AI-Enabled Intelligent Waste Detection and Classification Using Deep Learning for Smart Waste Management

The AI-Based Garbage Detection System developed in this project demonstrates an effective approach to identifying garbage in images or video streams using computer vision and deep learning techniques. The system utilizes the YOLOv8 object detection model, which provides high detection accuracy. By processing inputs frame-by-frame and marking detected garbage objects with bounding boxes, the system provides clear and interpretable results. The integration of Flask enables a web-based user interface, making the system accessible and easy to use for individuals without technical expertise. Users can upload both images or videos, and the system automatically detects garbage and displays the processed results. This helps in automation and reduces the dependency on manual monitoring efforts. In practical terms, this system significantly reduces manual garbage monitoring efforts by approximately 75-80%, making it useful for municipal waste management teams, environmental surveillance, public area monitoring, and smart city initiatives. Overall, the project successfully meets its objectives by providing a functional, automated, and efficient garbage detection solution.

[1]         A. Pandey et al., "Garbage Detection System Using Image Processing," 2025 3rd International Conference on Disruptive Technologies (ICDT), Greater Noida, India, 2025, pp. 250-254, doi: 10.1109/ICDT63985.2025.10986639. [2]         R. Raman et al., "Real-Time Video Management System for Robotic Waste Sorting and Recycling Using IoT and Machine Learning," 2023 Second International Conference On Smart Technologies For Smart Nation (SmartTechCon), Singapore, Singapore, 2023, pp. 227-232, doi: 10.1109/SmartTechCon57526.2023.10391637. [3]         J. Xu, "Research on garbage detection and classification based on YOLOv8," 2024 5th International Conference on Computer Vision, Image and Deep Learning (CVIDL), Zhuhai, China, 2024, pp. 778-781, doi: 10.1109/CVIDL62147.2024.10603839. [4]         Wing Li et al., “Dens-YOLO6: A Small Object Detection Model for Garbage Detection on Water Surface,” Multimed Tools Appl 83, vol. 83, pages 55751–55771, (2024) [5]         R. Bawankule et al., "Visual Detection of Waste using YOLOv8," 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS), Coimbatore, India, 2023, pp. 869-873, doi: 10.1109/ICSCSS57650.2023.10169688 [6]         P. K. Sree et al., "Waste Management Detection Using Deep Learning," 2023 3rd International Conference on Computing and Information Technology (ICCIT), Tabuk, Saudi Arabia, 2023, pp. 50-54, doi: 10.1109/ICCIT58132.2023.10273898 [7]         Z. Pan et al., "Research on Improved Yolo on Garbage Classification Task," 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), Changchun, China, 2022, pp. 951-953, doi: 10.1109/EEBDA53927.2022.9744865. [8]          Jiaqi Xu et al., "Research on River Floating Objects Detection Method Based on Deep Learning", 2024 2nd International Conference on Computer, Vision and Intelligent Technology (IEEE),  (2024),doi:10.1109/ICCVIT63928.2024.10872426 [9]         D. Patel et al., "Garbage Detection using Advanced Object Detection Techniques," 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS), Coimbatore, India, 2021, pp. 526-531, doi: 10.1109/ICAIS50930.2021.9395916 [10]       B. D. Carolis et al., "YOLO TrashNet: Garbage Detection in Video Streams," 2020 IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS), Bari, Italy, 2020, pp. 1-7, doi: 10.1109/EAIS48028.2020.9122693.