Multivariate Alteration Detection Research Articles

Improving Unsupervised Object-Based Change Detection via Hierarchical Multi-Scale Binary Partition Tree Segmentation: A Case Study in the Yellow River Source Region

Change detection in remote sensing enables identifying alterations in surface characteristics over time, underpinning diverse applications. However, conventional pixel-based algorithms encounter constraints in terms of accuracy when applied to medium- and high-resolution remote sensing images. Although object-oriented methods offer a step forward, they frequently grapple with missing small objects or handling complex features effectively. To bridge these gaps, this paper proposes an unsupervised object-oriented change detection approach empowered by hierarchical multi-scale segmentation for generating binary ecosystem change maps. This approach meticulously segments images into optimal sizes and leverages multidimensional features to adapt the Iteratively Reweighted Multivariate Alteration Detection (IRMAD) algorithm for GaoFen WFV data. We rigorously evaluated its performance in the Yellow River Source Region, a critical ecosystem conservation zone. The results unveil three key strengths: (1) the approach achieved excellent object-level change detection results, making it particularly suited for identifying changes in subtle features; (2) while simply increasing object features did not lead to a linear accuracy gain, optimized feature space construction effectively mitigated dimensionality issues; and (3) the scalability of our approach is underscored by its success in mapping the entire Yellow River Source Region, achieving an overall accuracy of 90.09% and F-score of 0.8844. Furthermore, our analysis reveals that from 2015 to 2022, changed ecosystems comprised approximately 1.42% of the total area, providing valuable insights into regional ecosystem dynamics.

An Unsupervised Transformer-Based Multivariate Alteration Detection Approach for Change Detection in VHR Remote Sensing Images

An Unsupervised Transformer-Based Multivariate Alteration Detection Approach for Change Detection in VHR Remote Sensing Images

Semi-Supervised Detection of Detailed Ground Feature Changes and Its Impact on Land Surface Temperature

This paper presents a semi-supervised change detection optimization strategy as a means to mitigate the reliance of unsupervised/semi-supervised algorithms on pseudo-labels. The benefits of the Class-balanced Self-training Framework (CBST) and Deeplab V3+ were exploited to enhance classification accuracy for further analysis of microsurface land surface temperature (LST), as indicated by the change detection difference map obtained using iteratively reweighted multivariate alteration detection (IR-MAD). The evaluation statistics revealed that the DE_CBST optimization scheme achieves superior change detection outcomes. In comparison to the results of Deeplab V3+, the precision indicator demonstrated a 2.5% improvement, while the commission indicator exhibited a reduction of 2.5%. Furthermore, when compared to those of the CBST framework, the F1 score showed a notable enhancement of 6.3%, and the omission indicator exhibited a decrease of 8.9%. Moreover, DE_CBST optimization improves the identification accuracy of water in unchanged areas on the basis of Deeplab V3+ classification results and significantly improves the classification effect on bare land in changed areas on the basis of CBST classification results. In addition, the following conclusions are drawn from the discussion on the correlation between ground object categories and LST on a fine-scale: (1) the correlation between land use categories and LST all have good results in GTWR model fitting, which shows that local LST has a high correlation with the corresponding range of the land use category; (2) the changes of the local LST were generally consistent with the changes of the overall LST, but the evolution of the LST in different regions still has a certain heterogeneity, which might be related to the size of the local LST region; and (3) the local LST and the land use category of the corresponding grid cells did not show a completely consistent correspondence relationship. When discussing the local LST, it is necessary to consider the change in the overall LST, the land use types around the region, and the degree of interaction between surface objects. Finally, future experiments will be further explored through more time series LST and land use data.

Change detection in VHR Remote Sensing Images by automatic sample selection and progressive classification

ABSTRACT This paper proposes an automatic method for land cover change detection in very-high-spatial-resolution optical remote sensing images based on the automatic selection of training samples using expectation-maximization (EM) and an extreme learning machine classifier, which has two key characteristics: (1) combining the advantages of supervised and unsupervised methods with progressive mask classification. (2) training samples of three classes (changed, unchanged, and unknown) were automatically selected by K-Means and EM, and then further refined by the likelihood function. The method was validated by one dataset of SuperView-1 imagery with a spatial resolution of 2.0 m, two datasets of TripleSat-2 imagery with a spatial resolution of 3.2 m, and one open dataset of Zi-Yuan-3 imagery with a spatial resolution of 5.8 m, and the results were compared with that of three unsupervised methods (iterative slow feature analysis, multivariate alteration detection, and adaptive object-oriented spatial-contextual extraction algorithm), two deep learning methods (convolutional-wavelet neural networks and dual-domain networks), and three supervised classifiers (support vector machine, random forest, and Naive Bayes), showing the effectiveness of this method in decrease of false-positive rates and increase of change detection accuracy. The average and maximum of the accuracy metric F1 score of our method are 0.6842 and 0.8708, respectively; the average F1 score of the unsupervised, deep learning, and supervised methods are 0.5049, 0.4943, and 0.633, respectively.

TRACKING THE URBAN CHAMELEON – TOWARDS A HYBRID CHANGE DETECTION OF GRAFFITI

Abstract. Colourful and ever-changing: Graffiti can be considered the urban chameleon skin. At the Donaukanal (Eng. Danube Channel), Vienna's central waterway and one of the largest and most active graffiti-scapes worldwide, this metaphor applies like hardly anywhere else. Every day a multitude of graffiti is destroyed by the creation of new works. Recently, efforts have been made to mitigate this constant loss of cultural heritage along the Donaukanal by systematically documenting the graffiti, mainly using photography and photogrammetry. However, keeping track of the newly added works is very time-consuming and often like finding needles in a haystack, considering the large extent and high volatility of the monitored area. Thus, an automated graffiti change detection would significantly reduce the effort and avoid overlooking graffiti.This contribution outlines the main challenges in image-based change detection for cultural heritage and proposes a hybrid graffiti change detection method. The investigated method exploits and combines an established pixel-based change detection algorithm, the Iteratively Multivariate Alteration Detection, with a novel descriptor-based method. The latter relies on image features, rather than pixels as analysis unit and can robustly filter false alarms from the high-performing but noise-prone pixel-based approach. Overall, the results indicate that the proposed method can largely automate image-based change detection of graffiti-scapes. It can uncover graffiti-related changes and robustly distinguish them from other image differences such as shadows but tends to overlook small-scale graffiti, indicating the need for further fine-tuning.

Relaxation-Based Radiometric Normalization for Multitemporal Cross-Sensor Satellite Images

Multitemporal cross-sensor imagery is fundamental for the monitoring of the Earth’s surface over time. However, these data often lack visual consistency because of variations in the atmospheric and surface conditions, making it challenging to compare and analyze images. Various image-normalization methods have been proposed to address this issue, such as histogram matching and linear regression using iteratively reweighted multivariate alteration detection (IR-MAD). However, these methods have limitations in their ability to maintain important features and their requirement of reference images, which may not be available or may not adequately represent the target images. To overcome these limitations, a relaxation-based algorithm for satellite-image normalization is proposed. The algorithm iteratively adjusts the radiometric values of images by updating the normalization parameters (slope (α) and intercept (β)) until a desired level of consistency is reached. This method was tested on multitemporal cross-sensor-image datasets and showed significant improvements in radiometric consistency compared to other methods. The proposed relaxation algorithm outperformed IR-MAD and the original images in reducing radiometric inconsistencies, maintaining important features, and improving the accuracy (MAE = 2.3; RMSE = 2.8) and consistency of the surface-reflectance values (R2 = 87.56%; Euclidean distance = 2.11; spectral angle mapper = 12.60).

Object-Oriented Unsupervised Change Detection Based on Neighborhood Correlation Images and k-Means Clustering for the Multispectral and High Spatial Resolution Images

An unsupervised change-detection problem is formulated as a binary classification problem corresponding to the change and no change areas. This paper proposes a novel unsupervised object-oriented change detection method based on neighborhood correlation images (NCIs) and k-means clustering for high-resolution remote sensing images. We tested our proposed method in two study areas of Beijing with RapidEye images and compared it with three other popular change detection methods based on different images: change vector analysis (CVA), principal component analysis (PCA), and multivariate alteration detection (MAD). The results indicate that our method has the highest overall accuracy (90.80% in Shunyi District, Beijing and 90.40% in Daxing District, Beijing) and Kappa coefficient (0.7922 in Shunyi District, Beijing and 0.7796 in Daxing District, Beijing). In addition, the McNemar test indicates that our method is robust and stable across different study areas. We concluded that the object-oriented NCIs method outperforms traditional difference images (CVA, PCA, and MAD) in unsupervised change detection. The experimental results demonstrate the effectiveness of the proposed approach in solving the problem of unsupervised change detection for high-resolution images.

Unsupervised Change Detection of Multispectral Remote Sensing Images Based on Deep Difference Feature Variance Maximization

Remote sensing (RS) image change detection (CD) is a basic application in the military and people's livelihood. The imaging results of multitemporal and multispectral RS images have interference effects such as spectral information difference, imaging light difference, sensor noise, so the accuracy and robustness of traditional CD algorithms are restricted. In this study, we propose an unsupervised fully connected multivariate alteration detection (UFMAD) algorithm. First, UFMAD is used to extract the deep difference feature of normalized multitemporal RS images. The weighted map was obtained by using the chi-square distance of the deep difference feature and weighted with the input data. Then, the UFMAD is iteratively optimized under the three proposed constraints of variance maximization, similarity maximization, and uncorrelation of deep features. Finally, the deep feature was clustered to get the change results. By analyzing the experimental results of six advanced CD algorithms on three sets of data, the highest relative detection accuracy of UFMAD has increased by 7.0% . It is verified that the algorithm proposed in this thesis has obvious performance advantages.

EPOCH: enhanced procedure for operational change detection using historical invariant features and PCA guided multivariate statistical technique

In this article, we have presented a methodology developed for automatic historical change detection using multi-decadal time-lapse remote sensing images, which we call as EPOCH. The unpaired bi-temporal images are spatially aligned using Mode Improved Scale Invariant Feature Transform (M-SIFT) to achieve sub-pixel co-registration accuracy. The surface changes are detected using Guided Image Filter Enhanced Multivariate Alteration Detection (GIF-MAD). The guidance image is extracted using Principal Component Analysis (PCA), and an operational processing framework is devised to generate change detection map. EPOCH is evaluated with Indian Remote Sensing (IRS) images and Landsat multi-temporal images that observe Earth for more than three decades. The procedure is generalized to detect changes using different satellite images over one of our neighboring planet Mars. EPOCH is compared with state-of-the-art techniques, and found to have closest consensus with ground truth data. The proposed approach achieved an overall accuracy of 90.9% with kappa value of 0.81.

Alteration Detection of Multispectral/Hyperspectral Images Using Dual-Path Partial Recurrent Networks

Numerous alteration detection methods are designed based on image transformation algorithms and divergence of bi-temporal images. In the process of feature transformation, pseudo variant information caused by complex external factors will be highlighted. As a result, the error of divergence between the two images will be further enhanced. In this paper, we propose to fuse the variability of Deep Neural Networks’ (DNNs) structure flexibly with various detection algorithms for bi-temporal multispectral/hyperspectral imagery alteration detection. Specifically, the novel Dual-path Partial Recurrent Networks (D-PRNs) was proposed to project more accurate and effective deep features. The Unsupervised Slow Feature Analysis (USFA), Iteratively Reweighted Multivariate Alteration Detection (IRMAD), and Principal Component Analysis (PCA) were then utilized, respectively, with the proposed D-PRNs, to generate two groups of transformed features corresponding to the bi-temporal remote sensing images. We next employed the Chi-square distance to compute the divergence between two groups of transformed features and, thus, obtain the Alteration Intensity Map. Finally, threshold algorithms K-means and Otsu were, respectively, applied to transform the Alteration Intensity Map into Binary Alteration Map. Experiments were conducted on two bi-temporal remote sensing image datasets, and the testing results proved that the proposed alteration detection model using D-PRNs outperformed the state-of-the-art alteration detection model.

Assessment of Sentinel-2 Images, Support Vector Machines and Change Detection Algorithms for Bark Beetle Outbreaks Mapping in the Tatra Mountains

Cambiophagous insects, fires and windthrow cause significant forest disturbances, generating ecological changes and economical losses. The bark beetle (Ips typographus L.), inhabiting coniferous forests and eliminating weakened trees, plays a key role in posing a threat to tree stands, which are dominated by Norway spruce (Picea abies) and covers a large part of mountain areas, as well as the lowlands of Northern, Central and Eastern Europe. Due to the dynamics of the phenomena taking place, the EU recommends constant monitoring of forests in terms of large-area disturbances and factors affecting tree stands’ susceptibility to destruction. The right tools for this are multispectral satellite images, which regularly and free of charge provide up-to-date information on changes in the environment. The aim of this study was to develop a method of identifying disturbances of spruce stands, including the identification of bark beetle outbreaks. Sentinel 2 images from 2015–2018 were used for this purpose; the reference data were high-resolution aerial images, satellite WorldView 2, as well as field verification data. Support Vector Machines (SVM) distinguished six classes: deciduous forests, coniferous forests, grasslands, rocks, snags (dieback of standing trees) and cuts/windthrow. Remote sensing vegetation indices, Multivariate Alteration Detection (MAD), Multivariate Alteration Detection/Maximum Autocorrelation Factor (MAD/MAF), iteratively re-weighted Multivariate Alteration Detection (iMAD) and trained SVM signatures from another year, stacked band rasters allowed us to identify: (1) no changes; (2) dieback of standing trees; (3) logging or falling down of trees. The overall accuracy of the SVM classification oscillated between 97–99%; it was observed that in 2015–2018, as a result of the windthrow and bark beetle outbreaks and the consequences of those natural disturbances (e.g., sanitary cuts), approximately 62.5 km2 of coniferous stands (29%) died in the studied area of the Tatra Mountains.

A novel automatic method on pseudo-invariant features extraction for enhancing the relative radiometric normalization of high-resolution images

ABSTRACT Relative radiometric normalization (RRN) is a critical preprocessing step that is widely applied to remote sensing data. Essential to RRN are the pseudo-invariant features (PIFs) – ground objects with invariant reflectance across the acquisition dates of multiple images. To meet the requirements of RRN for change detection in multi-temporal images, this paper proposed a novel automatic method for PIF extraction: first, we calculated spectral, spatial, and visual features for the images. Next, a set of change vectors were generated to quantify the features’ differences. Then, the initial PIF was obtained by synthesizing similar pixels from each change vector. Finally, an iterative linear regression was performed to generate the final PIFs. Furthermore, we employed the random sample consensus (RANSAC) algorithm to establish the RRN model for normalizing the target image. The methods and workflow of PIF extraction and the RRN model establishment were validated with two TripleSat-2 multi-spectral images with a spatial resolution of 3.2 metres. The applicability of the proposed PIF extraction method was further validated by Landsat-8 OLI, GF-1 WFV, Sentinel-2 MSI, and WorldView-2 images. The results showed that: (1) The proposed PIF extraction method can automatically obtain the PIFs with high precision. Based on the extracted PIFs, the RANSAC algorithm is capable of building the RRN model with a significant linear relationship. (2) The PIF extraction method is applicable to multi-spectral images with different spatial resolutions. (3) Compared with the multivariate alteration detection (MAD) and the iteratively reweighted MAD (IR-MAD), the proposed PIF extraction method achieved a better performance in selecting the pixels with smaller radiometric differences, which is helpful to reach a higher accuracy of the RRN model. (4) Differences in image brightness, spectral domain, and spatial domain are considered in the PIF extraction method with fewer parameters and high portability. (5) Spectral features are dominant to obtain ideal PIFs, and feature combinations can get the advantages to enhance the effectiveness of the PIFs.

A Preliminary Damage Assessment Using Dual Path Synthetic Aperture Radar Analysis for the M 6.4 Petrinja Earthquake (2020), Croatia

On 29 December 2020, an earthquake with a magnitude of M 6.4 hit the central part of Croatia. The earthquake resulted in casualties and damaged buildings in the town of Petrinja (~6 km away from the epicenter) and surrounding areas. This study aims to characterize ground displacement and to estimate the location of damaged areas following the Petrinja earthquake using six synthetic aperture radar (SAR) images (C-band) acquired from both ascending and descending orbits of the Sentinel-1 mission. Phase information from both the ascending (Sentinel-1A) and descending (Sentinel-1B) datasets, acquired from SAR interferometry (InSAR), is used for estimation of ground displacement. For damage mapping, we use histogram information along with the RGB method to visualize the affected areas. In sparsely damaged areas, we also propose a method based on multivariate alteration detection (MAD) and naive Bayes (NB), in which pre-seismic and co-seismic coherence maps and geocoded intensity maps are the main independent variables, together with elevation and displacement maps. For training, approximately 70% of the data are employed and the rest of the data are used for validation. The results show that, despite the limitations of C-band SAR images in densely vegetated areas, the overall accuracy of MAD+NB is ~68% compared with the results from the Copernicus Emergency Management Service (CEMS).

Discovering Potential Illegal Construction Within Building Roofs from UAV Images Using Semantic Segmentation and Object-Based Change Detection

A novel potential illegal construction (PIC) detection method by bitemporal unmanned aerial vehicle (UAV ) image comparison (change detection) within building roof areas is proposed. In this method, roofs are first extracted from UAV images using a depth-channel improved UNet model. A two-step change detection scheme is then implemented for PIC detection. In the change detection stage, roofs with appearance, disappearance, and shape changes are first extracted by morphological analysis. Subroof primitives are then obtained by roof-constrained image segmentation within the remaining roof areas, and object-based iteratively reweighted multivariate alteration detection (IR-MAD ) is implemented to extract the small PICs from the subroof primitives. The proposed method organically combines deep learning and object-based image analysis, which can identify entire roof changes and locate small object changes within the roofs. Experiments show that the proposed method has better accuracy compared with the other counterparts, including the original IR-MAD, change vector analysis, and principal components analysis-K-means.

BACKDATING OF INVARIANT PIXELS: COMPARISON OF ALGORITHMS FOR LAND USE AND LAND COVER CHANGE (LUCC) DETECTION IN THE SUBTROPICAL BRAZILIAN ATLANTIC FOREST

Abstract: A challenge for the use of medium spatial resolution imagery for land use change detection consists of the reduced availability of ground reference data for previous dates. This study aims to obtain invariant training points using the backdating process for supervised classification of images that have no field data available. The study area comprises 1,353 km² in Santa Catarina, southern Brazil. We compared the accuracy performance of invariant area sets (binary change maps) generated by using three methods (IR-MAD - Iteratively Reweighted Multivariate Alteration Detection, CVA - Change Vector Analysis and SGD - Spectral Gradient Difference) for two periods (2017-2011 and 2011-2006). The classification of the Landsat-5 TM image of 2006 was performed using as training data the sets of points indicated as invariant in the binary maps resulted from the three abovementioned methods. The accuracies for seven land-use classes were computed. The overall accuracy was greater (80,5% and 80,2%) when using training areas achieved by CVA and SGD, respectively than IR-MAD (76%). Were obtained accuracies greater than 80% for the forest class. The results stress that the combination of the IR-MAD and SGD is preferable since the CVA is more time consuming due to the subjective application of thresholds.

Understanding patterns of vegetation change at the Angkor World Heritage site by combining remote sensing results with local knowledge

ABSTRACT This research uses two disparate data types, quantitative bi-temporal Multivariate Alteration Detection (MAD) remote sensing with qualitative interview data, to examine the spatial and temporal relationships between patterns of vegetation change at the Angkor World Heritage site, Cambodia. The time period of the research data corresponds with periods where there were significant shifts in the regulations affecting management of the site. The findings suggest that components of change identified from MAD across different spatial and temporal scales can be translated to that observed in the field or ‘real world’. Although MAD results provide an indication of change at specific locations, the results from field investigations and interviews suggest, however, that the different forms of change identified are not always clearly understood. For example, in the case where MAD outputs and associated spectral plots suggest evidence of fire in the landscape, it is not clear whether this is the main contributor to vegetation loss at given sites. The research demonstrates that identifying patterns of vegetation change from satellite imagery is achievable using novel and largely under-utilized methods. However, understanding the forms of change and contributing factors are considerably more complex.

Object-Based Building Change Detection by Fusing Pixel-Level Change Detection Results Generated from Morphological Building Index

Change detection (CD) is an important tool in remote sensing. CD can be categorized into pixel-based change detection (PBCD) and object-based change detection (OBCD). PBCD is traditionally used because of its simple and straightforward algorithms. However, with increasing interest in very-high-resolution (VHR) imagery and determining changes in small and complex objects such as buildings or roads, traditional methods showed limitations, for example, the large number of false alarms or noise in the results. Thus, researchers have focused on extending PBCD to OBCD. In this study, we proposed a method for detecting the newly built-up areas by extending PBCD results into an OBCD result through the Dempster–Shafer (D–S) theory. To this end, the morphological building index (MBI) was used to extract built-up areas in multitemporal VHR imagery. Then, three PBCD algorithms, change vector analysis, principal component analysis, and iteratively reweighted multivariate alteration detection, were applied to the MBI images. For the final CD result, the three binary change images were fused with the segmented image using the D–S theory. The results obtained from the proposed method were compared with those of PBCD, OBCD, and OBCD results generated by fusing the three binary change images using the major voting technique. Based on the accuracy assessment, the proposed method produced the highest F1-score and kappa values compared with other CD results. The proposed method can be used for detecting new buildings in built-up areas as well as changes related to demolished buildings with a low rate of false alarms and missed detections compared with other existing CD methods.

Preliminary Selection and Characterization of Pseudo-Invariant Calibration Sites in Northwest China

Pseudo-invariant calibration sites (PICS) have been used for the radiometric calibration and stability monitoring of satellite optical sensors. Several stable PICS, such as those in the Sahara Desert in North Africa, were selected for the vicarious calibration of earth remote sensing satellites. However, the selection procedure of PICSs in the whole of Northwest China has not been fully explored before. This paper presents a novel technique for selecting PICS in Northwest China by combined using the coefficient of variation (CV) and the iteratively reweighted multivariate alteration detection (IR-MAD) technique. IR-MAD, which calculates the differences between two multispectral N-band images from the same scene acquired at different times, is used to identify no-change pixels (NCPs) of the scene through one image pair. The NCPs from IR-MAD using the long-term data of FY-3 visible infrared radiometer (VIRR) and aqua Moderate Resolution Imaging Spectroradiometer (MODIS) were aggregated into the contiguously stable sites. The traditional spatial uniformity and temporal stability from MODIS surface products were used to select the potential PICS. By combining the results of both methods, over thirty PICSs with a wider brightness range of the scene types were selected. To confirm and characterize these PICSs over Northwest China, Landsat operational land imager (OLI) high-spatial-resolution images were used to check the spatial uniformity of the selected site to determine the specific location and the size of these sites. Additionally, the surface spectral reflectance and bidirectional reflectance distribution function (BRDF) were obtained from the field campaign at Chaidamu Basin, 2018. To demonstrate the practical utilization and usability of these PICSs, they were employed in the multi-site top of atmosphere (TOA) reflectance simulation to validate the operational calibration performance of Aqua/MODIS and FY-3D/MERSI-II (Medium Resolution Spectral Imager II). The simulation results showed good consistency compared with the observations from both MODIS and MERSI-II, with a relative bias and root mean square error (RMSE) of <5% and <0.05%, respectively. These sites provide prospects for multi-site vicarious calibrations of solar reflective bands, which may help to evaluate or characterize instrumental nonlinear responses using a wider signal dynamic from the sites in different seasons.

LAND COVER MONITORING OF LAGUNA LAKE WATERSHED USING MODIS NDVI DATA

Abstract. Land use and land cover monitoring is an important component in the management of Laguna Lake watershed due to its impacts on the lake’s water quality. Due to limitations caused by cloud cover, satellite systems with limited revisit capability fail to provide sufficient data to more effectively monitor the land surface. Normalized difference vegetation index (NDVI) derived from MODIS image data were used to generate land cover maps for the years 2001, 2005, 2009, 2013, and 2017. These were produced by classifying ISODATA classes using annual NDVI profiles, which resulted in land cover classes, namely, agricultural land, built-up, forest, rangeland, water, and wetland. The resulting maps were post-processed using multi-variate alteration detection (MAD), resulting in multi-temporal land cover maps with improved overall accuracies and kappa coefficients that indicate moderate agreement with ground truth data. Spatiotemporal hot spot analysis was also performed using NDVI data from 2001 to 2017 to identify vegetation hot spot areas, where clustering of low NDVI values were observed over the years. Results showed an increasing trend in built-up areas accompanied by decreasing trends in water and wetland areas, indicating impacts caused by land reclamation and expansion of residential subdivisions near the lakeshore. The decrease in total vegetation area from 2001 to 2017 could be attributed to conversion of land to built-up surface. Vegetated areas in identified hot spots decreased from 41% in 2001 to 19% in 2017. This suggests that vegetation cover in these hot spots was converted to non-vegetated surface during the time period studied.

A RADIOMETRIC NORMALIZATION METHOD OF CONTROLLING NO-CHANGED SET (CNCS) FOR DIVERSE LANDCOVER USING MULTI-SENSOR DATA

Abstract. The accurate acquisition of land surface reflectance (SR) data determines the accuracy of ground objects recognition, classification and land surface parameter inversion using remote sensing data, which is the basis of remote sensing data application. In this study, a Control No-Changed Set (CNCS) radiometric normalization method is proposed to realize spectral information transformation of multi-sensor data, which is based on the Iteratively Reweighted Multivariate Alteration Detection (IR-MAD), and includes automatic selection and step-by-step optimization of no-change pixels. The No-Changed set (NC) is obtained by selecting the original no-change pixels between the target image and the reference image according to the linear relationship. In the obtained original no-change regions, IR-MAD rules with iterative control are used to fix the final no-change pixels, after regression modeling and calculation, the normalized images are obtained. The method is tested on multi-images from multi-sensors in three groups of experiments (GF-1 WFV and Landsat-8 OLI, GF-1 PMS and Sentinel-2 MSI, and Landsat-8 OLI and Sentinel-2 MSI) with different landcover areas. The results of radiometric normalization are evaluated qualitatively and quantitatively. The data of the three groups of experiments have a high correlation (correlation coefficient r values > 0.85), indicating that they can be used together as complementary data. The Root Mean Squared Error (RMSE) values calculate from the NC between the reference and normalized target images are much smaller than those between the reference and original target images. The radiometric colour composition effects, and the typical ground objects spectral reflective curves of the reference and normalized target images are very similar after radiometric normalization. These results indicate that the CNCS method considers the linear relationship of the no-change pixels and is effective, stable, and can be used to improve the consistency of SR of multi-images from multi-sensors.