The rapid growth of urban populations has intensified the challenges associated with solid waste management. Improper waste segregation leads to environmental pollution, health hazards, and inefficient recycling processes. Conventional waste management systems rely heavily on manual segregation, which is unhygienic, labor-intensive, and often inaccurate. To overcome these limitations, this paper proposes a computer vision–based smart waste segregation system integrating YOLO deep learning, embedded control, and IoT-enabled real-time monitoring. The proposed system employs a camera to capture waste images, which are processed using a YOLO-based object detection model to classify waste into biodegradable and non-biodegradable categories. Based on the classification result, an Arduino Nano–controlled mechanical unit automatically segregates waste into appropriate bins. Additionally, ultrasonic, flame, and air quality sensors continuously monitor bin fill levels and environmental safety conditions. All sensor data are transmitted to a cloud-based IoT dashboard for real-time visualization and alert generation. The proposed system reduces human intervention, improves segregation accuracy, enhances hygiene, and supports intelligent waste collection strategies. Owing to its low cost, modular design, and scalability, the system is suitable for deployment in smart cities and institutional environments.
Download
Download XML