Skip to Main content Skip to Navigation
Journal articles

Real-time bio-inspired contrast enhancement on GPU

Abstract : This paper describes a new contrast enhancement technique inspired in the way the human retina works to increase the degree of detail, mitigate glares and enhance the visibility of the scene in both bright and dim lighting conditions. The proposed operator and its real-time implementation are specially aimed as an aid system for visually impaired people who struggle to manage themselves in environments where illumination is not uniform or changes rapidly. This aid device processes in real-time, with minimum latency, the input of a camera and shows the enhanced image on a Head Mounted Display (HMD). To meet all these requirements we have implemented the whole model in a light-weight netbook which integrates a GPU NVIDIA ION2 and performs at a maximum rate of 27 frames per second when working with VGA resolution images (640x480RGB images).
Document type :
Journal articles
Complete list of metadata

https://www.hal.inserm.fr/inserm-03391584
Contributor : Christine Dupuis Connect in order to contact the contributor
Submitted on : Thursday, October 21, 2021 - 4:32:28 PM
Last modification on : Monday, November 8, 2021 - 6:32:02 PM

Identifiers

Collections

Citation

Raquel Ureña, Christian Morillas, Francisco Pelayo. Real-time bio-inspired contrast enhancement on GPU. Neurocomputing, Elsevier, 2013, 121, pp.40-52. ⟨10.1016/j.neucom.2012.09.035⟩. ⟨inserm-03391584⟩

Share

Metrics

Record views

11