Utilizing Polarization Diversity in GBSAR Data-Based Object Classification
In recent years, the development of intelligent sensor systems has experienced remarkable growth, particularly in the domain of microwave and millimeter wave sensing, thanks to the increased availability of affordable hardware components. With the development of smart Ground-Based Synthetic Aperture...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/7/2305 |
| _version_ | 1797211979600887808 |
|---|---|
| author | Filip Turčinović Marin Kačan Dario Bojanjac Marko Bosiljevac Zvonimir Šipuš |
| author_facet | Filip Turčinović Marin Kačan Dario Bojanjac Marko Bosiljevac Zvonimir Šipuš |
| author_sort | Filip Turčinović |
| collection | DOAJ |
| description | In recent years, the development of intelligent sensor systems has experienced remarkable growth, particularly in the domain of microwave and millimeter wave sensing, thanks to the increased availability of affordable hardware components. With the development of smart Ground-Based Synthetic Aperture Radar (GBSAR) system called GBSAR-Pi, we previously explored object classification applications based on raw radar data. Building upon this foundation, in this study, we analyze the potential of utilizing polarization information to improve the performance of deep learning models based on raw GBSAR data. The data are obtained with a GBSAR operating at 24 GHz with both vertical (VV) and horizontal (HH) polarization, resulting in two matrices (VV and HH) per observed scene. We present several approaches demonstrating the integration of such data into classification models based on a modified ResNet18 architecture. We also introduce a novel Siamese architecture tailored to accommodate the dual input radar data. The results indicate that a simple concatenation method is the most promising approach and underscore the importance of considering antenna polarization and merging strategies in deep learning applications based on radar data. |
| first_indexed | 2024-04-24T10:35:06Z |
| format | Article |
| id | doaj.art-e58c73112de14053a2b84f75f4a0a285 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-24T10:35:06Z |
| publishDate | 2024-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e58c73112de14053a2b84f75f4a0a2852024-04-12T13:26:44ZengMDPI AGSensors1424-82202024-04-01247230510.3390/s24072305Utilizing Polarization Diversity in GBSAR Data-Based Object ClassificationFilip Turčinović0Marin Kačan1Dario Bojanjac2Marko Bosiljevac3Zvonimir Šipuš4Faculty of Electrical Engineering and Computing, University of Zagreb, 10 000 Zagreb, CroatiaFaculty of Electrical Engineering and Computing, University of Zagreb, 10 000 Zagreb, CroatiaFaculty of Electrical Engineering and Computing, University of Zagreb, 10 000 Zagreb, CroatiaFaculty of Electrical Engineering and Computing, University of Zagreb, 10 000 Zagreb, CroatiaFaculty of Electrical Engineering and Computing, University of Zagreb, 10 000 Zagreb, CroatiaIn recent years, the development of intelligent sensor systems has experienced remarkable growth, particularly in the domain of microwave and millimeter wave sensing, thanks to the increased availability of affordable hardware components. With the development of smart Ground-Based Synthetic Aperture Radar (GBSAR) system called GBSAR-Pi, we previously explored object classification applications based on raw radar data. Building upon this foundation, in this study, we analyze the potential of utilizing polarization information to improve the performance of deep learning models based on raw GBSAR data. The data are obtained with a GBSAR operating at 24 GHz with both vertical (VV) and horizontal (HH) polarization, resulting in two matrices (VV and HH) per observed scene. We present several approaches demonstrating the integration of such data into classification models based on a modified ResNet18 architecture. We also introduce a novel Siamese architecture tailored to accommodate the dual input radar data. The results indicate that a simple concatenation method is the most promising approach and underscore the importance of considering antenna polarization and merging strategies in deep learning applications based on radar data.https://www.mdpi.com/1424-8220/24/7/2305ground-based SARpolarizationobject classificationradar dataResNet18 |
| spellingShingle | Filip Turčinović Marin Kačan Dario Bojanjac Marko Bosiljevac Zvonimir Šipuš Utilizing Polarization Diversity in GBSAR Data-Based Object Classification Sensors ground-based SAR polarization object classification radar data ResNet18 |
| title | Utilizing Polarization Diversity in GBSAR Data-Based Object Classification |
| title_full | Utilizing Polarization Diversity in GBSAR Data-Based Object Classification |
| title_fullStr | Utilizing Polarization Diversity in GBSAR Data-Based Object Classification |
| title_full_unstemmed | Utilizing Polarization Diversity in GBSAR Data-Based Object Classification |
| title_short | Utilizing Polarization Diversity in GBSAR Data-Based Object Classification |
| title_sort | utilizing polarization diversity in gbsar data based object classification |
| topic | ground-based SAR polarization object classification radar data ResNet18 |
| url | https://www.mdpi.com/1424-8220/24/7/2305 |
| work_keys_str_mv | AT filipturcinovic utilizingpolarizationdiversityingbsardatabasedobjectclassification AT marinkacan utilizingpolarizationdiversityingbsardatabasedobjectclassification AT dariobojanjac utilizingpolarizationdiversityingbsardatabasedobjectclassification AT markobosiljevac utilizingpolarizationdiversityingbsardatabasedobjectclassification AT zvonimirsipus utilizingpolarizationdiversityingbsardatabasedobjectclassification |