Automatic Counting and Classification of Mosquito Eggs in Field Traps

TL;DR

The paper tackles the labor-intensive task of monitoring SIT programs targeting Aedes albopictus by automating field ovitrap analysis. It introduces a hardware-assisted imaging pipeline that captures 165 overlapping microscope images per trap and a deep learning-based segmentation/classification framework using Mask R-CNN variants to identify individual eggs and label them as hatched or unhatched, while reconstructing complete ovitraps from partial views to avoid duplications. The approach enables simultaneous analysis of multiple traps, improving counting accuracy and scalability for large-field studies. This work supports more efficient SIT monitoring and could significantly reduce manual labor in vector-control programs, with practical deployment in the Valencian SIT program.

Abstract

Insect pest control poses a global challenge, affecting public health, food safety, and the environment. Diseases transmitted by mosquitoes are expanding beyond tropical regions due to climate change. Agricultural pests further exacerbate economic losses by damaging crops. The Sterile Insect Technique (SIT) emerges as an eco-friendly alternative to chemical pesticides, involving the sterilization and release of male insects to curb population growth. This work focuses on the automation of the analysis of field ovitraps used to follow-up a SIT program for the Aedes albopictus mosquito in the Valencian Community, Spain, funded by the Conselleria de Agricultura, Agua, Ganaderia y Pesca. Previous research has leveraged deep learning algorithms to automate egg counting in ovitraps, yet faced challenges such as manual handling and limited analysis capacity. Innovations in our study include classifying eggs as hatched or unhatched and reconstructing ovitraps from partial images, mitigating issues of duplicity and cut eggs. Also, our device can analyze multiple ovitraps simultaneously without the need of manual replacement. This approach significantly enhances the accuracy of egg counting and classification, providing a valuable tool for large-scale field studies. This document describes part of the work of the project Application of Industry 4.0 techniques to the production of tiger mosquitoes for the Sterile Insect Technique (MoTIA2,IMDEEA/2022/70), financed by the Valencian Institute for Business Competitiveness (IVACE) and the FEDER funds. The participation of J.Naranjo-Alcazar, J.Grau-Haro and P.Zuccarello has been possible thanks to funding from IVACE and FEDER funds. The participation of D.Almenar has been financed by the Conselleria de Agricultura, Agua, Ganaderia y Pesca of the Generalitat Valenciana and the Subdireccion de Innovacion y Desarrollo de Servicios (TRAGSA group).

Figures (3)

• Figure 1: Infographic describing the case of the SIT of the Aedes albopictus mosquito studied in this paper. The left rectangle shows schematically the process inside the biofactory, while the right rectangle shows what is expected to happen after the release of the sterile males into the environment.
• Figure 2: (a) A zenithal photo of the experimental setup is shown. In the lower-left corner, the engines in charge of microscope displacement can be appreciated. In the center of the image, the microscope can be seen above the trap. The whole setup is on a 30 $\times$ 30 cm wooden board. (b) Complete setup with the engine connected to the PC to send the movement and image acquisition commands.
• Figure 3: (a) Original image taken by the microscope (b) Prediction Mask-RCNN model