Preprint Article Version 1 This version not peer reviewed

Cross-Spectral Local Descriptors via Quadruplet Network

Version 1 : Received: 11 March 2017 / Approved: 13 March 2017 / Online: 13 March 2017 (08:31:22 CET)

A peer-reviewed article of this Preprint also exists.

Aguilera, C.A.; Sappa, A.D.; Aguilera, C.; Toledo, R. Cross-Spectral Local Descriptors via Quadruplet Network. Sensors 2017, 17, 873. Aguilera, C.A.; Sappa, A.D.; Aguilera, C.; Toledo, R. Cross-Spectral Local Descriptors via Quadruplet Network. Sensors 2017, 17, 873.

Journal reference: Sensors 2017, 17, 873
DOI: 10.3390/s17040873

Abstract

This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where for each matching pair there are always two possible non-matching patches; one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.

Subject Areas

cross-spectral; descriptor; infrared; CNN

Readers' Comments and Ratings (0)

Leave a public comment
Send a private comment to the author(s)
Rate this article
Views 0
Downloads 0
Comments 0
Metrics 0
Leave a public comment

×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.