Open Access Open Access  Restricted Access Subscription or Fee Access

Histogram-Based Image Registration for Real-Time High Dynamic Range Videos

M.B. Bose, B. Balaji, R. Rakesh


We introduce a novel approach for image registration for high dynamic range (HDR) videos. We estimate a translation vector between two low dynamic range (LDR) frames captured at different exposure settings. By using row and column histograms, counting the number of dark and bright pixels in a row or column, and maximizing the correlation between the histograms of two consecutive frames, we reduce the two-dimensional problem to two one-dimensional searches. This saves computation time, which is critical in recording HDR videos in real-time. The robustness of our estimation is increased through application of a Kalman filter. A novel certainty criterium controls whether the estimated translation is used directly or discarded and extrapolated from previous frames. Our experiments show that our proposed approach performs registration more robustly on videos and is 1.4 to 3times faster than comparable algorithms.


Image Registration, HDR Video

Full Text:



B. Guthier, S. Kopf, and W. Effelsberg, “Capturing high dynamic range images with partial re-exposures,” in IEEE 10th Workshop on Multimedia Signal Processing, 2008, pp. 241–246

S.B. Kang, M. Uyttendaele, S. Winder, and R. Szeliski, “High dynamic range video,” in ACM Transactions on Graphics 22(3), 2003, pp. 319–325.

B. Guthier, S. Kopf, and W. Effelsberg, “High-resolution inline video-aoi for printed circuit assemblies,” in Proceedings of IS&T/SPIE Electronic Imaging, 2009.

P.M.Q. Aguiar, “Unsupervised simultaneous registration and exposure correction,” in Proc. of IEEE ICIP, 2006,pp. 361–364.

G. Ward, “Fast, robust image registration for compositing high dynamic range photographs from handheld exposures,” in Journal of Graphics Tools, 8(2), 2003, pp.17–30.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.