Adaptive enhancement and noise reduction in very low light-level video

Henrik Malm, Magnus Oskarsson, Eric Warrant, Petrik Clarberg, Jon Hasselgren, Calle Lejdfors
Lund Vision Group, Department of Cell and Organism Biology, Lund Unversity, Helgonavagen 3, S-223 62 Lund, Sweden
11th International Conference on Computer Vision, 2007. – IEEE Press. – 1550-5499. – 978-1-4244-1631-8 ; p.1-8


   title={Adaptive enhancement and noise reduction in very low light-level video},

   author={Malm, H. and Oskarsson, M. and Warrant, E. and Clarberg, P. and Hasselgren, J. and Lejdfors, C.},

   booktitle={Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on},






Download Download (PDF)   View View   Source Source   



A general methodology for noise reduction and contrast enhancement in very noisy image data with low dynamic range is presented. Video footage recorded in very dim light is especially targeted. Smoothing kernels that automatically adapt to the local spatio-temporal intensity structure in the image sequences are constructed in order to preserve and enhance fine spatial detail and prevent motion blur. In color image data, the chromaticity is restored and demosaicing of raw RGB input data is performed simultaneously with the noise reduction. The method is very general, contains few user-defined parameters and has been developed for efficient parallel computation using a GPU. The technique has been applied to image sequences with various degrees of darkness and noise levels, and results from some of these tests, and comparisons to other methods, are presented. The present work has been inspired by research on vision in nocturnal animals, particularly the spatial and temporal visual summation that allows these animals to see in dim light.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: