Abstract
The field of high dynamic range (HDR) imaging deals with capturing the luminance of a natural scene, usually varying between 10−3 to 105 cd/m2 and displaying it on digital devices with much lower dynamic range. Here, we present a novel tone mapping algorithm that is based on K-means clustering. Our algorithm takes into account the color information within a frame and using k-means clustering algorithm it builds clusters on the intensities within an image and shifts the values within each cluster to a displayable dynamic range. We also implement a scene change detection to reduce the running time of our algorithm by using the cluster information from the previous frame for frames within the same scene. To reduce the flicker effect, we proposed a new method that multiplies a leaky integer to the centroid values of our clustering results. Our algorithm runs in O( N logK + K logK ) for an image with N input luminance levels and K output levels. We also show how to extend the method to handle video input. We display that our algorithm gives comparable results to state-of-the- art tone mapping algorithms. We test our algorithm on a number of standard high dynamic range images and video sequences and provide qualitative and quantitative comparisons to a number of state-of-the-art tone mapping algorithms for videos.
Highlights
1.1 MotivationThe luminance of a natural scene often has a high dynamic range (HDR), varying between 10 3 to 105 cd/m2, that unlike digital displays can be handled by the human visual system [1]
The proposed local TM algorithm segments an image into a number of local regions according to the luminance of initial global mapping.Our algorithm consists of the following steps: 1- Finding the number of clusters used in K- means. 2- Calculating the intensity channel. 3- Taking the logarithm of intensity channel. 4- Performing K-means algorithm. 5- Adjusting the color based on K-means results. 6- Applying a Gaussian kernel for smoother local factors
We used the HDR image tool Luminance HDR [61] to do the processing for generating other methods results. [61] is an open source graphical user interface application that aims to provide a workflow for HDR imaging
Summary
2-2 Before (left) and after (right) the application of HE on an image . 7 2-3 Durand’s method [15] (shown on the top right) and Reinhard’s method viii. 3-2 (a,b) a frame of a video before tone mapping with its histogram (c,d) ix. 4-6 Frame 80 (top left) and frame 265 (top right) from Hallway video sequence. (bottom left) Mean intensity value of each frame in Hallway video sequence before and after being tone-mapped by our method. 4.2 : List of tone mapping operators included in our survey.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have