net/archives/V3/i9/IRJET-V3I9171.pdf .

[26] F. Faithpraise, B. Philip, Y. Rupert, O. J, F. Bassey, and C. Chris, “Automatic plant pest detection & recognition using k-means clustering algorithm & correspondence filters,” Int. J. Adv. Biotechnol. Res., vol. 4, no. 2, pp. 1052–1062, 2013. Available at: http://sro.sussex.ac.uk/49042/1/IJABR-V4I2-2013-02.pdf.

[27] M. Türkoğlu and D. Hanbay, “Plant disease and pest detection using deep learning-based features,” Turkish J. Electr. Eng. Comput. Sci., vol. 27, no. 3, pp. 1636–1651, Jan. 2019, doi: 10.3906/elk-1809-181.

[28] V. Malathi and M. P. Gopinath, “Classification of pest detection in paddy crop based on transfer learning approach,” Acta Agriculturae Scandinavica, Section B — Soil & Plant Science, vol. 71, no. 7, pp. 552–559, 2021, doi: 10.1080/09064710.2021.1874045.

[29] A. Fuentes, S. Yoon, S. C. Kim, and D. S. Park, “A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition,” Sensors 2017, vol. 17, no. 9, p. 2022, Sep. 2017, doi: 10.3390/S17092022.

[30] L. Jiao, S. Dong, S. Zhang, C. Xie, and H. Wang, “AF-RCNN: An anchor-free convolutional neural network for multi-categories agricultural pest detection,” Comput. Electron. Agric., vol. 174, p. 105522, Jul. 2020, doi: 10.1016/J.COMPAG.2020.105522.

[31] D. Li et al., “A Recognition Method for Rice Plant Diseases and Pests Video Detection Based on Deep Convolutional Neural Network,” Sensors 2020, vol. 20, no. 3, p. 578, Jan. 2020, doi: 10.3390/S20030578.

[32] W. Li, D. Wang, M. Li, Y. Gao, J. Wu, and X. Yang, “Field detection of tiny pests from sticky trap images using deep learning in agricultural greenhouse,” Comput. Electron. Agric., vol. 183, p. 106048, Apr. 2021, doi: 10.1016/J.COMPAG.2021.106048.

[33] S. Li, X. Zhao, D. Patel, N. Bhatt, and A. Professor, “Improved accuracy of pest detection using augmentation approach with Faster R-CNN,” IOP Conf. Ser. Mater. Sci. Eng., vol. 1042, no. 1, p. 012020, Jan. 2021, doi: 10.1088/1757-899X/1042/1/012020.

[34] K. Zhang, Q. Wu, and Y. Chen, “Detecting soybean leaf disease from synthetic image using multi-feature fusion faster R-CNN,” Comput. Electron. Agric., vol. 183, p. 106064, Apr. 2021, doi: 10.1016/J.COMPAG.2021.106064.

[35] L. Jiao, C. Xie, P. Chen, J. Du, R. Li, and J. Zhang, “Adaptive feature fusion pyramid network for multi-classes agricultural pest detection,” Comput. Electron. Agric., vol. 195, p. 106827, Apr. 2022, doi: 10.1016/J.COMPAG.2022.106827.

[36] T. L. Lin, H. Y. Chang, and K. H. Chen, “Pest and Disease Identification in the Growth of Sweet Peppers using Faster R-CNN,” 2019 IEEE Int. Conf. Consum. Electron. - Taiwan, ICCE-TW 2019, pp. 1-2 May 2019, doi: 10.1109/ICCE-TW46550.2019.8991893.

[37] J. Liu and X. Wang, “Early recognition of tomato gray leaf spot disease based on MobileNetv2-YOLOv3 model,” Plant Methods, vol. 16, no. 1, pp. 1–16, Jun. 2020, doi: 10.1186/S13007-020-00624-2.

[38] P. V. Bhatt, S. Sarangi, and S. Pappula, “Detection of diseases and pests on images captured in uncontrolled conditions from tea plantations,” Proceedings Volume 11008, Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping IV, vol. 11008, pp. 73–82, May 2019, doi: 10.1117/12.2518868.

[39] J. W. Chen, W. J. Lin, H. J. Cheng, C. L. Hung, C. Y. Lin, and S. P. Chen, “A Smartphone-Based Application for Scale Pest Detection Using Multiple-Object Detection Methods,” Electron. 2021, vol. 10, no. 4, p. 372, Feb. 2021, doi: 10.3390/ELECTRONICS10040372.

[40] H. Kuzuhara, H. Takimoto, Y. Sato, and A. Kanagawa, “Insect Pest Detection and Identification Method Based on Deep Learning for Realizing a Pest Control System,” 2020 59th Annu. Conf. Soc. Instrum. Control Eng. Japan, SICE 2020, pp. 709–714, Sep. 2020, doi: 10.23919/SICE48898.2020.9240458.

[41] B. Liang, S. Wu, K. Xu, and J. Hao, “Butterfly detection and classification based on integrated YOLO algorithm,” Adv. Intell. Syst. Comput., vol. 1107 AISC, pp. 500–512, 2020, doi: 10.1007/978-981-15-3308-2_55.

[42] K. R. B. Legaspi, N. W. S. Sison, and J. F. Villaverde, “Detection and Classification of Whiteflies and Fruit Flies Using YOLO,” 2021 13th Int. Conf. Comput. Autom. Eng. ICCAE 2021, pp. 1–4, Mar. 2021, doi: 10.1109/ICCAE51876.2021.9426129.

[43] N. Mamdouh and A. Khattab, “YOLO-Based Deep Learning Framework for Olive Fruit Fly Detection and Counting,” IEEE Access, vol. 9, pp. 84252–84262, 2021, doi: 10.1109/ACCESS.2021.3088075.

[44] D. J. A. Rustia et al., “Automatic greenhouse insect pest detection and recognition based on a cascaded deep learning classification method,” J. Appl. Entomol., vol. 145, no. 3, pp. 206–222, Apr. 2021, doi: 10.1111/JEN.12834.

[45] Z. Tang, Z. Chen, F. Qi, L. Zhang, and S. Chen, “Pest-YOLO: Deep Image Mining and Multi-Feature Fusion for Real-Time Agriculture Pest Detection,” Proc. - IEEE Int. Conf. Data Mining, ICDM, vol. 2021-December, pp. 1348–1353, 2021, doi: 10.1109/ICDM51629.2021.00169.

[46] S. Verma, S. Tripathi, A. Singh, M. Ojha, and R. R. Saxena, “Insect Detection and Identification using YOLO Algorithms on Soybean Crop,” IEEE Reg. 10 Annu. Int. Conf. Proceedings/TENCON, vol. 2021-December, pp. 272–277, 2021, doi: 10.1109/TENCON54134.2021.9707354.

[47] M. Zha, W. Qian, W. Yi, and J. Hua, “A Lightweight YOLOv4-Based Forestry Pest Detection Method Using Coordinate Attention and Feature Fusion,” Entropy 2021, vol. 23, no. 12, p. 1587, Nov. 2021, doi: 10.3390/E23121587.

[48] D. Li, F. Ahmed, N. Wu, and A. I. Sethi, “YOLO-JD: A Deep Learning Network for Jute Diseases and Pests Detection from Images,” Plants 2022, vol. 11, no. 7, p. 937, Mar. 2022, doi: 10.3390/PLANTS11070937.

[49] J. Liu and X. Wang, “Tomato Diseases and Pests Detection Based on Improved Yolo V3 Convolutional Neural Network,” Front. Plant Sci., vol. 11, p. 521544, Jun. 2020, doi: 10.3389/FPLS.2020.00898.

[50] E. Önler, “Real Time Pest Detection Using YOLOv5,” Int. J. Agric. Nat. Sci., vol. 14, no. 3, pp. 232–246, Dec. 2021, Available at: https://www.ijans.org/index.php/ijans/article/view/550.

[51] I. Ahmad et al., “Deep Learning Based Detector YOLOv5 for Identifying Insect Pests,” Appl. Sci. 2022, vol. 12, no. 19, p. 10167, Oct. 2022, doi: 10.3390/APP121910167.

[52] M. G. Selvaraj et al., “AI-powered banana diseases and pest detection,” Plant Methods, vol. 15, no. 1, pp. 1–11, Aug. 2019, doi: 10.1186/S13007-019-0475-Z.

[53] S. A. Burhan, D. S. Minhas, D. A. Tariq, and M. Nabeel Hassan, “Comparative Study of Deep Learning Algorithms for Disease and Pest Detection in Rice Crops,” Proc. 12th Int. Conf. Electron. Comput. Artif. Intell. ECAI 2020, pp. 1-5, Jun. 2020, doi: 10.1109/ECAI50035.2020.9223239.

[54] T. T. Nguyen, Q. T. Vien, and H. Sellahewa, “An Efficient Pest Classification In Smart Agriculture Using Transfer Learning,” EAI Endorsed Trans. Ind. Networks Intell. Syst., vol. 8, no. 26, pp. 1–8, Jan. 2021, doi: 10.4108/EAI.26-1-2021.168227.

[55] L. Liu et al., “PestNet: An End-to-End Deep Learning Approach for Large-Scale Multi-Class Pest Detection and Classification,” IEEE Access, vol. 7, pp. 45301–45312, 2019, doi: 10.1109/ACCESS.2019.2909522.

[56] P. P. J. Roosjen, B. Kellenberger, L. Kooistra, D. R. Green, and J. Fahrentrapp, “Deep Learning For Automated Detection Of Drosophila Suzukii: Potential For UAV-Based Monitoring,” Pest Manag. Sci., vol. 76, no. 9, pp. 2994–3002, Sep. 2020, doi: 10.1002/PS.5845.

[57] B. Kellenberger, D. Marcos, and D. Tuia, “Detecting mammals in UAV images: Best practices to address a substantially imbalanced dataset with deep learning,” Remote Sens. Environ., vol. 216, pp. 139–153, Oct. 2018, doi: 10.1016/J.RSE.2018.06.028.

[58] Z. Lyu, H. Jin, T. Zhen, F. Sun, and H. Xu, “Small Object Recognition Algorithm of Grain Pests Based on SSD Feature Fusion,” IEEE Access, vol. 9, pp. 43202–43213, 2021, doi: 10.1109/ACCESS.2021.3066510.

[59] L. Liu et al., “Deep Learning Based Automatic Multiclass Wild Pest Monitoring Approach Using Hybrid Global and Local Activated Features,” IEEE Trans. Ind. Informatics, vol. 17, no. 11, pp. 7589–7598, Nov. 2021, doi: 10.1109/TII.2020.2995208.

[60] R. Wang, L. Jiao, C. Xie, P. Chen, J. Du, and R. Li, “S-RPN: Sampling-balanced region proposal network for small crop pest detection,” Comput. Electron. Agric., vol. 187, p. 106290, Aug. 2021, doi: 10.1016/J.COMPAG.2021.106290.

[61] M. Turkoglu, B. Yanikoğlu, and D. Hanbay, “PlantDiseaseNet: convolutional neural network ensemble for plant disease and pest detection,” Signal, Image Video Process., vol. 16, no. 2, pp. 301–309, Mar. 2022, doi: 10.1007/S11760-021-01909-2.




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

___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571  (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
   andri.pranolo.id@ieee.org (publication issues)

View IJAIN Stats

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0