A comparative study between deep learning approaches for aphid classification
Keywords:
aphids, AphidCV, classification, comparative study, object detection, YOLOv8Abstract
This study presents a performance comparison between two convolutional neural networks in the task of detecting aphids in digital images: AphidCV, customized for counting, classifying, and measuring aphids, and YOLOv8, state-of-the-art in real-time object detection. Our work considered 48,000 images for training for six different insect species (8,000 images divided into four classes), in addition to data augmentation techniques. For comparative purposes, we considered evaluation metrics available to both architectures (Accuracy, Precision, Recall, and F1-Score) and additional metrics (ROC Curve and PR AUC for AphidCV; mAP@50 and mAP@50-95 for YOLOv8). The results revealed an average F1-Score=0.891 for the AphidCV architecture, version 3.0, and an average F1-Score=0.882 for the YOLOv8, medium version, demonstrating the effectiveness of both architectures for training aphid detection models. Overall, AphidCV performed slightly better for the majority of metrics and species in the study, serving its design purpose very well. YOLOv8 proved to be faster to converge the models, with the potential to apply in research considering many aphid species.
Downloads
References
D. Lau, T. B. Mar, C. D. R. dos Santos, E. Engel, P. R. d. V. da Silva et al., "Advances in understanding the biology and epidemiology of barley yellow dwarf virus (bydv)," in Achieving durable disease resistance in cereals. Burleigh Dodds Science Publishing, 2021. [Online]. Available: https://doi.org/10.1201/9781003180715
P. Batz, T. Will, S. Thiel, T. M. Ziesche, and C. Joachim, "From identification to forecasting: the potential of image recognition and artificial intelligence for aphid pest monitoring," Frontiers in Plant Science, vol. 14, p. 1150748, 2023. [Online]. Available: https://doi.org/10.3389/fpls.2023.1150748
T. F. Döring, "How aphids find their host plants, and how they don’t," Annals of Applied Biology, vol. 165, no. 1, pp. 3–26, 2014. [Online]. Available: https://doi.org/10.1111/aab.12142
T. D. C. Júnior, R. Rieder, J. R. Di Domênico, and D. Lau, "InsectCV: A system for insect detection in the lab from trap images," Ecological Informatics, vol. 67, p. 101516, 2022. [Online]. Available: https://doi.org/10.1016/j.ecoinf.2021.101516
E. A. Lins, J. P. M. Rodriguez, S. I. Scoloski, J. Pivato, M. B. Lima, J. M. C. Fernandes, P. R. V. da Silva Pereira, D. Lau, and R. Rieder, "A method for counting and classifying aphids using computer vision," Computers and Electronics in Agriculture, vol. 169, p. 105200, 2020. [Online]. Available: https://doi.org/10.1016/j.compag.2019.105200
J. P. Rodriguez and R. Rieder, "AphidCV 2.0: uma nova abordagem de classificação, contagem e mensuração de afídeos," in Anais Estendidos da XXXIII Conference on Graphics, Patterns and Images. Porto Alegre, RS, Brasil: SBC, 2020, pp. 159–162. [Online]. Available: https://doi.org/10.5753/sibgrapi.est.2020.13001
IFSUL Passo Fundo. (2016) Trap System. Accessed on Ago. 12, 2024. [Online]. Available: http://gpca.passofundo.ifsul.edu.br/traps/
N. Kirinus, B. Taca, M. Iora, R. Rieder, T. C. Junior, and D. Lau, "AphidCV mobile: ferramenta para classificação e contagem de afídeos em dispositivos móveis," in Anais Estendidos da XXXVI Conference on Graphics, Patterns and Images. Porto Alegre, RS, Brasil: SBC, 2023, pp. 144–147. [Online]. Available: https://doi.org/10.5753/sibgrapi.est.2023.27468
G. Jocher. (2020) Ultralytics YOLOv5. https://github.com/ultralytics/yolov5. [Online]. Available: https://doi.org/10.5281/zenodo.3908559
N. W. Kirinus, E. G. Pessolano, D. Lau, T. De Cesaro Jr., and R. Rieder. (2024) AphidCV 3.0: Abordagem web integrada a uma plataforma de monitoramento de insetos. Accessed on Ago. 12, 2024. [Online]. Available: https://periodicos.ifsul.edu.br/index.php/ctipf/ article/view/3382/2269
G. Jocher, A. Chaurasia, and J. Qiu. (2023, Jan.) Ultralytics YOLO. Accessed on Ago. 12, 2024. [Online]. Available: https://github.com/ultralytics/ultralytics
S. Verma, S. Tripathi, A. Singh, M. Ojha, and R. R. Saxena, "Insect detection and identification using YOLO algorithms on soybean crop," in TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON), 2021, pp. 272–277. [Online]. Available: https://doi.org/10.1109/TENCON54134.2021.9707354
J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement," arXiv, no. 1804.02767, 2018. [Online]. Available: https://doi.org/10.48550/arXiv.1804.02767
A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "YOLOv4: Optimal speed and accuracy of object detection," arXiv, no. 2004.10934, 2020. [Online]. Available: https://doi.org/10.48550/arXiv.2004.10934
Y. Tian, S. Wang, E. Li, G. Yang, Z. Liang, and M. Tan, "MD-YOLO: Multi-scale dense YOLO for small target pest detection," Computers and Electronics in Agriculture, vol. 213, p. 108233, 2023. [Online]. Available: https://doi.org/10.1016/j.compag.2023.108233
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," arXiv, no. 2207.02696, 2022. [Online]. Available: https://doi.org/10.48550/arXiv.2207.02696
H.-S. Chang, C.-Y. Wang, R. R. Wang, G. Chou, and H.-Y. M. Liao, "YOLOR-based multi-task learning," arXiv, no. 2309.16921, 2023. [Online]. Available: https://doi.org/10.48550/arXiv.2309.16921
C.-J. Zhang, T. Liu, J. Wang, D. Zhai, Y. Zhang, Y. Gao, H.-Z. Wu, J. Yu, and M. Chen, "Evaluation of the YOLO models for discrimination of the alfalfa pollinating bee species," Journal of Asia-Pacific Entomology, vol. 27, no. 1, p. 102195, 2024. [Online]. Available: https://doi.org/10.1016/j.aspen.2023.102195
R. de Castro Pereira, E. Hirose, O. L. Ferreira de Carvalho, R. M. da Costa, and D. L. Borges, "Detection and classification of whiteflies and development stages on soybean leaves images using an improved deep learning strategy," Computers and Electronics in Agriculture, vol. 199, p. 107132, 2022. [Online]. Available: https://doi.org/10.1016/j.compag.2022.107132
J. D. Domênico, D. Lau, D. Ribeiro, R. Rieder, and T. C. Júnior, "Um estudo comparativo de redes convolucionais profundas para detecção de insetos em imagens," in Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images. Porto Alegre, RS, Brasil: SBC, 2021, pp. 183–188. [Online]. Available: https://doi.org/10.5753/sibgrapi.est.2021.20036
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 2818–2826. [Online]. Available: https://doi.org/10.1109/CVPR.2016.308
A. Buslaev, V. I. Iglovikov, E. Khvedchenya, A. Parinov, M. Druzhinin, and A. A. Kalinin, "Albumentations: Fast and flexible image augmentations," Information, vol. 11, no. 2, 2020. [Online]. Available: https://doi.org/10.3390/info11020125
OpenCV Team. (2024) Opencv - open computer vision library. Accessed on Ago. 12, 2024. [Online]. Available: https://opencv.org
P. Gavrikov. (2020) Visualkeras. Accessed on Ago. 12, 2024. [Online]. Available: https://github.com/paulgavrikov/visualkeras
J. Terven, D.-M. Córdova-Esparza, and J.-A. Romero-González, "A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS," Machine Learning and Knowledge Extraction, vol. 5, no. 4, pp. 1680–1716, 2023. [Online]. Available: https://doi.org/10.3390/make5040083
M. Sohan, T. Sai Ram, and C. V. Rami Reddy, "A review on YOLOv8 and its advancements," in Data Intelligence and Cognitive Informatics, I. J. Jacob, S. Piramuthu, and P. Falkowski-Gilski, Eds. Singapore: Springer Nature Singapore, 2024, pp. 529–545. [Online]. Available: https://doi.org/10.1007/978-981-99-7962-2_39
D. Reis, J. Kupec, J. Hong, and A. Daoudi, "Real-time flying object detection with YOLOv8," arXiv, no. 2305.09972, 2024. [Online]. Available: https://doi.org/10.48550/arXiv.2305.09972
N. Sharma, S. Baral, M. P. Paing, and R. Chawuthai, "Parking time violation tracking using yolov8 and tracking algorithms," Sensors, vol. 23, no. 13, p. 5843, 2023. [Online]. Available: https://doi.org/10.3390/s23135843
F. M. Shiri, T. Perumal, N. Mustapha, and R. Mohamed, "A comprehensive overview and comparative analysis on deep learning models: Cnn, rnn, lstm, gru," arXiv preprint arXiv:2305.17473, 2023. [Online]. Available: https://doi.org/10.48550/arXiv.2305.17473
M. Miric, N. Jia, and K. G. Huang, "Using supervised machine learning for large-scale classification in management research: The case for identifying artificial intelligence patents," Strategic Management Journal, vol. 44, no. 2, pp. 491–519, 2023. [Online]. Available: https://doi.org/10.1002/smj.3441
S. A. Khan and Z. Ali Rana, "Evaluating performance of software defect prediction models using area under precision-recall curve (auc-pr)," in 2019 2nd International Conference on Advancements in Computational Sciences (ICACS), 2019, pp. 1–6. [Online]. Available: https://doi.org/10.23919/ICACS.2019.8689135
R. C. Domingues, G. V. Fruet, H. F. Abud, and D. G. Gomes, "Imagens de raios-x e YOLOv8 para avaliação automatizada, precisa e não destrutiva da qualidade de sementes braquiária (urochloa brizantha)," in Anais do XIV Congresso Brasileiro de Agroinformática. SBC, 2023, pp. 167–174. [Online]. Available: https://doi.org/10.5753/sbiagro.2023.26555
P. Vasanthi and L. Mohan, "Efficient YOLOv8 algorithm for extreme small-scale object detection," Digital Signal Processing, vol. 154, p. 104682, 2024. [Online]. Available: https://doi.org/10.1016/j.dsp.2024.104682
E. Casas, L. Ramos, E. Bendek, and F. Rivas-Echeverria, "YOLOv5 vs. YOLOv8: Performance benchmarking in wildfire and smoke detection scenarios," Journal of Image and Graphics, vol. 12, no. 2, 2024. [Online]. Available: https://doi.org/10.18178/joig.12.2.127-136
C.-Y. Wang, H.-Y. M. Liao, and I.-H. Yeh, "Designing network design strategies through gradient path analysis," arXiv, no. 2211.04800, 2022. [Online]. Available: https://doi.org/10.48550/arXiv.2211.04800
Embrapa Trigo. (2024) BIS - Brazilian Insect Survey. Accessed on Nov. 12, 2024. [Online]. Available: https://www.bis.cnptia.embrapa.br
