This paper presents an algorithm for compositing a high dynamic range (HDR) image from multi-exposure images,\nconsidering inconsistent pixels for the reduction of ghost artifacts. In HDR images, ghost artifacts may appear when\nthere are moving objects while taking multiple images with different exposures. To prevent such artifacts, it is\nimportant to detect inconsistent pixels caused by moving objects in consecutive frames and then to assign zero\nweights to the corresponding pixels in the fusion process. This problem is formulated as a binary labeling problem\nbased on a Markov random field (MRF) framework, the solution of which is a binary map for each exposure image,\nwhich identifies the pixels to be excluded in the fusion process. To obtain the ghost map, the distribution of zero mean\nnormalized cross-correlation (ZNCC) of an image with respect to the reference frame is modeled as a mixture of\nGaussian functions, and the parameters of this function are used to design the energy function. However, this method\ndoes not well detect faint objects that are in low-contrast regions due to over- or under-exposure, because the ZNCC\ndoes not show much difference in such areas. Hence, we obtain an additional ghost map for the low-contrast regions,\nbased on the intensity relationship between the frames. Specifically, the intensity mapping function (IMF) between the\nframes is estimated using pixels from high-contrast regions without inconsistent pixels, and pixels out of the tolerance\nrange of the IMF are considered moving pixels in the low-contrast regions. As a result, inconsistent pixels in both the\nlow- and high-contrast areas are well found, and thus, HDR images without noticeable ghosts can be obtained.
Loading....