Optimizing Tone Mapping Operators for Keypoint Detection under Illumination Changes

Abstract :

Tone mapping operators (TMO) have recently raised interest for their capability to handle illumination changes. However, these TMOs are optimized with respect to perception rather than image analysis tasks like keypoint detection. Moreover, no work has been done to analyze the factors affecting the optimization of TMOs for such tasks. In this paper, we investigate the influence of two factors– Correlation Coefficient (CC) and Repeatability Rate (RR) of the tone mapped images for the optimization of classical Retinex based models to enhance keypoint detection under illumination changes. CC-based optimized models aim at increasing the similarity of the tone mapped images. Conversely, RR-based optimized models quantify the optimal detection performance gains. By considering two simple Retinex based models, i.e., Gaussian and bilateral filtering, we show that estimating as precisely as possible the illumination, CC-based optimized models do not necessarily bring to optimal keypoint detection performance. We conclude that, instead, other criteria specific to RR-based optimized models should be taken into account. Moreover, large gains in performance with respect to existing popular TMOs motivate further research towards optimal tone mapping technique for computer vision applications.

Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal-imt.archives-ouvertes.fr/hal-01349708
Contributor : Admin Télécom Paristech <>
Submitted on : Thursday, July 28, 2016 - 1:58:08 PM
Last modification on : Friday, June 7, 2019 - 11:07:44 AM
Long-term archiving on : Saturday, October 29, 2016 - 10:50:13 AM

File

inproceedings-2016-16267-1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01349708, version 1

Collections

Citation

Aakanksha Rana, Giuseppe Valenzise, Frederic Dufaux. Optimizing Tone Mapping Operators for Keypoint Detection under Illumination Changes. 2016 IEEE Workshop on Multimedia Signal Processing (MMSP 2016), Sep 2016, Montréal, Canada. ⟨hal-01349708⟩

Share

Metrics

Record views

426

Files downloads

313