MosquitoMiner: A Light Weight Rover for Detecting and Eliminating Mosquito Breeding Sites

TL;DR

The paper tackles the public health challenge of controling mosquito-borne diseases by introducing MosquitoMiner, a light-weight autonomous rover capable of detecting and eliminating mosquito breeding sites along a predefined path. It combines a Raspberry Pi-based processing stack with YOLOv8s for real-time detection, a Pixhawk-based autopilot for navigation, and a spray mechanism for on-site elimination, all coordinated through OpenCV and UDP-based communication with ground controllers. Evaluation on a custom dataset yields a detection performance of mAP@50 = $61.7%$, precision = $84.7%$, recall = $51.6%$, and an elimination effectiveness of $80%$ breeding-site reduction with $75%$ area coverage, plus practical metrics such as $9m43s$ mission time and $410$ USD total cost. The work demonstrates a feasible, scalable approach to automated vector-control tasks with potential for public health impact, while outlining concrete avenues for hardware upgrades, dataset expansion, and robustness improvements.

Abstract

In this paper, we present a novel approach to the development and deployment of an autonomous mosquito breeding place detector rover with the object and obstacle detection capabilities to control mosquitoes. Mosquito-borne diseases continue to pose significant health threats globally, with conventional control methods proving slow and inefficient. Amidst rising concerns over the rapid spread of these diseases, there is an urgent need for innovative and efficient strategies to manage mosquito populations and prevent disease transmission. To mitigate the limitations of manual labor and traditional methods, our rover employs autonomous control strategies. Leveraging our own custom dataset, the rover can autonomously navigate along a pre-defined path, identifying and mitigating potential breeding grounds with precision. It then proceeds to eliminate these breeding grounds by spraying a chemical agent, effectively eradicating mosquito habitats. Our project demonstrates the effectiveness that is absent in traditional ways of controlling and safeguarding public health. The code for this project is available on GitHub at - https://github.com/faiyazabdullah/MosquitoMiner

Figures (8)

• Figure 1: Exploded View of the Hardware Components
• Figure 2: Overview of our System Architecture
• Figure 3: Calibration of MissionPlanner Ardupilot with MosquitoMiner
• Figure 4: Real-time object detection and position determination, with the green lines indicating the center of the rover.
• Figure 5: Overview of our Software Architecture