Search

Hyperspectral (HS) image change detection (CD) is an integral component of multitemporal remote-sensing (RS) Earth observation research. However, the existing HS image CD technology still has some problems, such as insufficient effective information extraction and weak correlation between shallow information and deep information, and so on. This letter proposes a new approach called attention-guided feature fusion network for multitemporal HS image CD (AgF2Net). This method is capable of efficiently retrieving and combining spatial–spectral (SS) features extracted from both shallow and deep layers of HS images, thereby enhancing the network’s capability to capture features from multitemporal HS images. The attention-guided enhanced joint feature extraction strategy is used to obtain a better change discriminative feature representation, and the multilevel features extracted from the backbone network are combined between spatial information and spectral information. The integrated channel feature fusion module (ICFFM) not only solves the problem of insufficient feature fusion at different levels, but also strengthens effective semantic information and forms features with more discriminative ability, while also realizing the advantages of multiple features and enhancing the network’s robustness and the accuracy of CD results. According to experimental results obtained from three publicly available datasets for detecting changes in HS images, the findings indicate that the proposed AgF2Net outperforms most advanced state-of-the-art (SOTA) methods. The source code of the AgF2Net will be public on https://github.com/NWH/AgF2Net. [ABSTRACT FROM AUTHOR]

The use of deep learning (DL) methods for change detection (CD) is currently dominated by supervised models that require a large number of labeled samples. However, these samples are difficult to acquire in the multitemporal case. A possible alternative is leveraging methods that exploit transfer learning for CD by reusing DL models pretrained for other tasks. However, the performance of the transfer-learning-based models decreases as much as the target images differ from the ones used for training the model. To overcome this limit, we propose an unsupervised CD method that exploits multiresolution deep feature maps derived by a convolutional autoencoder (CAE). It automatically learns spatial features from the input during the training phase without requiring any labeled data. The proposed method processes the bitemporal images to obtain and compare multiresolution bitemporal feature maps. These feature maps are then analyzed by a feature-selection technique to select the most discriminant ones. Furthermore, an aggregated multiresolution difference image is computed and used for a detail-preserving multiscale CD. In the context of this CD approach, we propose two alternative strategies to retrieve multiscale reliability maps. We tested the proposed method on bitemporal multispectral images acquired by Landsat-5 and Landsat-8 representing burned areas and Sentinel-2 images representing deforested areas. Results confirm the effectiveness of the proposed CD technique. [ABSTRACT FROM AUTHOR]

Waterleakage detection and localization in distribution networks pipelines is a challenge for utility companies. For this purpose, thermal Infrared Radiation (IR) techniques have been widely applied in the literature. However, the classical analysis of IR images has not been robust in detecting and locating leakage, due to presence of thermal anomalies such as shadows. In this study, to improve the detection and location accuracy, a digital image processing tool based on multitemporal IR is proposed. In multitemporal IR analysis, the variation of soil’s temperature due to field temperature can be obtained; and hence; estimating variations due to water leakage would be more accurate. An experimental setup was built to evaluate the proposed multitemporal IR water leak detection method. In order to consider the temporal temperature variation due to water leakage and mitigate the field temperature effects, a luminance transformation of the IRimages was introduced. To determine the temporal temperature variation of the soil’s surface due to the leakage, several metrics have been considered such as the difference, the ratio, the log-ratio and the coefficient variation (CV) images. Based on the experimental results, the log-ratio and the CVimages were the most robust metrics. Then, based on log-ratio or the CV image, a temporal variation image (TVI) that traduces the temporal IR luminance variation was introduced. The analysis of the TVI image showed that the CV image is less noisy than the log-ratio image, and can more accurately locate the leakage. Finally, based on TVI histogram, a threshold was defined to classify the TVI image into leakage/non-leakage areas. Results showed that the proposed method is capable of accurately detecting and locating water leakage, which is an improvement to the false detections of spatial thermal IR analysis.

Differential interferometric synthetic aperture radar (DInSAR) has been widely used as one of the most important technologies for determining coseismic deformation. However, DInSAR processing is often perturbed by errors including atmospheric effects and those in topographic models, SAR satellite orbits, and phase unwrapping operation. These nuisance components can degrade the accuracy of the measurements and, therefore, distort the inversion of fault slips especially for moderate earthquakes. We propose in this letter a multitemporal InSAR (MTInSAR) method aiming to accurately determine coseismic deformation. By jointly analyzing a set of preseismic SAR images and one postseismic image, the method allows effective separation of coseismic deformation from topographic and satellite orbital errors deformation based on the distinct spatio-temporal characteristics of the signals. Since the solution is achieved directly from wrapped differential phases, the retrieved deformation is also immune to phase unwrapping errors. The October 6, 2008 Mw 6.3 Dangxiong, China earthquake is studied with the proposed method as an example. The slip inverted, respectively, from the MTInSAR and DInSAR coseismic deformation measurements shows up to 34-cm differences, indicating that the topographic error and inaccurate removal of orbital errors can bias the fault slip inversion. [ABSTRACT FROM AUTHOR]

Information from polarimetric synthetic aperture radar (PolSAR) imagery has been used for detecting built-up targets in classification problems, whereas it has been poorly exploited for change detection in multitemporal images. In this letter, we proposed an unsupervised approach for the detection of built-up changed areas from multitemporal full-polSAR images. The approach is based on the automatic thresholding of a novel change index based on the joint use of polarimetric span and average-alpha multitemporal information. The index is proposed for highlighting both constructed and demolished built-up elements. The experimental results on multitemporal UAVSAR images demonstrate that the proposed approach provides high detection accuracy and effectively separates among different types of changes, which is not the case with standard methods. [ABSTRACT FROM AUTHOR]

The repetitive acquisition of airborne light detection and ranging (LiDAR) data for forest surveys is rapidly increasing, thus making possible the forest dynamic analysis. Moreover, the availability of multitemporal data enables the possibility to improve the forest attribute estimates performed at single date, especially when one LiDAR acquisition has a lower pulse density with respect to the other. This letter presents a novel approach that exploits the bitemporal data information to: 1) improve the tree detection at both dates and 2) identify forest changes at single tree level. This is done by using a novel compound approach to the detection of trees in bitemporal data based on the Bayes rule for minimum error. Significant geometric features are extracted for each candidate tree-top and are used to estimate statistical terms employed in the compound approach. The multitemporal information is considered by estimating (in an iterative way) the probabilities of transition, which takes into account the temporal dependence between the LiDAR acquisitions. The proposed approach is evaluated on multitemporal LiDAR data acquired in a coniferous forest located in the Southern Italian Alps. Experimental results confirm the effectiveness of the compound detection that increases the overall accuracy (OA) up to 8.6% with respect to the single-date detection. [ABSTRACT FROM AUTHOR]

Due to the limited number of spectral channels in multispectral remote sensing images, change information, especially the multiclass changes, may be insufficiently represented, resulting in inaccurate detection of changes. In this paper, we propose to use unsupervised band expansion techniques to generate artificial spectral and spatial bands to enhance the change representation and discrimination for change detection (CD) from multispectral images. In particular, in the proposed approach, two simple nonlinear functions, i.e., multiplication and division, are applied for spectral expansion. Multiscale morphological reconstruction is used to extend the band spatial information. The expanded band sets are then used and validated in three popular unsupervised CD techniques for solving a multiclass CD problem. Experimental results obtained on three real bitemporal multispectral remote sensing datasets confirm the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Light Detection and Ranging (LiDAR) data have been widely used to characterize the 3-D structure of the forest. However, their use in a multitemporal framework has been quite limited due to the relevant challenges introduced by the comparison of pairs of point clouds. Because of the irregular sampling of the laser scanner and the complex structure of forest areas, it is not possible to perform a point-to-point comparison between the two data. To overcome these challenges, a novel hierarchical approach to the detection of 3-D changes in forest areas is proposed. The method first detects the large changes (e.g., cut trees) by comparing the Canopy Height Models derived from the two LiDAR data. Then, according to an object-based change detection approach, it identifies the single-tree changes by monitoring both the treetop and the crown volume growth. The proposed approach can compare LiDAR data with significantly different pulse densities, thus allowing the use of many data available in real applications. Experimental results pointed out that the method can accurately detect large changes, exhibiting a low rate of false and missed alarms. Moreover, it can detect changes in terms of single-tree growth, which are consistent with the expected growth rates of the considered areas. [ABSTRACT FROM AUTHOR]

Missing data in Landsat imagery caused by cloud cover and the scan line corrector error confound analysis, and effective methods for gap filling would greatly improve the usability of these data. Several methods for gap filling Landsat data have been proposed, but they typically assume little change in the images being corrected, which is a weakness in change detection applications. We present a profile-based k-nearest-neighbor method for estimating missing spectral index data that provides accurate gap filling under both gradual and abrupt changes. The profile-based interpolator (PBI) uses a multitemporal image sequence and exploits similarities in land cover temporal profiles and spatial relationships to reliably estimate missing data. PBI uses both complete and incomplete pixel profiles to maximize information for estimation and aligns pixel profiles to the target pixel profile to minimize scale biases. For testing, we used eight-image mid-infrared bispectral index sequences from 2009 and 2014 for a study area in eastern Zambia. For ten stratified random samples (n=\mathbf{1200}), we simulated one to six missing values per pixel profile and estimated the missing values at various k$ values (5–29). Comparison of estimated with original values found results to be highly correlated ( $R^2$ of 0.95–0.72 for one to six missing values, respectively) and precise (mean absolute percent errors of 4%–8%). PBI provided comparable performance to a dictionary learning image recovery method with much better computational efficiency. PBI provides spatially and temporally consistent outputs, preserving abrupt changes in the imagery due to landscape fires even with large data gaps. [ABSTRACT FROM AUTHOR]

The new generation of satellite hyperspectral (HS) sensors can acquire very detailed spectral information directly related to land surface materials. Thus, when multitemporal images are considered, they allow us to detect many potential changes in land covers. This paper addresses the change-detection (CD) problem in multitemporal HS remote sensing images, analyzing the complexity of this task. A novel hierarchical CD approach is proposed, which is aimed at identifying all the possible change classes present between the considered images. In greater detail, in order to formalize the CD problem in HS images, an analysis of the concept of “change” is given from the perspective of pixel spectral behaviors. The proposed novel hierarchical scheme is developed by considering spectral change information to identify the change classes having discriminable spectral behaviors. Due to the fact that, in real applications, reference samples are often not available, the proposed approach is designed in an unsupervised way. Experimental results obtained on both simulated and real multitemporal HS images demonstrate the effectiveness of the proposed CD method. [ABSTRACT FROM PUBLISHER]

The analysis of multitemporal very high spatial resolution imagery is too often limited to the sole use of pixel digital numbers which do not accurately describe the observed targets between the various collections due to the effects of changing illumination, viewing geometries, and atmospheric conditions. This paper demonstrates both qualitatively and quantitatively that not only physically based quantities are necessary to consistently and efficiently analyze these data sets but also the angular information of the acquisitions should not be neglected as it can provide unique features on the scenes being analyzed. The data set used is composed of 21 images acquired between 2002 and 2009 by QuickBird over the city of Denver, Colorado. The images were collected near the downtown area and include single family houses, skyscrapers, apartment complexes, industrial buildings, roads/highways, urban parks, and bodies of water. Experiments show that atmospheric and geometric properties of the acquisitions substantially affect the pixel values and, more specifically, that the raw counts are significantly correlated to the atmospheric visibility. Results of a 22-class urban land cover experiment show that an improvement of 0.374 in terms of Kappa coefficient can be achieved over the base case of raw pixels when surface reflectance values are combined to the angular decomposition of the time series. [ABSTRACT FROM PUBLISHER]

Grasslands cover approximately 40% of the Earth's surface. Low-cost tools for inventory, management, and monitoring are needed because of their great expanse, diversity, and the importance for environmental processes. Remote sensing is a useful technique for providing accurate and reliable information for land use planning and large-scale grassland management. In the context of “GIO land” (Copernicus Initial Operations land program), which is currently contracted by the European Environment Agency, a high-resolution grassland layer of 39 European countries is being created with an overall classification accuracy of better than 80%. Since grassland canopy density, chlorophyll status, and ground cover (GC) are highly dynamic throughout the growing season, no unique spectral signature can be used to map grasslands. Therefore, it is necessary to use image time series to characterize the phenological dynamics of grasslands throughout the year in order to discriminate between grasslands and other vegetation with similar spectral responses. This paper describes an operational approach based on a multisensor concept that employs optical multitemporal and multiscale satellite imagery to generate the high-resolution pan-European grassland layer. The approach is based on the supervised decision tree classifier C5.0 in combination with previous image segmentation and seasonal statistics for various vegetation indices (VIs). Results from the grassland classification for Hungary are presented. The accuracy assessment for this classification was carried out using 328 independent sample points derived from a ground-based European field survey program (LUCAS) and current CORINE Land Cover data. The grassland classification approach is explained in detail on the example of Hungary where an overall accuracy of 92.2% has been reached. [ABSTRACT FROM PUBLISHER]

Synthetic Aperture Radar (SAR) systems represent a powerful tool to monitor floods because of their all-weather capability, the very high spatial resolution of the new generation of instruments and the short revisit time of the present and future satellite constellations. To exploit these technological advances, an accurate interpretation of the multitemporal radar signature of the flooded areas is required. Mapping flooded vegetation is a task in which the interpretation of SAR data is not straightforward and should rely on the knowledge about the radar scattering phenomena in the volume between canopy, trunks and floodwater. This paper presents a methodology aiming at mapping flooded areas with a focus on flooded vegetation; the algorithm is based on an image segmentation technique and a fuzzy logic classifier. The tuning of the parameters of the fuzzy algorithm, based on the outputs of a theoretical backscattering model, is described in detail. Ancillary data giving accurate information on land cover are also used to set the input parameters of the model. The methodology is tested on a case study regarding a flood occurred in Tuscany (Central Italy) on December 2009 monitored using COSMO-SkyMed data. The multitemporal radar signatures observed during the event are discussed; it is shown that the simulated radar measurements produced by the selected electromagnetic model agree well with actual data and help their interpretation. Furthermore, a qualitative evaluation of the produced flood maps carried out with the aid of a couple of aerial photos indicates that the proposed methodology is reliable. [ABSTRACT FROM PUBLISHER]

Phase unwrapping and integration of finite differences are key problems in several technical fields, among which is synthetic aperture radar (SAR) interferometry. In this paper, we propose a general formulation for robust and efficient integration of finite differences and for phase unwrapping, which includes standard techniques (e.g., minimum cost flow and least squares phase unwrapping) as subcases. The proposed approach allows obtaining more reliable and accurate solutions by exploiting redundant differential estimates (not only between nearest neighboring points) and multidimensional information (e.g., multitemporal). In addition, a model of the signal (e.g., multibaseline or multifrequency) or external data (e.g., GPS or leveling measurements) can be integrated. The method requires the solution of linear or quadratic programming problems, for which computationally efficient algorithms exist. The validation tests performed on real and simulated SAR data confirm the validity of the method, which was integrated in our production chain and successfully used also in massive productions. [ABSTRACT FROM AUTHOR]

By means of the permanent scatterer (PS) technique, repeated spaceborne synthetic aperture radar (SAR) images with relatively low resolution (about 25 m × 5 m for the European Remote Sensing (ERS) and Envisat satellites) can be used to estimate the displacement (1-mm precision) and 3-D location (1-m precision) of targets that show an unchanged electromagnetic signature. The main drawback of the PS technique is the limited spatial density of targets that behave coherently during the whole observation span (hundreds of PSs per square kilometer in urban site and up to few points in vegetated areas). In this paper, we describe a new approach for multitemporal analysis of SAR images that also allows extracting information from partially coherent targets. The basic idea is to loosen the restrictive conditions imposed by the PS technique. The results obtained in different test sites allowed to increase significantly the spatial coverage of the estimate of height and deformation trend, particularly in extraurban areas. [ABSTRACT FROM AUTHOR]