Toward improved surveillance of Aedes aegypti breeding grounds through artificially augmented data

Abstract

The Aedes aegypti mosquito transmits several diseases, including dengue, zika, and chikungunya. To prevent these diseases, identifying and removing mosquito breeding sites is essential, but it is a time-consuming and labor-intensive task. To improve efficiency, computer vision and machine learning can be used to detect potential breeding grounds automatically. In this context, we explore the use of data augmentation strategies including random scaling, rotation, as well as color and brightness adjustments for improving the automatic detection of potential Aedes aegypti breeding grounds using videos acquired by a drone. The faster region-based convolutional neural network (Faster R-CNN) and the you only look once (YOLO) v5 object detectors are used on a database of aerial videos containing breeding-related objects. When employing the data augmentation, tire-detection results show F1 scores of 0.79 and 0.81 for the Faster R-CNN and YOLOv5 networks, respectively, surpassing current state-of-the-art values. The detection performance of the algorithms increased by up to 14.1%, which is a significant improvement. These results indicate that artificial data augmentation reduces overfitting, improving the models’ robustness. The developed system can be employed to help health agencies in locating potential Aedes aegypti outbreaks more efficiently.