Loading [MathJax]/extensions/MathMenu.js
IEEE Xplore Search Results

Showing 1-25 of 2,389 resultsfor

Filter Results

Show

Results

Many remote-sensing satellites can obtain images in multispectral and panchromatic bands. By fusing low-resolution multispectral and high-resolution panchromatic images, one can obtain high-resolution multispectral images. In this paper, an image fusion algorithm based on image restoration is proposed to combine multispectral and panchromatic images. For remote-sensing satellites, the wavelength o...Show More
High-resolution satellite imagery is considered an excellent candidate for extracting information about the human activities on Earth. The information about residential development and suburban area mapping is of interest that can be obtained from these images. Shadow of structures such as man-made buildings is one of the main cues for structure detection in panchromatic high-resolution satellite ...Show More
This paper proposes a new method of fusing panchromatic and multispectral images based on NSCT and PCA. The first principle component is obtained by applying PCA on multispectral images. Then fusing the first principle component and low frequent coefficients of panchromatic images after transformed by NSCT. Substituting the fusion data performed by inverse NSCT for the first principle component an...Show More
Certain sensors such as IKONOS produce panchromatic and multispectral (MS) images at different spatial resolutions. Several efforts have been made to increase the resolution of these MS images using panchromatic image information. In this paper, we present a fast and efficient panchromatic sharpening method that accurately estimates missing high-frequency components. We also use a postprocessing t...Show More
A deep neural network (DNN)-based new pansharpening method for the remote sensing image fusion problem is proposed in this letter. Research on representation learning suggests that the DNN can effectively model complex relationships between variables via the composition of several levels of nonlinearity. Inspired by this observation, a modified sparse denoising autoencoder (MSDA) algorithm is prop...Show More
Pan-sharpening is a rapidly growing independent discipline considered with and finds many applications in several research fields. Pan-sharpening is the merger of high spec-tral resolution multispectral image and high spatial resolution panchromatic image which gives the best of both in the resultant image. This paper presents a novel pan-sharpening hybrid technique by combining Brovey with Laplac...Show More
In this paper, a low spatial resolution multispectral (LR MS) and panchromatic (PAN) image fusion method based on convolution sparse coding (CSC) is proposed to model the global structures existing in source images. In the proposed method, CSC is adopted to decompose the high frequency (HF) component properly and joint sparse prior is also used to capture the correlation in the bands of MS images....Show More
The pansharpening has been a wide area of interest during these days because of its applications in remote sensing, geoscience. Day by day it is going deep, vast and interesting as well. The concept arises due to the fact that data provided by most earth observation satellites such as Ikonos, geoeye, quickbird and wordview2 are composed of several channels of multispectral image and single channel...Show More
We describe a novel image fusion method for remote sensing based on structured dictionary learning and joint sparse representation which improves both quality and execution time. First, structured dictionaries are separately trained from the panchromatic (PAN) image and multispectral (MS) image by the double-sparsity model. Then, we use the joint sparse model to obtain the innovation components of...Show More
In this paper, we propose a novel technique for feature preserving interpolation of multi spectral (MS) images. Given an MS image and a panchromatic (PAN), high resolution MS image is obtained by estimating the details from the PAN image. We exploit the fact that the local geometry of the low resolution MS image is similar to that of the PAN image. The image features such as edges, corners, and cu...Show More
Recently, sparse coding-based image fusion methods have been developed extensively. Although most of them can produce competitive fusion results, three issues need to be addressed: 1) these methods divide the image into overlapped patches and process them independently, which ignore the consistency of pixels in overlapped patches; 2) the partition strategy results in the loss of spatial structures...Show More
Hyperspectral imagery is used for a wide variety of applications, including target detection, tracking, agricultural monitoring, and natural resources exploration. The main reason for using hyperspectral imagery is that images reveal spectral information about the scene that is not available in a single band. Unfortunately, many factors, such as the limitations of focal plane array technology, the...Show More
The adjustable image fusion methods are presented based on intensity-hue-saturation (IHS) transform and principal component analysis (PCA) transform in this paper. IHS and PCA can quickly merge huge amounts of remote sensing images and can preserve both spectral and spatial information. On the basis of summarized adjustable transform algorithm and transform processing procedure, the methods have b...Show More
One significant advantage of the deep convolutional neural networks (DCNN) is their representational ability for local complex structures. Inspired by this observation, a DCNN based residual learning model is proposed to learn a nonlinear mapping function between the high-resolution (HR) and low-resolution (LR) image patches. The DCNN is trained based on image patches, which are only sampled from ...Show More
HIS image fusion model has been widely used in the fusion of multi-spectral image with low spatial resolution and panchromatic image with high spatial resolution. In this paper, a new fusion algorithm is proposed by considering some existing problems in certain algorithms using HIS model, such as spectral distortion and sensitivity to noise. The proposed algorithm adopts gradient pyramid structure...Show More
In this paper, a novel hyperspectral (HS) image fusion method using matting model is presented. Matting model refers to each band of an HS image that can be decomposed into three components, i.e., alpha channel, spectral foreground, and spectral background. First, panchromatic (PAN) image is sharpened to enhance details, and the spatial information of each band of HS image is obtained by weighted ...Show More
The fusion of images is defined as an alignment of important information from diverse sensors using various mathematical models to generate a single compound image. The fusion of images is used for integrating the complementary multi-temporal, multi-view, and multi-sensor information into a single image with improved image quality and by keeping the integrity of essential features. It is considere...Show More
In this article, we proposed a novel image fusion method based on multiscale convolution sparse decomposition (MCSD). A unified framework based on MCSD is first utilized to decompose panchromatic (PAN) image and the spatial component of upsampled low spatial resolution multispectral (LR MS) images, which can produce the corresponding low frequencies and feature maps. By combining convolution spars...Show More
Due to the limited training data, current data-driven algorithms, including deep convolutional networks (DCNs), are susceptible to training data that cannot be applied to new data directly. Unlike existing methods that are trying to improve model generation capability using limited data, we introduce a learning-based image translation method to generate data that share the same characteristics of ...Show More
In order to effectively combine the spectral information of the multispectral (MS) image with the spatial details of the panchromatic (PAN) image and improve the fusion quality, a fusion method based on morphological operator and improved pulse coupled neural network (PCNN) in mixed multi-scale (MM) domain is proposed. Firstly, the MS and PAN images are decomposed by nonsubsampled shearlet transfo...Show More
For IKONOS imagery, both multi-spectral and panchromatic data are provided with different spatial resolutions. In order to produce multi-spectral images with high spatial resolution, a number of panchromatic sharpening methods have been developed. However, the classical methods such as IHS, PCA and Brovey transform often introduce severe color distortion due to injecting undesired low-pass compone...Show More
Cloud detection is a crucial step for automatic satellite image analysis. Some cloud detection methods exploit specially designed spectral bands, other base the detection on time series, or on the inter-band delay in push-broom satellites. Nevertheless many use cases occur where these methods do not apply. This paper describes a convolutional neural network for cloud detection in panchromatic and ...Show More
In this paper, Local Spatial Recovery Model (LSRM) between images of the same scene with different spatial resolutions is constructed and utilized in multispectral and panchromatic image fusion to propose a new algorithm (LSRM-MPF algorithm). The newly proposed fusion algorithm employs HIS Transform to separate spectral and spatial information, Redundant Wavelet Transform to separate low- and high...Show More
Image matching is an important method to collect ground control points (GCPs) by finding correspondence between incoming images and chips of reference image maps. It is an essential process for automated precise geo-registration of satellite imagery. To get higher georeferencing accuracy, reference chips must be matched precisely on the images. The importance of higher matching success rate is inc...Show More
A new hyperspectral (HS) pansharpening method based on guided filter is proposed in this letter. The proposed method, which obtains the spatial detail difference of each band successively, is different from the traditional component substitution method. The detail information of each band is extracted at first. Then, the panchromatic (PAN) image is sharpened to enhance the details. The spatial inf...Show More