A LINE SEGMENT DETECTOR FOR SAR IMAGES WITH CONTROLLED FALSE ALARM RATE

Abstract :

In this paper we propose to adapt LSD [1] (a state-of-the-art line segment detector for optical images) to SAR images. The first modification is replacing the gradient computation with an exponentially weighted ratio-based method which has a constant false alarm rate for SAR images. Next, we observe that the strong noise removal necessary for processing SAR images strongly impairs the independent hypothesis of the a contrario model used by LSD. A first order Markov chain is used to take the spatial dependencies into consideration. Experiments show that the proposed method has good perfor- mances and the number of false detections is well controlled.

Type de document :
Communication dans un congrès
IGARSS, Jul 2018, Valencia, Spain. IGARSS, 2018
Liste complète des métadonnées

https://hal-imt.archives-ouvertes.fr/hal-01860265
Contributeur : Admin Télécom Paristech <>
Soumis le : jeudi 23 août 2018 - 10:56:27
Dernière modification le : mardi 11 septembre 2018 - 14:48:01

Identifiants

  • HAL Id : hal-01860265, version 1

Citation

Chenguang Liu, Rémy Abergel, Yann Gousseau, Florence Tupin. A LINE SEGMENT DETECTOR FOR SAR IMAGES WITH CONTROLLED FALSE ALARM RATE. IGARSS, Jul 2018, Valencia, Spain. IGARSS, 2018. 〈hal-01860265〉

Partager

Métriques

Consultations de la notice

39