CDWNet: An Efficient and Lightweight Classification and Object Detection Algorithm for Construction and Demolition Waste

To address the challenge of effectively classifying and recycling construction and demolition waste (CDW), this study proposes a lightweight object detection algorithm, CDWNet, based on YOLO11. The model constructs a Global Context-Aware Detection Head (GCADHead) and a Hierarchical Enriched Feature Aggregation Network (HEFAN), and introduces the lightweight convolution module GSConv. Experimental results demonstrate that CDWNet achieves high accuracy and efficiency in waste classification under complex scenarios, significantly reducing the number of parameters and computational costs while improving performance. This study provides an effective solution for deployment on resource-constrained edge devices, contributing to the automation of CDW classification.