High-Resolution Range Profile Classifiers Require Aspect-Angle Awareness
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912931559505920 |
|---|---|
| author | Brient, Edwyn Velasco-Forero, Santiago Kassab, Rami |
| author_facet | Brient, Edwyn Velasco-Forero, Santiago Kassab, Rami |
| contents | We revisit High-Resolution Range Profile (HRRP) classification with aspect-angle conditioning. While prior work often assumes that aspect-angle information is incomplete during training or unavailable at inference, we study a setting where angles are available for all training samples and explicitly provided to the classifier. Using three datasets and a broad range of conditioning strategies and model architectures, we show that both single-profile and sequential classifiers benefit consistently from aspect-angle awareness, with an average accuracy gain of about 7% and improvements of up to 10%, depending on the model and dataset. In practice, aspect angles are not directly measured and must be estimated. We show that a causal Kalman filter can estimate them online with a median error of 5{\textdegree}, and that training and inference with estimated angles preserves most of the gains, supporting the proposed approach in realistic conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00087 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | High-Resolution Range Profile Classifiers Require Aspect-Angle Awareness Brient, Edwyn Velasco-Forero, Santiago Kassab, Rami Signal Processing Artificial Intelligence Machine Learning We revisit High-Resolution Range Profile (HRRP) classification with aspect-angle conditioning. While prior work often assumes that aspect-angle information is incomplete during training or unavailable at inference, we study a setting where angles are available for all training samples and explicitly provided to the classifier. Using three datasets and a broad range of conditioning strategies and model architectures, we show that both single-profile and sequential classifiers benefit consistently from aspect-angle awareness, with an average accuracy gain of about 7% and improvements of up to 10%, depending on the model and dataset. In practice, aspect angles are not directly measured and must be estimated. We show that a causal Kalman filter can estimate them online with a median error of 5{\textdegree}, and that training and inference with estimated angles preserves most of the gains, supporting the proposed approach in realistic conditions. |
| title | High-Resolution Range Profile Classifiers Require Aspect-Angle Awareness |
| topic | Signal Processing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.00087 |