Reduction of ghost effect in exposure fusion by detecting the ghost pixels in saturated and non-saturated regions

An, Jaehyun; Ha, Seong Jong; Cho, Nam Ik

doi:10.1109/icassp.2012.6288079

Cited by 8 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the previous section, we have seen that each of the steps provides a less noisy and/or more plausible ghost map than the hard thresholding methods [26,29]. In this section, we compare the accuracy of the overall ghost map g = g w ∪ g l with those of the existing methods.…”

Section: Resultsmentioning

confidence: 98%

“…When a pixel in the ghost map is 1, the corresponding pixel in the input frame will be included in the fusion process and vice versa. The proposed method begins by finding the reference frame that has the largest well-contrasted region (i.e., smallest saturated region) as in conventional methods [16,[24][25][26]29,30]. It needs to be noted that our method identifies the inconsistent pixels in high-contrast regions and low-contrast regions separately.…”

Section: Proposed Algorithmmentioning

confidence: 99%

“…Then, minimizing the total energy by graph cuts gives a binary map g l for the given input frame. Figure 6 compares the binary maps that represent ghost pixels as black, which are generated by hard thresholding method [29] and the proposed optimization method. Figure 6a,b shows the reference image and a differently exposed image, respectively, and Figure 6c,d shows the ghost maps of the thresholding and probabilistic methods, respectively.…”

Section: Construction Of G Lmentioning

confidence: 99%

See 2 more Smart Citations

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

Cho

2014

J Image Video Proc

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 98%

Section: Proposed Algorithmmentioning

confidence: 99%

Section: Construction Of G Lmentioning

confidence: 99%

See 1 more Smart Citation

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

Cho

2014

J Image Video Proc

Self Cite

View full text Add to dashboard Cite

show abstract

“…For some examples, Jacobs et al [20] computed the local entropy of input images to detect regions with motions. Heo et al [16] and An et al [1], [3] computed the correlation between the images to reject the moving regions. Zhang and Cham [56] analyzed the magnitude and orientation of gradients to classify regions with and without motions.…”

Section: Related Workmentioning

confidence: 99%

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

2020

Self Cite

View full text Add to dashboard Cite

This paper presents a deep end-to-end network for high dynamic range (HDR) imaging of dynamic scenes with background and foreground motions. Generating an HDR image from a sequence of multi-exposure images is a challenging process when the images have misalignments by being taken in a dynamic situation. Hence, recent methods first align the multi-exposure images to the reference by using patch matching, optical flow, homography transformation, or attention module before the merging. In this paper, we propose a deep network that synthesizes the aligned images as a result of blending the information from multi-exposure images, because explicitly aligning photos with different exposures is inherently a difficult problem. Specifically, the proposed network generates under/over-exposure images that are structurally aligned to the reference, by blending all the information from the dynamic multiexposure images. Our primary idea is that blending two images in the deep-feature-domain is effective for synthesizing multi-exposure images that are structurally aligned to the reference, resulting in betteraligned images than the pixel-domain blending or geometric transformation methods. Specifically, our alignment network consists of a two-way encoder for extracting features from two images separately, several convolution layers for blending deep features, and a decoder for constructing the aligned images. The proposed network is shown to generate the aligned images with a wide range of exposure differences very well and thus can be effectively used for the HDR imaging of dynamic scenes. Moreover, by adding a simple merging network after the alignment network and training the overall system end-to-end, we obtain a performance gain compared to the recent state-of-the-art methods.

show abstract

“…This technique indeed widens the dynamic range for the static scene. However, it suffers from ghost artifacts caused by moving objects and/or moving camera while capturing the scene, and thus needs complicated post-processing to remove the ghosts [23][24][25][26]. On the other hand, the space-division multiplexing methods using multiple sensors do not have ghost artifact problem, but they need complicated registration and interpolation process to match the view differences between the sensors [27].…”

Section: Introductionmentioning

confidence: 99%

Generation of high dynamic range illumination from a single image for the enhancement of undesirably illuminated images

Park

Soh

Cho

2019

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

This paper presents an algorithm that enhances undesirably illuminated images by generating and fusing multi-level illuminations from a single image. The input image is first decomposed into illumination and reflectance components by using an edge-preserving smoothing filter. Then the reflectance component is scaled up to improve the image details in bright areas. The illumination component is scaled up and down to generate several illumination images that correspond to certain camera exposure values different from the original. The virtual multi-exposure illuminations are blended into an enhanced illumination, where we also propose a method to generate appropriate weight maps for the tone fusion. Finally, an enhanced image is obtained by multiplying the equalized illumination and enhanced reflectance. Experiments show that the proposed algorithm produces visually pleasing output and also yields comparable objective results to the conventional enhancement methods, while requiring modest computational loads.

show abstract

Reduction of ghost effect in exposure fusion by detecting the ghost pixels in saturated and non-saturated regions

Cited by 8 publications

References 12 publications

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

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

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

Generation of high dynamic range illumination from a single image for the enhancement of undesirably illuminated images

Contact Info

Product

Resources

About