Probabilistic motion pixel detection for the reduction of ghost artifacts in high dynamic range images from multiple exposures

Abstract

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

Exposure-Structure Blending Network for High Dynamic Range Imaging of Dynamic Scenes

“…Zhang and Cham [56] analyzed the magnitude and orientation of gradients to classify regions with and without motions. An et al [2] also attempted to find the moving regions by measuring the zero-mean normalized cross-correlation. Lee et al [30] and Oh et al [41] used rank minimization to find outlier regions, and Yan et al [55] synthesized ghost-free HDR images based on the sparse representation.…”

Depth maps and high-dynamic range image generation from alternating exposure multiview images

“…Kuk and Cho 32 proposed a novel weighted gradient domain image processing algorithm that can robustly fuse multiple exposures. An et al 33 proposed an artifact-free exposure fusion method that is based on the probabilistic motion detection by estimating intensity mapping function between frames. Hu et al 34 presented a method to align and produce an HDR image from misaligned multiexposure images.…”

High Dynamic Range Imaging Based on Bidirectional Structural Similarities and Weighted Low-Rank Matrix Completion

“…First, we propose the bidirectional structural similarities to segment an image into four groups: motion regions, saturated regions in the source image, saturated regions in the reference image, static and unsaturated regions. Similarity measurements irrelevant to luminance variation, such as local entropy [28], zero-mean normalized cross-correlation [29,30], interconsistency and intraconsistency [31], direction of the signal structure component [32], were employed to detect motion regions.…”