Solid waste mapping based on very high resolution remote sensing imagery and a novel deep learning approach

The urbanization worldwide leads to the rapid increase of solid waste, posing a threat to environment and people's wellbeing. However, it is challenging to detect solid waste sites with high accuracy due to complex landscape, and very few studies considered solid waste mapping across multi-cities and in large areas. To tackle this issue, this study proposes a novel deep learning model for solid waste mapping from very high resolution remote sensing imagery. By integrating a multi-scale dilated convolutional neural network (CNN) and a Swin-Transformer, both local and global features are aggregated. Experiments in China, India and Mexico indicate that the proposed model achieves high performance with an average accuracy of 90.62%. The novelty lies in the fusion of CNN and Transformer for solid waste mapping in multi-cities without the need for pixel-wise labelled data. Future work would consider more sophisticated methods such as semantic segmentation for fine-grained solid waste classification.

Automated summary

Urbanization leads to increased solid waste worldwide, endangering the environment and people's wellbeing. Detecting solid waste sites accurately is challenging due to complex landscapes, and few studies have investigated solid waste mapping across multiple cities and large areas. This study proposes a deep learning model that integrates a multi-scale dilated convolutional neural network (CNN) and a Swin-Transformer to map solid waste from high-resolution remote sensing imagery. Experiments in China, India, and Mexico show that the model achieves high performance with an average accuracy of 90.62%. The novelty lies in fusing CNN and Transformer for solid waste mapping without the need for pixel-wise labeled data. Future work may explore more advanced methods such as semantic segmentation for fine-grained solid waste classification.