K. Greitans, M. Greitans. Multi-static UWB radar for classification of objects from different materials. Proceedings of 2021 IEEE Workshop on Microwave Theory and Techniques in Wireless Communications, 2021.
Bibtex citāts:
Bibtex citāts:
@inproceedings{12065_2021,
author = {K. Greitans and M. Greitans},
title = {Multi-static UWB radar for classification of objects from different materials},
journal = {Proceedings of 2021 IEEE Workshop on Microwave Theory and Techniques in Wireless Communications},
year = {2021}
}
author = {K. Greitans and M. Greitans},
title = {Multi-static UWB radar for classification of objects from different materials},
journal = {Proceedings of 2021 IEEE Workshop on Microwave Theory and Techniques in Wireless Communications},
year = {2021}
}
Anotācija: This paper evaluates the advantages of Multi-static Ultra-wide band (UWB) radar architecture for the classification of objects from different materials comparing single-static and bistatic UWB radar cases. In this research single transmitting and four receiving Vivaldi antennas are used. Antennas are connected to the UWB impulse radio radar that is configured to sample 1023 points with a sampling time of 20 ps per point. For the classification of objects, a hybrid artificial neural network model is used. The model consists of 4 channel single convolution layer blocks for feature recognition that are combined and processed by two extra deep layers. The networks were trained on data obtained from several objects from different materials - metal cans, regular PET bottles, crushed PET bottles, and glass bottles. The impact of the additional antennas of UWB radar are evaluated on PET material involved into two classes - regular and crushed bottles. This takes into account the impact of the different structures of objects. The results show 6 times increase of correctly classified objects with the multi-static approach in comparison with a single-channel case. The Multi-static architecture reaches 98.4% accuracy but a single channel evaluation accuracy varies from 91% to 95.1%. © 2021 IEEE.