A Feasibility Study on Opportunistic Rainfall Measurement From Satellite TV Broadcasts

Rainfall precipitation maps are usually derived based on the measurements collected by classical weather devices, such as rain gauges and weather stations. This article aims to show the benefits obtained by opportunistic rainfall measurements based on signal strength measurements provided by commercial-grade satellite terminals (e.g., used in TV broadcasting). To assess not only the feasibility of this approach, with significant advantages in terms of capital and operational expenditure, but also improvements in terms of accuracy, we focus on a case study for agricultural applications using a Gaussian-modeled synthetic rain over a specific, real-world test area.

Vehicle classification based on convolutional networks applied to FM-CW radar signals

This paper investigates the processing of Frequency Modulated-Continuos Wave (FM-CW) radar signals for vehicle classification. In the last years deep learning has gained interest in several scientific fields and signal processing is not one exception. In this work we address the recognition of the vehicle category using a Convolutional Neural Network (CNN) applied to range Doppler signature. The developed system first transforms the 1-dimensional signal into a 3-dimensional signal that is subsequently used as input to the CNN. When using the trained model to predict the vehicle category we obtain good performance.