Automatic Detection and Counting of Tuta Absoluta Insect in Trap Images

Gabriel Santos de Souza; Camila Corrêa Vargas; Jean Carlo Hamerski

doi:10.22456/2175-2745.143522

Authors

Gabriel Souza Federal Institute of Education, Science and Technology of Rio Grande do Sul (IFRS)
Camila Vargas Business Incubator of the Biotechnology Center (IECBiot) - UFRGS
Jean Hamerski Federal Institute of Education, Science and Technology of Rio Grande do Sul (IFRS) https://orcid.org/0000-0003-2544-2334

DOI:

https://doi.org/10.22456/2175-2745.143522

Keywords:

Biological Pest Control, Precision Agriculture, Computer Vision, Deep Learning, Tuta absoluta

Abstract

The integration of artificial intelligence (AI) into agriculture offers solutions to challenges such as pest control. AI can improve productivity and sustainability through precision agriculture. This paper presents an automatic system for identifying and counting Tuta absoluta pests in trap images, integrated into a monitoring platform. The platform uses a biological defensive system for sustained pest control. The solution employs ImageAI deep learning algorithms to detect and classify pests, using YOLOv3 and TinyYOLOv3 models. We provide assessments of the performance and resource consumption of the evaluated models. YOLOv3 achieved a detection precision of 95.28% in images with 10-50 insects, decreasing to 87.51% for around 100 insects. Despite YOLOv3 demonstrating higher precision in the detection of the number of insects, the Tiny YOLOv3 model was shown to be 4.5 times faster in the training process and occupies almost 8 times less storage space.

Downloads

Download data is not yet available.

References

ABIA. Notícias - ABIA - Associação Brasileira da Indústria de Alimentos. 2024. ⟨https://www.abia.org.br/noticias/industria-de-alimentos-do-brasil-gera-70-mil-vagas-de-emprego-em-2023⟩. (Accessed on 09/05/2024).

BANDNEWS. Mercado de alimentos saudáveis deve faturar R$ 127 bilhões. 2024. ⟨https://bandnewsfmcuritiba.com/mercado-de-alimentos-saudaveis-deve-faturar-r-127-bilhoes/⟩. (Accessed on 09/05/2024).

INVESTING. Defensivos Agrícolas e Bioinsumos — Investing.com. 2022. ⟨https://br.investing.com/analysis/defensivos-agricolas-e-bioinsumos-200449414⟩. (Accessed on 09/05/2024).

ALETDINOVA, A. A. Popular mobile applications for crop production. IOP Conference Series: Earth and Environmental Science, IOP Publishing, v. 666, n. 3, p. 032036, mar 2021. Disponível em: ⟨https://dx.doi.org/10.1088/1755-1315/666/3/032036⟩.

CHRISTAKAKIS, P. et al. Smartphone-based citizen science tool for plant disease and insect pest detection using artificial intelligence. Technologies, v. 12, n. 7, 2024. ISSN 2227-7080.

NASIM, S. et al. Artificial intelligence techniques for the pest detection in banana field: A systematic review. Pakistan Journal of Biotechnology, v. 20, n. 02, p. 209–223, Jun. 2023.

RAHMAN, S. M.; RAVI, G. Role of artificial intelligence in pest management. Current Topics in Agricultural Sciences Vol, v. 7, p. 64–81, 2022.

BÜTÜNER, A. K. et al. Enhancing pest detection: Assessing Tuta absoluta (Lepidoptera: Gelechiidae) damage intensity in field images through advanced machine learning. Journal of Agricultural Sciences, Ankara University, v. 30, n. 1, p. 99–107, 2024.

GEORGANTOPOULOS, P. et al. A multispectral dataset for the detection of Tuta absoluta and Leveillula taurica in tomato plants. Smart Agricultural Technology, v. 4, p. 100146, 2023. ISSN 2772-3755. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S2772375522001101⟩.

ULLAH, N. et al. An efficient approach for crops pests recognition and classification based on novel DeepPestNet deep learning model. IEEE Access, IEEE, v. 10, p. 73019–73032, 2022.

VEIGA, A. C. P. Compatibilidade entre produtos químicos e biológicos à base de Bacillus thuringiensis Berliner no controle de Tuta absoluta (Meyrick) (Lepidoptera: Gelechiidae). Tese (Doutorado), 2014.