In the context of rapid urbanization, the challenge of effective garbage disposal has become increasingly significant. Traditional methods for addressing illegal littering by pedestrians are not only inefficient but also resource-intensive, demanding considerable manpower and materials. This study introduces a deep learning-based approach for detecting improper garbage disposal behavior. Leveraging advanced deep learning technologies, this approach focuses on object detection, tracking, and human posture analysis to identify and alert against illegal dumping activities captured in video footage, specifically targeting incidents outside designated times or areas. The primary aim is to facilitate prompt detection and mitigate associated health risks. The system uses three deep learning models, YOLOv5, DeepSORT and MobilePose. YOLOv5 is used to identify the human body and garbage bag, DeepSORT is used to track the two, and MobilePose identifies the key points of the human body for posture estimation. The tracking algorithm is used to determine whether to throw garbage.