An Evaluation of HDR Image Matching under Extreme Illumination Changes - IMT - Institut Mines-Télécom Access content directly
Conference Papers Year : 2016

An Evaluation of HDR Image Matching under Extreme Illumination Changes


High dynamic range (HDR) imaging has potential to facili- tate computer vision tasks such as image matching where lighting trans- formations hinder the matching performance. However, little has been done to quantify the gains with different possible HDR representations for vision algorithms like feature extraction. In this paper, we evaluate the performance of the full feature extraction pipeline, including detection and description, on ten different image representations: low dynamic range (LDR), seven different tone mapped (TM) HDR and two HDR imaging (linear and log encoded) representations. We measure the impact of using these different representations for feature matching using mean average precision (mAP) scores on four illumination change datasets. We perform feature extraction using four popular schemes in the literature: SIFT, SURF, BRISK, FREAK. With respect to previous studies, our observations confirm the advantages of HDR over conventional LDR imagery, and the fact that HDR linear values are not appropriate for vision tasks. However, HDR representations that work best for keypoint detection are not necessarily optimal when the full feature extraction is taken into account.
Fichier principal
Vignette du fichier
inproceedings-2016-16387-2.pdf (1.77 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01357141 , version 1 (02-09-2016)


  • HAL Id : hal-01357141 , version 1


Aakanksha A Rana, Giuseppe Valenzise, Frederic Dufaux. An Evaluation of HDR Image Matching under Extreme Illumination Changes. The International Conference on Visual Communications and Image Processing (VCIP), Nov 2016, Chengdu, China. ⟨hal-01357141⟩
188 View
232 Download


Gmail Facebook Twitter LinkedIn More