Topic
Channel (digital image)
About: Channel (digital image) is a research topic. Over the lifetime, 7211 publications have been published within this topic receiving 69974 citations.
Papers published on a yearly basis
Papers
More filters
TL;DR: A normalised gamma transformation-based contrast-limited adaptive histogram equalisation (CLAHE) with colour correction in Lab colour space for sand-dust image enhancement is proposed in this study and can obtain the highest percentage of new visible edges for all testing images.
Abstract: Images captured in the sand-dust weather often suffer from serious colour cast and poor contrast, and this has serious implications for outdoor computer vision systems. To address these problems, a normalised gamma transformation-based contrast-limited adaptive histogram equalisation (CLAHE) with colour correction in Lab colour space for sand-dust image enhancement is proposed in this study. This method consists of image contrast enhancement and image colour correction. To avoid producing new colour deviation, the input sand-dust images are first transformed from red, green, and blue colour space into Lab colour space. Then, the contrast of the lightness component (L channel) of the sand-dust image is enhanced using CLAHE. To avoid unbalanced contrast, as well as to reduce the overincreased brightness caused by CLAHE, a normalised gamma correction function is introduced to CLAHE. After that, the a and b chromatic components are recovered by a grey-world-based colour correction method. Experiments on real sand-dust images demonstrate that the proposed method can obtain the highest percentage of new visible edges for all testing images. The contrast restoration exhibits good colour fidelity and proper brightness.
32 citations
TL;DR: This paper reports the super-resolution reconstruction of infrared images based on a convolutional neural network with skip connections with obvious advantages in the ability of high-resolution details acquisition.
32 citations
Patent•
20 May 2002TL;DR: In this article, a method of transforming the color appearance of a plurality of digital images is proposed, where each digital image includes a pixel value relating to at least three basic colors.
Abstract: A method of transforming the color appearance of a plurality of digital images includes receiving a plurality of digital images from a capture medium wherein each digital image includes a plurality of pixel values relating to at least three basic colors; calculating a color correction transform by using a non-linear adjustment that is independent of the digital images and which corrects an under-exposure condition as a function of the capture medium; and a linear functional relationship dependent upon the pixels of the basic colors, the linear functional relationship defining an exposure-level-dependent estimate of gray corresponding to the photographic response of the capture medium; and using the color correction transform to modify the pixels of the plurality of digital images wherein the pixels within a digital image are transformed with varying degrees of color modification as a function of exposure
32 citations
22 Jul 2013-ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
TL;DR: In this paper, two new oblique camera systems are presented and the characteristics of such images are summarized, and the problems experienced in these processes and the solutions to these problems are presented.
Abstract: Oblique images enable three-dimensional (3d) modelling of objects with vertical dimensions. Such imagery is nowadays systematically taken of cities and may easily become available. The documentation of cultural heritage can take advantage of these sources of information. Two new oblique camera systems are presented and characteristics of such images are summarized. A first example uses images of a new multi-camera system for the derivation of orthoimages, facade plots with photo texture, 3d scatter plots, and dynamic 3d models of a historic church. The applied methodology is based on automatically derived point clouds of high density. Each point will be supplemented with colour and other attributes. The problems experienced in these processes and the solutions to these problems are presented. The applied tools are a combination of professional tools, free software, and of own software developments. Special attention is given to the quality of input images. Investigations are carried out on edges in the images. The combination of oblique and nadir images enables new possibilities in the processing. The use of the near-infrared channel besides the red, green, and blue channel of the applied multispectral imagery is also of advantage. Vegetation close to the object of interest can easily be removed. A second example describes the modelling of a monument by means of a non-metric camera and a standard software package. The presented results regard achieved geometric accuracy and image quality. It is concluded that the use of oblique aerial images together with image-based processing methods yield new possibilities of economic and accurate documentation of tall monuments.
32 citations
TL;DR: A novel encoder-decoder deep network architecture which exploits the several contextual frames of 2D+t sequential images in a sliding window centered at current frame to segment 2D vessel masks from the current frame is developed.
32 citations