Classification of Buried Objects From Ground Penetrating Radar Images by Using Second-Order Deep Learning Models
In this article, a new classification model based on covariance matrices is built in order to classify buried objects. The inputs of the proposed models are the hyperbola thumbnails obtained with a classical ground penetrating radar (GPR) system. These thumbnails are then inputs to the first layers...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10836936/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592912561471488 |
|---|---|
| author | Douba Jafuno Ammar Mian Guillaume Ginolhac Nickolas Stelzenmuller |
| author_facet | Douba Jafuno Ammar Mian Guillaume Ginolhac Nickolas Stelzenmuller |
| author_sort | Douba Jafuno |
| collection | DOAJ |
| description | In this article, a new classification model based on covariance matrices is built in order to classify buried objects. The inputs of the proposed models are the hyperbola thumbnails obtained with a classical ground penetrating radar (GPR) system. These thumbnails are then inputs to the first layers of a classical CNN, which then produces a covariance matrix using the outputs of the convolutional filters. Next, the covariance matrix is given to a network composed of specific layers to classify symmetric positive definite matrices. We show in a large database that our approach outperform shallow networks designed for GPR data and conventional CNNs typically used in computer vision applications, particularly when the number of training data decreases and in the presence of mislabeled data. We also illustrate the interest of our models when training data and test sets are obtained from different weather modes or considerations. |
| format | Article |
| id | doaj-art-282cbd432b2845d3ad41c9d1bd722b97 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-282cbd432b2845d3ad41c9d1bd722b972025-01-21T00:00:44ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183185319710.1109/JSTARS.2024.352442410836936Classification of Buried Objects From Ground Penetrating Radar Images by Using Second-Order Deep Learning ModelsDouba Jafuno0Ammar Mian1https://orcid.org/0000-0003-1796-8707Guillaume Ginolhac2https://orcid.org/0000-0001-9318-028XNickolas Stelzenmuller3LISTIC, University Savoie Mont-Blanc, Annecy, FranceLISTIC, University Savoie Mont-Blanc, Annecy, FranceLISTIC, University Savoie Mont-Blanc, Annecy, FranceGeolithe, Crolles, FranceIn this article, a new classification model based on covariance matrices is built in order to classify buried objects. The inputs of the proposed models are the hyperbola thumbnails obtained with a classical ground penetrating radar (GPR) system. These thumbnails are then inputs to the first layers of a classical CNN, which then produces a covariance matrix using the outputs of the convolutional filters. Next, the covariance matrix is given to a network composed of specific layers to classify symmetric positive definite matrices. We show in a large database that our approach outperform shallow networks designed for GPR data and conventional CNNs typically used in computer vision applications, particularly when the number of training data decreases and in the presence of mislabeled data. We also illustrate the interest of our models when training data and test sets are obtained from different weather modes or considerations.https://ieeexplore.ieee.org/document/10836936/Buried objects classificationcovariance matricesground penetrating radarsymmetric positive definite matrix networks |
| spellingShingle | Douba Jafuno Ammar Mian Guillaume Ginolhac Nickolas Stelzenmuller Classification of Buried Objects From Ground Penetrating Radar Images by Using Second-Order Deep Learning Models IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Buried objects classification covariance matrices ground penetrating radar symmetric positive definite matrix networks |
| title | Classification of Buried Objects From Ground Penetrating Radar Images by Using Second-Order Deep Learning Models |
| title_full | Classification of Buried Objects From Ground Penetrating Radar Images by Using Second-Order Deep Learning Models |
| title_fullStr | Classification of Buried Objects From Ground Penetrating Radar Images by Using Second-Order Deep Learning Models |
| title_full_unstemmed | Classification of Buried Objects From Ground Penetrating Radar Images by Using Second-Order Deep Learning Models |
| title_short | Classification of Buried Objects From Ground Penetrating Radar Images by Using Second-Order Deep Learning Models |
| title_sort | classification of buried objects from ground penetrating radar images by using second order deep learning models |
| topic | Buried objects classification covariance matrices ground penetrating radar symmetric positive definite matrix networks |
| url | https://ieeexplore.ieee.org/document/10836936/ |
| work_keys_str_mv | AT doubajafuno classificationofburiedobjectsfromgroundpenetratingradarimagesbyusingsecondorderdeeplearningmodels AT ammarmian classificationofburiedobjectsfromgroundpenetratingradarimagesbyusingsecondorderdeeplearningmodels AT guillaumeginolhac classificationofburiedobjectsfromgroundpenetratingradarimagesbyusingsecondorderdeeplearningmodels AT nickolasstelzenmuller classificationofburiedobjectsfromgroundpenetratingradarimagesbyusingsecondorderdeeplearningmodels |