Visual Identification System for Aedes Detection using Drones
Resumo
The proliferation of diseases transmitted by the Aedes aegypti mosquito, such as dengue, poses a persistent challenge to public health systems worldwide. Traditional surveillance methods for identifying breeding sites are often laborintensive and limited in scale. This paper introduces VISADE (Visual Identification System for Aedes Detection), a system designed to automate this process through the use of Unmanned Aerial Vehicles (UAVs) and deep learning. By capturing and analyzing aerial imagery, VISADE employs a state-of-the-art object detection model, YOLOv11m, to identify and georeference potential breeding sites like discarded tires, buckets, and water tanks. A key aspect of our methodology is the use of high-resolution images (1200x1200 pixels) to enhance the detection of small objects, a significant challenge in aerial surveys. Our model, trained on a custom dataset collected in urban areas of Minas Gerais, Brazil, achieved a mean Average Precision (mAP@0.5) of 0.934, demonstrating high efficacy in identifying potential breeding sites. VISADE aims to provide public health authorities with an efficient, scalable, and low-cost tool, generating risk maps to direct vector control actions more effectively.
Referências
C. Laranjeira, D. Andrade, and J. A. dos Santos, “YOLOv7 for Mosquito Breeding Grounds Detection and Tracking,” in arXiv preprint arXiv:2310.10423, Oct 2023.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
W. Liu, W. Gu, F. Yang, S. Liu, H. Chen, and J. Liu, “RLRD-YOLO: Research on Lightweight Real-Time Detection Algorithm for Small Unmanned Aerial Vehicle Objects Based on Improved YOLOv8,” Sensors, vol. 24, no. 7, p. 2199, 2024.
Y. Gao, Z. Chen, J. Li, T. Wu, W. Xu, L. Wang, Y. Liu, and D. Chen, “Detection of Potential Breeding Sites Based on UAV Remote Sensing Imagery and MultiDCCSP-YOLO Network,” Remote Sensing, vol. 16, no. 7, p. 1198, 2024.
M. S. H. Apu, S. Ahmed, M. T. Ahmed, D. D. Gnakamene, M. Bhatt, S. Bhatia, S. Kadry, R. Kumar, and G. Meena, “Smart System for Real Time Monitoring and Diagnosis of Dengue Surfaces in Bangladesh Using CBAM-Enhanced YOLOv9,” Drones, vol. 8, no. 5, p. 194, 2024.
V. Perumal, R. Sasana, P. Rakshitha, and J. F. F. Doss, “Mosquito Breeding Grounds Detection Using Deep Learning Techniques,” in 2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI), 2023, pp. 1–6.
P. Skalski, “Make Sense,” [link], 2019.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
G. Jocher, A. Chaurasia, J. Qiu, and U. contributors, “Ultralytics YOLO,” 2023. [Online]. Available: [link]
T. Jiang and Y. Zhong, “ODverse33: Is the New YOLO Version Always Better? A Multi Domain benchmark from YOLO v5 to v11,” arXiv preprint arXiv:2502.14314, Feb 2025.
Z. Tong, Y. Chen, Z. Xu, and L. Lu, “Wise-IoU v3: A More Powerful Bounding Box Loss Function,” arXiv preprint arXiv:2301.10055v3, Sep 2023.
I. Maza and A. Ollero, “Multiple uav cooperative searching operation using polygon area decomposition and efficient coverage algorithms,” in Distributed Autonomous Robotic Systems 6. Springer, 2004, pp. 221–230.
F. Balampanis, K. Patsianis, E. Kosmatopoulos, and S. Chatzichristofis, “Coastal areas division and coverage with multiple uavs for remote sensing,” Sensors, vol. 17, no. 4, p. 808, 2017.
C. Gao et al., “A hierarchical multi-uav cooperative framework for infrastructure inspection and reconstruction,” Control Theory and Technology, vol. 22, pp. 394–405, 2024.
M. Luna et al., “Fast multi-uav path planning for optimal area coverage in aerial sensing applications,” Sensors, vol. 22, no. 6, p. 2297, 2022.
Y. Yu and S. Lee, “Efficient multi-uav path planning for collaborative area search operations,” Applied Sciences, vol. 13, no. 15, p. 8728, 2023.
H. Zeng et al., “Multi-uav cooperative coverage search for various regions based on differential evolution algorithm,” Biomimetics, vol. 9, no. 7, p. 384, 2024.
F. Causa et al., “Multi-drone cooperation for improved lidar-based mapping,” Sensors, vol. 24, no. 10, p. 3014, 2024.
M. Rahman et al., “A survey on multi-uav path planning: Classification, algorithms, open research problems, and future directions,” Drones, vol. 9, no. 4, p. 263, 2025.
