Clutter Classification Using Deep Learning in Multiple Stages
This work addresses the need for more accurate path loss predictions in wireless communications by providing automated clutter classification, though it appears incremental as it applies existing deep learning methods to a specific domain.
The paper tackled the problem of improving wireless propagation model accuracy by automatically identifying environmental clutter types from satellite imagery using deep learning, resulting in enhanced prediction of key metrics like path loss.
Path loss prediction for wireless communications is highly dependent on the local environment. Propagation models including clutter information have been shown to significantly increase model accuracy. This paper explores the application of deep learning to satellite imagery to identify environmental clutter types automatically. Recognizing these clutter types has numerous uses, but our main application is to use clutter information to enhance propagation prediction models. Knowing the type of obstruction (tree, building, and further classifications) can improve the prediction accuracy of key propagation metrics such as path loss.