Comparison of SEM methods for poles estimation from scattered field by canonical objects

Zaky, Yasmina; Fortino, Nicolas; Dauvignac, Jean-Yves; Seyfert, Fabien; Olivi, Martine; Baratchart, Laurent

doi:10.1109/radarconf2043947.2020.9266410

Cited by 8 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SEM data are extracted by applying VF in frequency domain [23]. Indeed, it was shown in [24] that VF is more robust to noise and more accurate than other SEM techniques. It is a widely used Fig.…”

Section: Scattered Field Data Generation and Pre-processingmentioning

confidence: 99%

Section: )mentioning

confidence: 99%

“…The poles are of the following form: a m = − σ m + jω m , where σ m is the damping factor and ω m is the natural pulsation of the m th singularity. VF is chosen to extract the object CNRs because we have shown in a previous work that this method is more robust to noise and more accurate than other SEM techniques (Zaky et al., 2020).…”

Section: Scattered Field Data Generation and Pre‐processingmentioning

confidence: 99%

“…Although the SEM is known for its sensitivity to noise, these performances can be explained by a combination of three major elements. First, the use of VF which is an efficient SEM method chosen for its robustness to noise and that has been seldom used for object characterization (Zaky et al., 2020). Second, the sparsity of the proposed original input vector integrating not only the natural frequencies but also their respective Q ‐factors and residues.…”

Section: Classification Of Sphere Materialsmentioning

confidence: 99%

See 3 more Smart Citations

Generalization Ability of Deep Learning Algorithms Trained Using SEM Data for Objects Classification

et al. 2022

View full text Add to dashboard Cite

This paper proposes a workflow to efficiently determine the material of spherical objects and the location of the receiving antenna relative to their position in bi-static measurements using supervised learning techniques. From a single observation, we compare classification performances resulting from the application of several classifiers on different data types: the Ultra-Wide Band scattered field in time and frequency domains and pre-processed data from the Singularity Expansion Method (SEM). Indeed, the resonances extracted using the SEM are aspect independent and therefore, are used to discriminate the objects. As for the residues, they depend upon the aspect angle and can hence be exploited to determine the observation angle. We construct 3 datasets to assess which one yields the highest accuracy while using the simplest and fastest classifiers. Hence, 80% of each dataset is used for training and the remaining 20% are used for testing. In a further step, we test with sphere sizes and data with several noisy levels that were not in the training datasets. Although SEM is noise sensitive, associating a robust feature extraction technique (Vector Fitting) with a simple but reliable classifier is promising, particularly when generalizing to data not included in the training set.

show abstract

Section: Scattered Field Data Generation and Pre-processingmentioning

confidence: 99%

Section: )mentioning

confidence: 99%

Section: Scattered Field Data Generation and Pre‐processingmentioning

confidence: 99%

Section: Classification Of Sphere Materialsmentioning

confidence: 99%

See 2 more Smart Citations

Generalization Ability of Deep Learning Algorithms Trained Using SEM Data for Objects Classification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Although the SEM is known for its sensitivity to noise, these performances can be explained by a combination of three major elements. Firstly, the use of VF which is an efficient SEM method chosen for its robustness to noise [24]. Secondly, the sparsity of the proposed original input vector integrating not only the natural frequencies but also their respective residues and Q-factors.…”

Section: )mentioning

confidence: 99%

Generalization Ability of Deep Learning Algorithms Trained using SEM Data for Objects Classification

Zaky¹,

fortino²,

Miramond³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper proposes a workflow to efficiently determine the material of spherical objects and the location of the receiving antenna relative to their position in bi-static measurements using supervised learning techniques. From a single observation, we compare classification performances resulting from the application of several classifiers on different data types: the Ultra-Wide Band scattered field in time and frequency domains and pre-processed data from the Singularity Expansion Method (SEM). Indeed, the resonances extracted using the SEM are aspect independent and therefore, are used to discriminate the objects. As for the residues, they depend upon the aspect angle and can hence be exploited to determine the observation angle. We construct 3 datasets to assess which one yields the highest accuracy while using the simplest and fastest classifiers. Hence, 80% of each dataset is used for training and the remaining 20% are used for testing. In a further step, we test with sphere sizes and data with several noisy levels that were not in the training datasets. Although SEM is noise sensitive, associating a robust feature extraction technique with a simple but reliable classifier is promising, particularly when generalizing to data not included in the training set.

show abstract

Shape and orientation classification of objects based on their electromagnetic signatures using convolutional neural networks

Zaky,

Fortino,

Miramond

et al. 2024

Inverse Problems

View full text Add to dashboard Cite

This study addresses the classification of objects using their electromagnetic signatures with Convolutional Neural Networks (CNNs) trained on noiseless data. The singularity expansion method (SEM) was applied to establish a compact model that accurately represents the ultra-wideband scattered field of an object, independently of its orientation and observation angle. To perform the classification, we used a CNN associated with a noise-robust SEM technique to classify different objects based on their characteristic parameters. To validate this approach, we compared the performance of the classifier with and without SEM pre-processing of the scattered field for different noise levels and for object sizes not present in the training set. Moreover, we propose a procedure that determines the direction of the receiving antenna and orientation of an object based on the residues associated with each complex natural resonance. This classification procedure using pre-processed SEM data is promising, especially when generalizing to object sizes not included in the training set.

show abstract

Comparison of SEM methods for poles estimation from scattered field by canonical objects

Cited by 8 publications

References 18 publications

Generalization Ability of Deep Learning Algorithms Trained Using SEM Data for Objects Classification

Generalization Ability of Deep Learning Algorithms Trained Using SEM Data for Objects Classification

Generalization Ability of Deep Learning Algorithms Trained using SEM Data for Objects Classification

Shape and orientation classification of objects based on their electromagnetic signatures using convolutional neural networks

Contact Info

Product

Resources

About