Selection Of Pseudo-invariant Features Research Articles

A simple model for PIFs extraction at digital change detection approach

The radiometric normalization using pseudo-invariant features (PIFs) is one of the best methods of image-based atmospheric correction. However, one of the main challenges of this approach is the correct selection of PIFs. So far many efforts have been made to automate radiometric correction using PIFs, although the capability of all these automated methods has been proven in various studies, their application requires intermediate to advanced statistical and computational knowledge and their application is beyond the reach of most conventional remote sensing users. Therefore, in this research, a straightforward simple method is proposed based on the definition of PIFs that automatically identifies these areas and uses them on a regression procedure for automatic normalization. The study area is Hara Protection Area (the Hara international wetland), which has sub-tropical climate and due to surface homogeneity of its mangrove forests can be used as a pilot for natural, and homogeneous ecosystems such as forested areas. To create an automatic PIFs extraction in this area, initially, we masked areas that should not be in the PIFs by applying some thresholds. At this stage, water, vegetation and mountainous areas were filtered. Then, the radiometric resolution of the two different sensor images was identical, and using the differential histogram shape of the two images, unvaried areas were extracted. To validate the accuracy of the proposed method, absolute radiometric correction using atmospheric and topographic correction (ATCOR), fast line-of-sight atmospheric analysis of hypercubes (FLAASH) and atmospheric correction (ATMOSC) methods, and relative radiometric correction using both empirical line calibration method and dark object subtraction method and automatic radiometric correction using QUick atmospheric correction (QUAC) and autonomous atmospheric correction (IMAGINE AAIC) were applied on the data. The output of all atmospheric correction methods and the proposed method was applied in the image algebra change detection in the form of a difference and with a threshold of twice the standard deviation from the mean to be checked by 219 points. The results of validation and qualitative studies of the histogram comparisons proved the proper functioning of the proposed method (κ greater than 0.8), and using cross tables, the performance of the proposed method is similar to that of the empirical line calibration method (more than 76%). Finally, a few unique features in the current research proposal, including simplicity, automation, negligible systematic error, the possibility of using in a biomarker degradation warning system, the independence on the type of sensor used, distinguish it from other radiometric correction methods.

Pseudoinvariant Feature Selection Using Multitemporal MAD for Optical Satellite Images

Pseudoinvariant features (PIFs) are ground objects with invariant or near-invariant reflectance during data acquisition. The extraction of PIFs from optical satellite images generally plays a crucial role in relative radiometric normalization (RRN) and landcover change detection. Previous studies extract PIFs from bitemporal images while can generally obtain satisfactory results. However, they do not fully consider the problem of inconsistent PIF selection caused by performing pairwise PIF selection on more than two images. To decrease this inconsistency problem, a novel method called multitemporal and multivariate alteration detection (MMAD) is proposed. This method is based on a weighted generalized canonical correlation analysis, which solves canonical coefficients for multivariable and multitemporal data, thereby resulting in consistent PIF selection and RRN. In addition, a new weighting scheme based on pixel similarity, image quality, and temporal coherence is introduced into MMAD to reduce the sensitivity of PIF selection to landcover changes and to stably distinguish PIFs from non-PIFs. Qualitative and quantitative analyses of several multitemporal images acquired by Satellite Pour l’Observation de la Terre 5 are conducted to evaluate the proposed method. Experimental results demonstrate the superiority of the proposed method over related methods in terms of extracted PIF quality and radiometric consistency, particularly for image sequences with considerable landcover changes.

Spectral-consistent relative radiometric normalization for multitemporal Landsat 8 imagery

Radiometric normalization is a fundamental and important preprocessing method for remote sensing applications using multitemporal satellite images due to uncertainties of at-sensor radiances caused by different sun angles and atmospheric conditions. In case the atmospheric model and ground measurements are unavailable during data acquisitions, relative normalization is an alternative method which minimizes the radiometric differences among images without the requirement of additional information. The keys to a successful relative normalization are the selection of pseudo invariant features (PIFs) from bitemporal images and the regression of selected PIFs for transformation coefficient determination. Previous studies on transformation coefficient determination adopted band-by-band regression. These studies have obtained satisfactory normalization results; however, they have not fully considered the spectral inconsistency problem caused by individual band regression. To alleviate this problem, this study proposed a constrained orthogonal regression, which enforces pixel spectral signatures to be as consistent as possible during radiometric normalization while band regression quality is preserved. In addition, instead of selecting one of the input images as reference for radiometric transformation, a common radiometric level located between bitemporal images is selected as the reference to further reduce possible spectral inconsistency. Qualitative and quantitative analyses of several bitemporal images acquired by the Landsat 8 sensor were conducted to evaluate the proposed method with the measurements of spectral distance and similarity. The experimental results demonstrate the superiority of the proposed method to related regression and radiometric normalization methods, in terms of spectral signature consistency.

Pseudoinvariant feature selection for cross-sensor optical satellite images

Processing of multitemporal satellite images generally suffers from uncertainties caused by differences in illumination and observation angles, as well as variation in atmospheric conditions. Moreover, satellite images acquired from different sensors contain not only the uncertainties but also disparate relative spectral response. Given that radiometric calibration and correction of satellite images are difficult without ground measurements during data acquisition, this study addresses pseudoinvariant feature selection for relative radiometric normalization (RRN) that minimizes the radiometric differences among images caused by atmospheric and spectral band inconsistencies during data acquisition. The key to a successful RRN is the selection of pseudoinvariant features (PIFs) among bitemporal images. To select PIFs, multivariate alteration detection (MAD) algorithm is adopted with kernel canonical correlation analysis (KCCA) instead of canonical correlation analysis (CCA). KCCA, which assumes that the relation between at-sensor radiance is spatially nonlinear, can obtain more appropriate PIFs for cross-sensor images than that of CCA, which assumes that the relation between the at-sensor radiances of bitemporal image is spatially linear. In addition, a regularization term is added to the optimization of KCCA to avoid trivial solutions and overfitting. Qualitative and quantitative analyses on bitemporal images acquired by Landsat-7 enhanced thematic mapper plus and Landsat-8 operational and imager sensors were conducted to evaluate the proposed method. The experimental results demonstrate the superiority of the proposed KCCA-based MAD to the CCA-based MAD in terms of PIF selection, particularly for images containing significant cloud covers.

Pseudo-Invariant Feature Selection for Crosssensor Optical Satellite Images

Processing of multitemporal satellite images generally suffers from uncertainties caused by differences in illumination and observation angles, as well as variation in atmospheric conditions. Moreover, satellite images acquired from different sensors contain not only the uncertainties but disparate relative spectral response. Given that radiometric calibration and correction of satellite images are difficult without ground measurements during data acquisition, this study addresses pseudo-invariant feature selection for relative radiometric normalization (RRN) that minimizes the radiometric differences among images caused by atmospheric and spectral band inconsistencies during data acquisition. The key to a successful RRN is the selection of pseudo-invariant features (PIFs) among bitemporal images. To select PIFs, multivariate alteration detection (MAD) algorithm is adopted with kernel canonical correlation analysis (KCCA) instead of canonical correlation analysis (CCA). KCCA, which assumes that the relation between at-sensor radiance is spatially nonlinear, can obtain more appropriate PIFs for cross-sensor images than that of CCA, which assumes that the relation between the at-sensor radiances of bitemporal image is spatially linear. In addition, a regularization term is added to the optimization of KCCA to avoid trivial solutions and overfitting. Qualitative and quantitative analyses on bitemporal images acquired by Landsat-7 Enhanced Thematic Mapper Plus and Landsat-8 Operational and Imager sensors were conducted to evaluate the proposed method. The experimental results demonstrate the superiority of the proposed KCCA based MAD to the CCA-based MAD in terms of PIF selection, particularly for images containing significant cloud

Radiometric Normalization of Temporal Images Combining Automatic Detection of Pseudo-Invariant Features from the Distance and Similarity Spectral Measures, Density Scatterplot Analysis, and Robust Regression

Radiometric precision is difficult to maintain in orbital images due to several factors (atmospheric conditions, Earth-sun distance, detector calibration, illumination, and viewing angles). These unwanted effects must be removed for radiometric consistency among temporal images, leaving only land-leaving radiances, for optimum change detection. A variety of relative radiometric correction techniques were developed for the correction or rectification of images, of the same area, through use of reference targets whose reflectance do not change significantly with time, i.e., pseudo-invariant features (PIFs). This paper proposes a new technique for radiometric normalization, which uses three sequential methods for an accurate PIFs selection: spectral measures of temporal data (spectral distance and similarity), density scatter plot analysis (ridge method), and robust regression. The spectral measures used are the spectral angle (Spectral Angle Mapper, SAM), spectral correlation (Spectral Correlation Mapper, SCM), and Euclidean distance. The spectral measures between the spectra at times t1 and t2 and are calculated for each pixel. After classification using threshold values, it is possible to define points with the same spectral behavior, including PIFs. The distance and similarity measures are complementary and can be calculated together. The ridge method uses a density plot generated from images acquired on different dates for the selection of PIFs. In a density plot, the invariant pixels, together, form a high-density ridge, while variant pixels (clouds and land cover changes) are spread, having low density, facilitating its exclusion. Finally, the selected PIFs are subjected to a robust regression (M-estimate) between pairs of temporal bands for the detection and elimination of outliers, and to obtain the optimal linear equation for a given set of target points. The robust regression is insensitive to outliers, i.e., observation that appears to deviate strongly from the rest of the data in which it occurs, and as in our case, change areas. New sequential methods enable one to select by different attributes, a number of invariant targets over the brightness range of the images.

Comparison of relative radiometric normalization methods using pseudo-invariant features for change detection studies in rural and urban landscapes

Relative radiometric normalization (RRN) to remove sensor effects, solar and atmospheric variation from at-sensor radiance values is often necessary for effective detection of temporal change. Traditionally, pseudo-invariant features (PIFs) are chosen subjectively, where as an analyst manually chooses known objects, often man-made, that should not change over time. An alternative method of selecting PIFs uses a principal component analysis (PCA) to select the PIFs. We compare the two RRN methods using PIFs in multiple Landsat images of urban and rural areas in Australia. An assessment of RRN quality was conducted including measurements of slope, root mean square error, and normalized difference vegetation index. We found that in urban areas both methods performed similarly well. However, in the rural area the automated PIF selection method using a PCA performed better due to the rarity of built features that are required for the manual PIF selection. We also found that differences in performance of the manual and automated methods were dependent on the accuracy assessment method tested. We conclude with a discussion on the relative merits of different RRN methods and practical advice on how to apply the automated PIF selection method.

Radiometric correction techniques and accuracy assessment for Landsat TM data in remote forested regions

Subtle change detection analysis in remote sensing relies on some form of radiometric consistency. Radiometric correction techniques developed in previous studies often require ancillary information such as climate data, illumination geometry, ground reference data of pseudo-invariant features (PIFs), and satellite calibration data. Most studies do not have the luxury of all these data. A relative radiometric correction technique of consistent quality applicable to study areas that lack urban development has not been generally accepted by the remote sensing community. A series of Landsat-5 thematic mapper (TM) and Landsat-7 enhanced thematic mapper plus (ETM+) images spanning 18 years was obtained for a primarily forested area in central British Columbia, Canada. Different techniques of radiometric correction that do not rely on ground reference data, climate data, or the subjective selection of PIFs were assessed for these images. They included an atmospheric transfer model that requires no ancillary climate data, a simple scaling function, and two scatterplot-based regression functions. Assessment of radiometric consistency was performed qualitatively by using edge detection and quantitatively using analysis of old-growth forests in equilibrium and measures of biomass accumulation in clearcuts. For these three methods of assessment, the two scatterplot-based regression functions yielded the best radiometric fidelity. These two techniques can be completely automated and are equally applicable in any Landsat TM- or ETM-based change detection studies.

Radiometric normalization of multitemporal high-resolution satellite images with quality control for land cover change detection

The radiometric normalization of multitemporal satellite optical images of the same terrain is often necessary for land cover change detection, e.g., relative differences. In previous studies, ground reference data or pseudo-invariant features (PIFs) were used in the radiometric rectification of multitemporal images. Ground reference data are costly and difficult to acquire for most satellite remotely sensed images and the selection of PIFs is generally subjective. In addition, previous research has been focused on radiometric normalization of two images acquired on different dates. The problem of conservation of radiometric resolution in the case of radiometric normalization between more than two images has not been addressed. This article reports on a new procedure for radiometric normalization between multitemporal images of the same area. The selection of PIFs is done statistically. With quality control, principal component analysis (PCA) is used to find linear relationships between multitemporal images of the same area. The satellite images are normalized radiometrically to a common scale tied to the reference radiometric levels. The procedure ensures the conservation of radiometric resolution for the multitemporal images involved. The new procedure is applied to three Landsat-5 Thematic Mapper (TM) images from three different years (August 1986, 1987, and 1991) and of the same area. Quality control measures show that the error in radiometric consistency between the multitemporal images is reduced effectively. The Normalized Difference Vegetation Index (NDVI) is calculated using the radiometrically normalized multitemporal imagery and assessed in the context of land cover change analysis.