Differentiating Stagnant Water from Wet Surface for Detecting Potential Mosquito Breeding Sites in Real Time

Abstract

Objective: Mosquito breeding site detection is crucial due to the colorization of water. Most systems fail to identify different types of stagnant water; hence, accurate water identification is essential. This study aims to devise an approach that can help increase the accuracy of detecting and distinguishing stagnant water from that of other wet surfaces. Methods: This work has proposed a technique using anchor boxes to reduce misclassification for detecting stagnant water. The images were collected for different types of water. The dataset was manually created by labeling images. Findings: We evaluated the proposed approach’s results and discovered that changing the anchor size and increasing training iterations on the dataset reduced misclassification by 89.20%. Novelty: The proposed method improves accuracy by using suitable anchor boxes to distinguish the water body from the wet surface. Unlike existing systems that are only capable of detecting a particular type of water; the improved YOLO V3 detects wet surfaces and different types of stagnant water due to training on a real-time customized dataset. Keywords: Object detection; Stagnant water; Street-View images; Misclassification; Mosquito breeding site