Optimization of automated garbage recognition model based on ResNet-50 and weakly supervised CNN for sustainable urban development

Abstract

In the context of sustainable urban development, effective garbage management plays a crucial role. However, traditional methods encounter limitations in terms of data quality and quantity. The research on automatic garbage image recognition and classification methods based on deep learning has been gaining attention. This study proposes an integrated garbage image recognition and classification method that combines ResNet-50, YOLOv5, and weakly supervised CNN algorithms. The aim is to enhance both the accuracy and efficiency of image recognition, optimize intelligent garbage management, and promote urban sustainable development planning. The ResNet-50 model is employed to extract meaningful features from images and train weakly supervised CNN models for subsequent training and prediction. This enables the analysis of urban environmental development trends and the formulation of planning measures. Through evaluation on four representative public datasets, the proposed method outperforms several traditional algorithms in terms of accuracy, efficiency, and stability in garbage image recognition systems. Notably, on the HGI-30 dataset, the algorithm achieves significant improvements by reducing inference time by over 48.6%, FLOPs by over 46.5%, and MAPE by over 41%. These enhancements greatly enhance the accuracy and robustness of garbage image classification, highlighting the substantial significance of this method in the realms of garbage management and environmental protection.

Keywords

• Garbage image recognition
• ResNet-50
• YOLOv5
• Internet of Things (IoT)
• Sustainable urban development planning