Detection and Classification of Whiteflies and Fruit Flies Using YOLO

摘要

Pests such as whiteflies and fruit flies are very small and are impractical to find and locate using only the naked eye. Pests Detection and monitoring will greatly help the farmers to detect and locate pests even if they are very small and even if they are too far from their farms. In this study, YOLOV3 was used to classify and detect objects, specifically whiteflies and fruit flies. The researchers used a Raspberry Pi camera to gather images. Moreover, the researcher provides desktop and web application to display images obtained by the Raspberry Pi camera. Based on the confusion matrix (Table 3), the model obtained an overall accuracy of 83.07% in classifying and detecting whiteflies and fruit flies.