Waste, as a primary cause of visual pollution, not only impacts public health but also has significant economic implications, particularly in tourism. Visual pollution from waste or trash encompasses various types that require classification. Cognitive cities are beginning to develop automatic systems to classify these types, but the task is challenging due to the similarity among different types of waste and the common features of most elements. To address this issue, we propose an innovative two-stage methodology using YOLOv8 for object detection. This advanced approach is designed to detect and classify 16 different types of waste objects. The proposed approach is compared to the traditional YOLOv8 to evaluate its performance. The experimental results highlight the effectiveness of the modified YOLOv8 approach, which integrates YOLOv8 for detection and the Swin Transformer for classification. Notably, when applied to larger image sizes, this enhanced method achieved a significant improvement in the F1-score, underscoring the viability and robustness of the proposed framework