Histogram-based image registration for real-time high dynamic range videos

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 3 times faster than comparable algorithms.