Dynamic histogram warping of image pairs for constant image brightness.
IEEE International Conference on Image Processing.
(pp. 366 - 369).
An examination of the images contained in the SRI JISCT stereo database revealed that the constant image brightness assumption in computer vision is often false. In this paper, experimental results show that image histograms are closely matched after dynamic histogram warping (DHW), especially when both histograms are modified simultaneously. DHW is also capable of removing simple constant additive and multiplicative biases without derivative operations, thereby avoiding amplification of high frequency noise. It is demonstrated that DHW can improve the estimates from stereo and optical flow estimators.
|Title:||Dynamic histogram warping of image pairs for constant image brightness|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science > Computer Science|
Archive Staff Only