Aquatic Waste Sorting and Classification Using Image Processing and Detection System Using YOLOV8 Model and Django

In waste management, efficient and automated sorting systems are critical in enhancing recycling processes and reducing labor. A real-time waste sorting method has been developed using YOLOv8, a state-of-the-art object detection model, in detecting and classifying plastics, metals, glass, and paper. It works by capturing live video feeds and then processes every frame through YOLOv8 for object detection; it also provides the output through a web interface that has been developed with Django. With YOLOv8’s capability of real-time object detection, it can classify waste materials at high speed and accuracy to ensure sorting can be carried out without substantial delays, thereby being suitable for dynamic and high-throughput environments like recycling plants or municipal waste management facilities. The problem of proper waste management is an acute global concern, especially in aquatic ecosystems, where pollution poses significant threats to ecological integrity and public health. This introduces a new approach: front-end development through HTML, CSS, and back-end development using Python language with Anaconda to develop an environment that can be used to deploy an API. The most outstanding feature is giving the system real-time feedback that improves rapid classification without increasing errors in waste sorting. It is designed to be scalable, thus fitting diverse operation settings such as municipal waste management facilities, industrial recycling centers, and even remote aquatic environments.