Research on High-Precision Detection Scheme for Scenic Area Garbage Based on Deep Learning

With the rapid development of tourism, the issue of garbage pollution in scenic areas has become increasingly severe. Traditional manual cleaning methods are inefficient and prone to omissions. To address this problem, this paper proposes a high-precision garbage detection scheme (EYOLO-G) based on an improved YOLO algorithm. By introducing a lightweight network structure (GhostNet and Slim-Neck), a Coordinate Attention mechanism (CA), and a multi-scale receptive field module (RFB), the proposed method effectively enhances the detection accuracy of small-object garbage and improves the real-time performance of the system while reducing the model's parameter count and computational complexity. Experimental results show that the EYOLO-G model achieves [email protected] and [email protected]:0.95 scores of 96.20% and 77.77%, respectively, significantly outperforming mainstream object detection algorithms. This provides an efficient and intelligent solution for environmental management in smart scenic areas.