Aedes aegypti Egg Counting with Neural Networks for Object Detection

Micheli Nayara  de Oliveira Vicente; João Vitor de Andrade Porto; Gabriel Toshio Hirokawa Higa; Higor Henrique Picoli Nucci; Asser Botelho Santana; Karla Rejane de Andrade Porto; Antonia Railda Roel Roel; Hemerson Pistori

doi:10.22456/2175-2745.143494

Authors

Micheli Nayara de Oliveira Vicente Dom Bosco Catholic University (UCDB)
João Vitor de Andrade Porto Dom Bosco Catholic University (UCDB) https://orcid.org/0000-0002-4766-3675
Gabriel Toshio Hirokawa Higa Dom Bosco Catholic University (UCDB) https://orcid.org/0009-0006-6771-0076
Higor Henrique Picoli Nucci Federal University of Mato Grosso do Sul (UFMS)
Asser Botelho Santana Dom Bosco Catholic University (UCDB)
Karla Rejane de Andrade Porto Kerow Soluções de Precisão https://orcid.org/0000-0002-6309-8696
Antonia Railda Roel Dom Bosco Catholic University (UCDB) https://orcid.org/0000-0002-6403-0554
Hemerson Pistori Dom Bosco Catholic University (UCDB)

DOI:

https://doi.org/10.22456/2175-2745.143494

Keywords:

Deep Learning, Ovitrap, Disease Vector Control, Counting

Abstract

Aedes aegypti is still one of the main concerns when it comes to disease vectors. Among the many ways to deal with it, there are important protocols that make use of egg numbers in ovitraps to calculate indices, such as LIRAa and Breteau Index, which can provide information on predictable outbursts and epidemics. Also, there are many research lines that require egg numbers, specially when mass production of mosquitoes is needed. Egg counting is a laborious and error-prone task that can be automated via computer vision-based techniques, specially deep learning-based counting with object detection. In this work, we propose a new dataset comprising field and laboratory eggs, along with test results of three neural networks applied to the task: Faster R-CNN, Side-Aware Boundary Localization and FoveaBox. With FoveaBox, we achieve a median mean absolute error of 6.854. Finally, we also discuss the main difficulties and possibilities for future research.

Downloads

Download data is not yet available.

Author Biographies

Micheli Nayara de Oliveira Vicente, Dom Bosco Catholic University (UCDB)

Conceptualization, Data Curation, Writing

João Vitor de Andrade Porto, Dom Bosco Catholic University (UCDB)

Data ˜Curation, Writing

Gabriel Toshio Hirokawa Higa, Dom Bosco Catholic University (UCDB)

Conceptualization, Methodology, Formal Analysis, Writing, Visualization

Higor Henrique Picoli Nucci, Federal University of Mato Grosso do Sul (UFMS)

Investigation, Writing

Asser Botelho Santana, Dom Bosco Catholic University (UCDB)

Data Curation, Resources

Antonia Railda Roel, Dom Bosco Catholic University (UCDB)

Data Curation, Resources, Supervision;

Hemerson Pistori, Dom Bosco Catholic University (UCDB)

Conceptualization, Software, Methodology, Supervision, Project Administration.

References

JUNIOR, J. B. S. et al. Epidemiology and costs of dengue in Brazil: a systematic literature review. INTERNATIONAL JOURNAL OF INFECTIOUS DISEASES, v. 122, p. 521–528, SEP 2022. ISSN 1201-9712.

GARCIA, P. S. C. et al. Acquisition of digital images and identification of Aedes aegypti mosquito eggs using classification and deep learning. In: . [S.l.]: Institute of Electrical and Electronics Engineers Inc., 2019. p. 47–53. ISBN 9781728152271.

SANCHEZ-GENDRIZ, I. et al. Data-driven computational intelligence applied to dengue outbreak forecasting: a case study at the scale of the city of Natal, RN-Brazil. Scientific Reports, v. 12, n. 1, 2022. Cited by: 4.

BAKRAN-LEBL, K. et al. First nationwide monitoring program for the detection of potentially invasive mosquito species in Austria. INSECTS, v. 13, n. 3, MAR 2022.

BRISCO, K. K. et al. Field evaluation of In2Care mosquito traps to control Aedes aegypti and Aedes albopictus (Diptera: Culicidae) in Hawai’i Island. JOURNAL OF MEDICAL ENTOMOLOGY, 2023. ISSN 0022-2585.

BRUN, A. L. et al. Uma revisão das técnicas computacionais para contagem de ovos de Aedes aegypti em imagens de ovitrampas. Revista Brasileira de Computação Aplicada, v. 12, n. 3, p. 1–15, 2020.

JUNIOR, C. J. de S. et al. A solution for counting Aedes aegypti and Aedes albopictus eggs in paddles from ovitraps using deep learning. IEEE Latin America Transactions, IEEE, v. 17, n. 12, p. 1987–1994, 2019.

GUMIRAN, C. R. et al. Aedes aegypti egg morphological property and attribute determination based on computer vision. In: . [S.l.: s.n.], 2022. p. 581–585. Cited by: 1.

ABAD-SALINAS, J. E. et al. Computer vision-based ovitrap for dengue control. Communications in Computer and Information Science, v. 1658 CCIS, p. 123–135, 2022. Cited by: 0.

JAVED, N. et al. EggCountAI: A Convolutional Neural Network Based Software for Counting of Aedes Aegypti Mosquito Eggs. [S.l.]: Research Square, 2023.

IYYAPPAN, V. et al. Oviposition responses of gravid Aedes aegypti Linn. mosquitoes (Diptera: Culicidae) to natural organic infusions under laboratory condition. JOURNAL OF ASIA-PACIFIC ENTOMOLOGY, v. 25, n. 1, MAR 2022. ISSN 1226-8615.

KHAN, A. et al. Assessment of various colors combined with insecticides in devising ovitraps as attracting and killing tools for mosquitoes. INSECTS, v. 14, n. 1, JAN 2023.

RICCI, A. P.; FREITAS, G. F. M. D.; NOGUEIRA, M. L. Estudo da viabilidade do ciclo de vida do Aedes (Stegomyia) aegypti (Linnaeus, 1762) (Diptera, Culicidae) em condições otimizadas. Anais do VIII Simpósio em Ciência e Tecnologia Ambiental e IV Encontro Multidisciplinar em Ciências Ambientais da Fronteira Sul, Universidade Federal da Fronteira Sul, Erechim, RS., 2021.

REN, S. et al. Faster R-CNN: towards real-time object detection with region proposal networks. CoRR, abs/1506.01497, 2015.

GIRSHICK, R. B. et al. Rich feature hierarchies for accurate object detection and semantic segmentation. CoRR, abs/1311.2524, 2013.

GIRSHICK, R. B. Fast R-CNN. CoRR, abs/1504.08083, 2015.

WANG, J. et al. Side-aware boundary localization for more precise object detection. CoRR, abs/1912.04260, 2019.

KONG, T. et al. FoveaBox: Beyond anchor-based object detection. IEEE Transactions on Image Processing, IEEE, v. 29, p. 7389–7398, 2020.

TERVEN, J.; CÓRDOVA-ESPARZA, D.-M.; ROMERO-GONZÁLEZ, J.-A. A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, v. 5, n. 4, p. 1680–1716, 2023. ISSN 2504-4990.

CARION, N. et al. End-to-end object detection with transformers. In: SPRINGER. European conference on computer vision. [S.l.], 2020. p. 213–229.

CHENG, Z.-Q. et al. Rethinking spatial invariance of convolutional networks for object counting. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [S.l.: s.n.], 2022. p. 19606–19616.

SONG, Q. et al. Rethinking counting and localization in crowds: A purely point-based framework. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Los Alamitos, CA, USA: IEEE Computer Society, 2021. p. 3345–3354.

TRAN, N. H. et al. Improving local features with relevant spatial information by vision transformer for crowd counting. In: 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, November 21-24, 2022. [S.l.]: BMVA Press, 2022.