Classification of GPR Signals Via Covariance Pooling on CNN Features Within a Riemannian Framework

Gallet, Matthieu; Mian, Ammar; Ginolhac, Guillaume; Stelzenmuller, Nickolas

doi:10.1109/igarss46834.2022.9884684

Cited by 3 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This selection details the behaviour of the 3 main proposed families. More results can be found in [83], where the authors focus specifically on the Random Forest and CNN studies.…”

Section: A Evaluation Of Modelsmentioning

confidence: 99%

“…For the remainder of this study, our focus will be on the KNN algorithm due to its ability to incorporate a distance measure between samples. Additional analyses can be found in [83] on random forest and CNN.…”

Section: B Evaluation Of Auxiliary Datamentioning

confidence: 99%

“…But, the emphasis is placed on recognising attributes that can serve as distinguishing factors between classes. These features can be directly polarimetric channels [43], obtained through the use of classical textural extractors such as GLCM 1 [44] or even through the first layers of deep learning networks as shown in the GPR 2 data in [45]. Some works have integrated the use of these supervised techniques for the study of the cryosphere, such as [46] with artificial neural networks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Wet Snow Detection From Satellite SAR Images by Machine Learning With Physical Snowpack Model Labeling

Gallet,

Atto,

Karbou

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

The detection of wet snow by satellite imaging is currently done in an unsupervised way and lacks quantitative evaluation due to the difficulty of collecting ground truths in extreme environments. In this paper, we propose to take into account information associated with a physical model to label satellite data for the purpose of supervised learning of snow properties using Synthetic Aperture Radar (SAR) imagery. This dataset is constructed from Sentinel-1 SAR images, augmented with topographic information obtained from a Digital Elevation Model (DEM). The labelling of this data is done at the scale of the Northern Alps using the CROCUS physical snow model. Then, we trained, over thirteen combinations of labelled dataset, a wide range of machine learning models to quantitatively identify the most relevant learners for the wet snow detection task. The results demonstrate consistency among the different algorithms, with significant improvement observed when incorporating polarimetric combinations and topographic orientation data in the input of the model. The best algorithmic solution trained on this dataset is evaluated by comparing the obtained wet snow map over a validation area in the French massif of the Grandes Rousses with the existing Copernicus products, Fractional Snow Cover (FSC) and SAR Wet Snow (SWS). We also compare the temporal results obtained at one meteorological station located in the test area. The results show a better representation of wet snow during the melting period using the supervised learning approach, as well as a reduction in areas classified as wet during the winter season.

show abstract

“…This selection details the behaviour of the 3 main proposed families. More results can be found in [83], where the authors focus specifically on the Random Forest and CNN studies.…”

Section: A Evaluation Of Modelsmentioning

confidence: 99%

Section: B Evaluation Of Auxiliary Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Wet Snow Detection From Satellite SAR Images by Machine Learning With Physical Snowpack Model Labeling

Gallet,

Atto,

Karbou

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper, we study the detection of stationary targets in a way that is robust to heterogeneous wall clutter. This topic of robustness has been studied for Ground Penetrating Radar [3,4] and TWRI [5] which added onto nonrobust methods [6,7]. In a setting of measures obtained parallel to the wall, front wall interferences form a low rank matrix.…”

Section: Introductionmentioning

confidence: 99%

Through-The-Wall Radar Imaging With Wall Clutter Removal Via Riemannian Optimization On The Fixed-Rank Manifold

Brehier,

Breloy,

Ren

et al. 2024

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

We introduce a new method for Through-the-Wall Radar Imaging (TWRI) that detects the location of stationary targets hidden by a wall. A crucial step is the mitigation of wall returns which obscure the scene and which are characterized by their low-rankedness given the radar measurement setup. Whereas existing methods make use of nuclear norm minimization or Truncated Singular Value Decomposition (TSVD), we propose to leverage Riemannian optimization over the manifold of fixed-rank matrices in order to use robust estimation while keeping the original rank constraint without relaxation. A detection step via sparse recovery is then performed and the overall method is compared with existing methods over simulated scenes. The results show that the proposed method achieves a better performance.

show abstract

Hyperbolic Attention-Driven Deep Networks for Enhanced GPR Imaging of Underground Pipelines

Liu,

Yuan,

Song

et al. 2024

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Classification of GPR Signals Via Covariance Pooling on CNN Features Within a Riemannian Framework

Cited by 3 publications

References 10 publications

Wet Snow Detection From Satellite SAR Images by Machine Learning With Physical Snowpack Model Labeling

Wet Snow Detection From Satellite SAR Images by Machine Learning With Physical Snowpack Model Labeling

Through-The-Wall Radar Imaging With Wall Clutter Removal Via Riemannian Optimization On The Fixed-Rank Manifold

Hyperbolic Attention-Driven Deep Networks for Enhanced GPR Imaging of Underground Pipelines

Contact Info

Product

Resources

About