Learning-based Adaptive Tone Mapping for Keypoint Detection

Abstract : The goal of tone mapping operators (TMOs) has traditionally been to display high dynamic range (HDR) pictures in a perceptually favorable way. However, when tone-mapped images are to be used for computer vision tasks such as keypoint detection, these design approaches are suboptimal. In this paper, we propose a new learning-based adaptive tone mapping framework which aims at enhancing keypoint stability under drastic illumination variations. To this end, we design a pixel-wise adaptive TMO which is modulated based on a model derived by Support Vector Regression (SVR) using local higher order characteristics. To circumvent the difficulty to train SVR in this context, we further propose a simple detection similarity-maximization model to generate appropriate training samples using multiple images undergoing illumination transformations. We evaluate the performance of our proposed framework in terms of keypoint repeatability for state-of-the-art keypoint detectors. Experimental results show that our proposed learning-based adaptive TMO yields higher keypoint stability when compared to existing perceptually-driven state-of-the-art TMOs.
Type de document :
Communication dans un congrès
IEEE International Conference on Multimedia & Expo (ICME’2017), Jul 2017, Hong Kong, Hong Kong SAR China. 2017, 〈10.1109/icme.2017.8019394 〉
Liste complète des métadonnées

Littérature citée [29 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01478337
Contributeur : Frédéric Dufaux <>
Soumis le : mercredi 19 juillet 2017 - 15:41:39
Dernière modification le : mercredi 20 février 2019 - 14:38:23

Fichier

aakanksha_icme17.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Aakanksha Rana, Giuseppe Valenzise, Frederic Dufaux. Learning-based Adaptive Tone Mapping for Keypoint Detection. IEEE International Conference on Multimedia & Expo (ICME’2017), Jul 2017, Hong Kong, Hong Kong SAR China. 2017, 〈10.1109/icme.2017.8019394 〉. 〈hal-01478337〉

Partager

Métriques

Consultations de la notice

602

Téléchargements de fichiers

83