About this document
Solid Waste Mapping via Deep Learning by Delon Temo is a document available to read on EtoBox.
The study presents a novel deep learning model, SW-Net, for solid waste mapping using very high resolution remote sensing imagery. By integrating a multi-scale dilated convolutional neural network and a Swin-Transformer, the model achieves an average accuracy of 90.62% in detecting solid waste across cities in China, India, and Mexico without requiring pixel-wise labeled data. This research addresses the challenges of solid waste detection in complex urban landscapes and aims to provide valuable spatial dat
- Author
- Delon Temo
- Language
- EN