Super-resolution Mapping Technique Research Articles

Super-resolution for mapping the debris-covered glaciers, central Himalaya, India

New techniques are being implemented to precisely monitor the changes in debris-covered glaciers for ascertaining their response to climate change. The super-resolution mapping (SRM) technique is implemented here to provide the low-cost and fine-resolution facies maps of debris-covered glaciers in the Indian Himalayan region using coarse-resolution satellite data. The implemented SRM algorithm is capable of preserving the spatial pattern of facies on the debris-covered glacier surface. Scale factor (sf) and surface heterogeneity are two possible determinants of SRM accuracy. Larger sfs decrease the SRM accuracy and its computing efficiency, and hence optimal sfs must be selected. Higher SRM accuracies are obtained for less heterogenic glacier surfaces and vice-versa. Uncertainty in the resultant maps arises due to the underlying natural factors (shadow/clouds) and seasonal differences in the image acquisition. Temporal implementation of SRM is feasible to assess the facies variations on a debris-covered glacier surface, facilitating time- and cost-effective monitoring of its response to climate change over large areas.

Evaluation of SCATSAT-1 data for snow cover area mapping over a part of Western Himalayas

In the present work, the potential of Scatterometer Satellite (SCATSAT-1) data (operated at Ku-band 13.515 GHz) is evaluated to estimate the binary Snow Cover Maps (SCMs) over a part of the Western Himalayas, India. Three classifiers namely, K-Means Clustering (KMC), Support Vector Machine (SVM), and Linear Spectral Mixing (LSM) has been implemented on time-series backscattered dataset during the period 2017–18. Moreover, Super-Resolution Mapping (SRM) technique has also been tested over SCATSAT-1 data with the help of LSM, termed LSM-SRM. To validate the outcomes, the Normalized Difference Snow Index (NDSI) maps were generated from Landsat-8 and Moderate-resolution Imaging Spectroradiometer (MODIS) data. Experimental results have shown that LSM achieved higher accuracy (75.61–91.36%) as compared to SVM (72.07–85.71%) and KMC (71.79–85.47%). On the other hand, LSM-SRM offers better class category estimation (89.30–96.93%) as compared to LSM (75.61–91.36%) or other classifiers (71.79–85.71%). The present study investigates the sensitivity of Ku-band backscatter for snow conditions and performance analysis of geospatial techniques in the interpretation of backscatter data.

Optimizing Hopfield Neural Network for Super-Resolution Mapping

Remote sensing is a potential source of information of land covers on the surface of the Earth. Different types of remote sensing images offer different spatial resolution quality. High resolution images contain rich information, but they are expensive, while low resolution image are less detail but they are cheap. Super-resolution mapping (SRM) technique is used to enhance the spatial resolution of the low resolution image in order to produce land cover mapping with high accuracy. The mapping technique is crucial to differentiate land cover classes. Hopfield neural network (HNN) is a popular approach in SRM. Currently, numerical implementation of HNN uses ordinary differential equation (ODE) calculated with traditional Euler method. Although producing satisfactory accuracy, Euler method is considered slow especially when dealing with large data like remote sensing image. Therefore, in this paper several advanced numerical methods are applied to the formulation of the ODE in SRM in order to speed up the iterative procedure of SRM. These methods are an improved Euler, Runge-Kutta, and Adams-Moulton. Four classes of land covers such as vegetation, water bodies, roads, and buildings are used in this work. Results of traditional Euler produces mapping accuracy of 85.18% computed in 1000 iterations within 220-1020 seconds. Improved Euler method produces accuracy of 86.63% computed in a range of 60-620 iterations within 20-500 seconds. Runge-Kutta method produces accuracy of 86.63% computed in a range of 70-600 iterations within 20-400 seconds. Adams-Moulton method produces accuracy of 86.64% in a range of 40-320 iterations within 10-150 seconds.

Spatial Resolution Enhancement Mapping of Hyperspectral Image via Pixel Filling Algorithm

The classification of hyperspectral data by means of per pixel classifiers forces each mixed pixel to map onto a single class, whereas sub-pixel classifiers are incapable of spatial arrangement of the land cover classes at its sub-pixel level. Super resolution mapping technique takes advantage of fractional abundance of each pixel and its surrounding pixels to make the classified image much finer spatial resolution. The pixel to be super resolved (PTS) is divided into equal number of rows and columns, according to pre-defined zoom factor. The spatial proximity of the pixel is also considered in mapping at the sub-pixel level of the hyperspectral data. Now, each sub-pixel of the PTS is modelled as linear combination of number of sub-pixels allotted to the neighbouring pixels with pre-defined weights, and here they are 8 and 17, which directly depend upon the spatial location or proximity of the sub-pixels of PTS and neighbouring pixels. Irrespective of the sizes of the classes, all classes are treated equal while filling the sub-pixels in that PTS, which preserves small classes or targets of the image. Experiments have been carried out on a synthetic data and two hyperspectral datasets of different nature. The overall accuracy of super resolution mapping for synthetic data comes to be 96.3% for the whole image, while the accuracy for super resolved of only mixed pixels comes to be 86.3%. Further, experiments on real hyperspectral datasets have been carried out, and the overall accuracy comes to be more than 95% for both the datasets.

Improving Remote Sensing Image Super-Resolution Mapping Based on the Spatial Attraction Model by Utilizing the Pansharpening Technique

The spatial distribution information of remote sensing images can be derived by the super-resolution mapping (SRM) technique. Super-resolution mapping, based on the spatial attraction model (SRMSAM), has been an important SRM method, due to its simplicity and explicit physical meanings. However, the resolution of the original remote sensing image is coarse, and the existing SRMSAM cannot take full advantage of the spatial–spectral information from the original image. To utilize more spatial–spectral information, improving remote sensing image super-resolution mapping based on the spatial attraction model by utilizing the pansharpening technique (SRMSAM-PAN) is proposed. In SRMSAM-PAN, a novel processing path, named the pansharpening path, is added to the existing SRMSAM. The original coarse remote sensing image is first fused with the high-resolution panchromatic image from the same area by the pansharpening technique in the novel pansharpening path, and the improved image is unmixed to obtain the novel fine-fraction images. The novel fine-fraction images from the pansharpening path and the existing fine-fraction images from the existing path are then integrated to produce finer-fraction images with more spatial–spectral information. Finally, the values predicted from the finer-fraction images are utilized to allocate class labels to all subpixels, to achieve the final mapping result. Experimental results show that the proposed SRMSAM-PAN can obtain a higher mapping accuracy than the existing SRMSAM methods.

Soft-Then-Hard Super-Resolution Mapping Based on Pansharpening Technique for Remote Sensing Image

Super-resolution mapping (SRM) technique can explore the spatial distribution information of land cover classes in mixed pixels for multispectral image (MSI) or hyspectral image (HSI). Soft-then-hard super-resolution mapping (STHSRM) is an important type of SRM technique. STHSRM first utilizes the subpixel sharpening to produce the high-resolution fractional images with the soft attribute values for each subpixel and then allocates the hard class labels to each subpixel. However, due to the low resolution in the original image, the fractional images are difficult to pick up the full spatial-spectral information from the original image. In this paper, pansharpening technique is utilized in STHSRM (STHSRM-PAN) to produce the fractional images with more spatial-spectral information, which improves the mapping results. First, the original low-resolution MSI or HSI and a panchromatic image (PAN) are fused by pansharpening technique to produce the improved resolution image with the high spectral resolution of MSI or HSI and the high spatial resolution of PAN. The high-resolution fractional images with more spatial-spectral information are then obtained by unmixing the improved resolution image. Finally, the class labels are assigned to each subpixel according to the soft attribute values from the high-resolution fractional images. Comparing with the state-of-the-art STHSRM algorithms, the STHSRM-PAN shows the best performance with the percentage correctly classified and Kappa coefficient (Kappa) in the three experimental results.

Super-Resolution Mapping of Impervious Surfaces from Remotely Sensed Imagery with Points-of-Interest

The accurate mapping of impervious surfaces is of key significance for various urban applications. Usually, traditional methods extract the proportion image of impervious surfaces from remote sensing images; however, the proportion image cannot specify where the impervious surfaces spatially distribute within a pixel. Meanwhile, impervious surfaces often locate urban areas and have a strong correlation with the relatively new big (geo)data points of interest (POIs). This study, therefore, proposed a novel impervious surfaces mapping method (super-resolution mapping of impervious surfaces, SRMIS) by combining a super-resolution mapping technique and POIs to increase the spatial resolution of impervious surfaces in proportion images and determine the accurate spatial location of impervious surfaces within each pixel. SRMIS was evaluated using a 10-m Sentinel-2 image and a 30-m Landsat 8 Operational Land Imager (OLI) image of Nanjing city, China. The experimental results show that SRMIS generated satisfactory impervious surface maps with better-classified image quality and greater accuracy than a traditional hard classifier, the two existing super-resolution mapping (SRM) methods of the subpixel-swapping algorithm, or the method using both pixel-level and subpixel-level spatial dependence. The experimental results show that the overall accuracy increase of SRMIS was from 2.34% to 5.59% compared with the hard classification method and the two SRM methods in the first experiment, while the overall accuracy of SRMIS was 1.34–3.09% greater than that of the compared methods in the second experiment. Hence, this study provides a useful solution to combining SRM techniques and the relatively new big (geo)data (i.e., POIs) to extract impervious surface maps with a higher spatial resolution than that of the input remote sensing images, and thereby supports urban research.

Estimation of Water-Spread Area of Singoor Reservoir, Southern India by Super Resolution Mapping of Multispectral Satellite Images

Estimation of reservoir water-spread area is often carried out by field surveys which are cumbersome, time consuming, expensive and involves more man power. Hence, such surveys cannot be carried out periodically. To overcome this issue, satellite images are used, wherein the reservoir water-spread is estimated by conventional per-pixel classification such as the maximum likelihood and minimum distance to mean approaches that often results in inaccurate estimate of water-spread area due to the presence of mixed pixels. High cost and non-availability of high resolution images demands the use of an alternative approach that can give accurate information about the reservoir water-spread area. In this work, IRS, LISS III images of moderate (24 m) resolution were used for accurate estimation of the water-spread area of Singoor reservoir, southern India. The reservoir water-spread areas were extracted using per-pixel classification, sub-pixel classification and super resolution mapping approaches. These results were validated with the water-spread areas obtained from field data of the same dates. The error produced by the per-pixel approach was 6.66%, while it was 4.37% for the sub-pixel approach and a meagre 1.71% for the super-resolution approach. Fairly less error produced by the super resolution mapping technique implies that it is an efficient approach for accurate quantification of reservoir water-spread area. The estimated water-spread can be used in a simple volume estimation formula to estimate the capacity of the reservoir.

Fully spatially adaptive smoothing parameter estimation for Markov random field super-resolution mapping of remotely sensed images

This article presents a fully spatially adaptive Markov random field (MRF)-based super-resolution mapping (SRM) technique to produce land-cover maps at a finer spatial resolution than the original coarse-resolution image. MRF combines the spectral and spatial energies; hence, an MRF-SRM technique requires a smoothing parameter to manage the contributions of these energies. The main aim of this article is to introduce a new method called fully spatially adaptive MRF-SRM to automatically determine the smoothing parameter, overcoming limitations of the previously proposed approaches. This method estimates the number of endmembers in each image and uses them to assess the proportions of classes within each coarse pixel by a linear spectral unmixing method. Then, the real pixel intensity vectors and the local properties of each coarse pixel are used to compute the local spectral energy change matrix and the local spatial energy change matrix for each coarse pixel. Each pair of matrices represents all possible situations in spatial and spectral energy change for each coarse pixel and can be used to examine the balance between spatial and spectral energies, and hence to estimate a smoothing parameter for each coarse pixel. Thus, the estimated smoothing parameter is fully spatially adaptive with respect to real pixel spectral vectors and their local properties. The performance of this method is evaluated using two synthetic images and an EO1-ALI (The Advanced Land Imager instrument on Earth Observing-1 satellite) multispectral remotely sensed image. Our experiments show that the proposed method outperforms the state-of-the-art techniques.

Landscape heterogeneity and scale considerations for super-resolution mapping

Super-resolution mapping (SRM) is a rapidly emerging field of remote sensing that seeks to map the spatial distribution of land cover proportions resulting from soft classification techniques. Many methods have been proposed, but there has been little impetus to converge these efforts or compare the results. One reason for this lack of comparison is the issue of landscape heterogeneity and the range of scaling issues it embodies. Landscape heterogeneity refers to the complex distribution of land cover types across the landscape and the spatial patterns or spatial frequency of those land cover types. Landscape heterogeneity and the spatial patterns it produces are inherently scale-dependent while SRM is fundamentally an inverse scaling challenge being applied to real landscapes. The result is that SRM techniques developed for a particular landscape or scaling factor may not translate well when applied to other landscapes with different heterogeneity or computed for a different scaling factor. This lack of transferability due to landscape heterogeneity has largely been ignored in the literature. Heterogeneity is rarely reported in SRM studies and its behaviour across resolutions rarely integrated into SRM techniques. This article discusses the importance of heterogeneity in SRM, demonstrates how heterogeneity impacts SRM results, proposes several solutions for reporting landscape heterogeneity, and discusses the difficulties associated with incorporating heterogeneity into SRM. By highlighting the interrelatedness between landscape heterogeneity and SRM, the aim is for studies to begin reporting heterogeneity to facilitate inter-comparisons and ultimately incorporate the scale-dependency of landscape heterogeneity into SRM techniques to improve accuracy and applicability.

Improved adaptive Markov random field based super-resolution mapping for mangrove tree identification

Abstract. Traditionally, forest tree crowns are extracted using airborne or spaceborne hyper-/multi-spectral remotely sensed images or pansharpened images. However, these medium/low spatial resolution images suffer from the mixed pixel problem, and the cost to collect very high resolution image collection is high. Moreover, existing feature extraction techniques cannot extract local patterns from medium/low resolution images. Therefore, super-resolution mapping (SRM) techniques, which generate land-cover maps with finer spatial resolution than the original remotely sensed image, can be beneficial for the extraction of forest trees. The SRM methods can improve the quality of information extraction by combining spectral information and spatial context into image classification problems. In this paper we have improved an adaptive Markov random field approach for super-resolution mapping (MRF-SRM) based on spatially adaptive MRF-SPM to overcome the limitation of equal covariance matrices assumption for all classes. We applied the developed method for mangrove tree identification from multispectral image recorded by QuickBird satellite, where we generated a super-resolution map with the panchromatic image spatial resolution of 0.6 m. Moreover, the performance of the proposed technique is evaluated by employing the simulated image with different covariance matrices for each class. Our experimental results have demonstrated that the new adaptive MRF-SRM method has increased the overall accuracy by 5.1% and the termination conditions of this method were satisfied three times faster when compared to the state-of-the-art methods.

Increasing Spatial Resolution of Remotely Sensed Image using HNN Super-resolution Mapping Combined with a Forward Model

Spatial resolution of land covers from remotely sensed images can be increased using super-resolution mapping techniques for soft-classified land cover proportions. A further development of super-resolution mapping technique is downscaling the original remotely sensed image using super-resolution mapping techniques with a forward model. In this paper, the model for increasing spatial resolution of remote sensing multispectral image is tested with real SPOT 5 imagery at 10m spatial resolution for an area in Bac Giang Province, Vietnam in order to evaluate the feasibility of application of this model to the real imagery. The soft-classified land cover proportions obtained using a fuzzy c-means classification are then used as input data for a Hopfield neural network (HNN) to predict the multispectral images at sub-pixel spatial resolution. The 10m SPOT multispectral image was improved to 5m, 3,3m and 2.5m and compared with SPOT Panchromatic image at 2.5m resolution for assessment.Visually, the resulted image is compared with a SPOT 5 panchromatic image acquired at the same time with the multispectral data. The predicted image is apparently sharper than the original coarse spatial resolution image.

IMPROVING MARKOV RANDOM FIELD BASED SUPER RESOLUTION MAPPING THROUGH FUZZY PARAMETER INTEGRATION

Abstract. The objective of this study was to improve the Markov Random Field (MRF) based Super Resolution Mapping (SRM) technique to account for the vague land-cover interpretations (class mixture and the intermediate conditions) in an urban area. The algorithm has been improved to integrate the fuzzy mean and fuzzy covariance measurements, to a MRF based SRM scheme to optimize the classification results. The technique was tested on a WORLDVIEW-2 data set, acquired over a highway construction area, in Colombo, Sri Lanka. Based on the visual interpretation of the image, three major land-cover types of this area were identified for the study; those were vegetation, soil and exposed grass and impervious surface with low medium and high albedo. The membership values for each pixel were determined from training samples through Spectral Angle Mapper (SAM) technique. The compulsory fuzzy mean and the covariance measurements were derived using these membership grades, and subsequently was applied in MRF based SRM technique. The primary reference data was generated using Maximum Likelihood Classification (MLC) performed on the same data which was resampled to 1m resolution. The scale factor was set to be (S) = 2, to generate SRM of 1m resolution. The smoothening parameter (λ) which balances the prior and likelihood energy terms were tested in the range from 0.3 to 0.9. SRM were generated using fuzzy MRF and the conventional MRF models respectively. Results suggest that the fuzzy integrated model has improved the results with an overall accuracy of 85.60% and kappa value of 0.78 between the optimal results and the reference data, while in the conventional case it was 77.81% of overall accuracy with kappa being 0.65. Among the two MRF models, fuzzy parameter integrated model shows the highest agreement with class fractions from the reference image with a smallest average _MAE (MAE, Mean Absolute Error) of 0.03.

Super-resolution mapping of lakes from imagery with a coarse spatial and fine temporal resolution

The potential of super-resolution mapping (SRM) techniques for the representation of lakes was evaluated using both an established and a newly proposed method. Both super-resolution mapping techniques were typically able to provide representations that were visually and quantitatively more realistic than standard hard classifications. The new technique was able to represent more small lakes than the established technique. The results also demonstrate the value of using a time series of images as input to the super-resolution analysis, enabling researchers to usefully exploit the typically fine temporal resolution of coarse spatial resolution sensors for land cover mapping.

Super-resolution mapping using Hopfield Neural Network with panchromatic imagery

Land-cover proportions of mixed pixels can be predicted using soft classification. From the land-cover proportions, a hard land-cover map can be predicted at sub-pixel spatial resolution using super-resolution mapping techniques. It has been demonstrated that the Hopfield Neural Network (HNN) provides a suitable method for super-resolution mapping. To increase the detail and accuracy of the sub-pixel land-cover map, supplementary information at an intermediate spatial resolution can be used. In this research, panchromatic (PAN) imagery was used as an additional source of information for super-resolution mapping. Information from the PAN image was captured by a new PAN reflectance constraint in the energy function of the HNN. The value of the new PAN reflectance constraint was defined based on forward and inverse models with local end-member spectra and local convolution weighting factors. Two sets of simulated and degraded data were used to test the new technique. The results indicate that PAN imagery can be used as a source of supplementary information to increase the detail and accuracy of sub-pixel land-cover maps produced by super-resolution mapping from land-cover proportion images.

Enhanced Self-Training Superresolution Mapping Technique for Hyperspectral Imagery

An efficient superresolution technique through spatial-spectral data fusion for hyperspectral (HS) imagery is proposed in this letter. The spatial and spectral contents of an HS image are extracted using a linear mixture model and a fully constrained least squares unmixing technique. These data are then combined using a spatial correlation model through a learning-based superresolution mapping (SRM) algorithm. The proposed spatial correlation model realistically simulates a mapping model between the low-resolution (LR) HS image and its subsampled version ( LR2 HS image) to train the designed SRM algorithm for mapping from the LR to high resolution. The experiments on real HS images validate the accuracy and low complexity of the proposed autonomous technique for key information detection in HS imagery.