Plastic waste poses a vast danger to the surroundings and human health. Effective detection and control are vital for mitigating this problem. This study introduces about plastic waste detection using YOLOv5 algorithm by using this we can detect the objects. We advanced a device that makes use of YOLO to correctly identify plastic waste in various environments, along with seashores, oceans, and concrete regions. The gadget became skilled in a numerous dataset of categorized images containing distinct kinds of plastic waste. Data augmentation strategies have been employed to improve the version’s robustness. Our consequences reveal that the YOLO-primarily based system achieves high accuracy and outperforms conventional methods. This research aims to offer automatic solutions for tracking plastic pollution, with plans to integrate actual-time tracking and support waste management initiatives. The research paper offers a unique technique for identifying and categorizing primary assets of plastic waste via the utilization of the YOLOv5 deep studying object detection set of rules. The proliferation of plastic waste has emerged as a full-size environmental subject because of its destructive impact on ecosystems and human health. Accurate and efficient detection of plastic waste is important for effective waste control and pollution management. The assessment of the overall performance is carried out the use of overarching criteria, inclusive of the counseled common precision (mAP) and frames consistent with 2nd (FPS), showcasing its efficacy in figuring out and classifying plastic waste with precision and performance. The research paper contributes to the sphere of laptop imaginative and prescient and environmental technological know-how imparting a practical and efficient answer for plastic waste detection. The proposed technique can be included in automatic.