Search

In the application of remote sensing SAR process in Guizhou karst mountainous region, the fragmented terrain and the complicated crops lead to the unsatisfactory precision, which is caused by using the grey value of SAR image simply in the classification. The original image was processed by the FROST filtering window with 7 × 7. After computing the different window size and direction of GLCM, the different texture characteristic values of GLCM were analyzed. The results show that step size of 1 and moving window with 5 × 5 of GLCM gets the optimum characteristic value. In addition, based on the four GLCM characteristic values of each landuse types, the correlation characteristic is fluctuating and easy to distinguish. To improve the precision of SAR image target recognition ability, as the image texture feature, the correlation characteristic will take part in the classification of the whole study area. But the range of the improvement needs further research.

In this paper, a novel algorithm based on Gabor-Wavelet and SVM is proposed. Compared to other algorithms of classification, our method fully exploited the external feature of remote sensing (RS) images extracted by Gabor-Wavelet. In detail, our algorithm can be divided into the following steps. Gabor wavelet decomposition is firstly applied to the fused RS images. The experiment shows that choosing 5 frequencies and 7 phases, that is, 35 Kernel functions, may reach good performance. Then we get a feature vector with several dimensions. Considering that Gabor filtering is not a orthogonal decomposition, principle component analysis (PCA) is used to reduce redundancy. Secondly, feature vectors are divided into two parts- training set and testing set. The training set is put into SVM classifier. The effect of the algorithm for different RS image type was compared. The result shows that our method performs better with fused images, only panchromatic images or multispectral images can not provide enough information for RS image classification.

This paper proposed a texture's feature of gray-level co-occurrence matrix (GLCM) as a calibrator of the sea wave height. Texture in Synthetic Aperture Radar (SAR) images represent the surface roughness of the sea or the wave height. As an archipelago country which has 70% sea of entire region, Indonesia needs and must have early warning system to provide transportation and fisherman safety circumvent the accident. Object of research are the P band full polarization Synthetic Aperture Radar (SAR) image acquired from coastal of East Kalimantan. These polarization are; horizontal-horizontal, horizontal-vertical, vertical-horizontal and vertical-vertical. Extraction of feature is done under observation angle 0° and adjacent pixels is 1. The results showed homogeneity is a consistent and toughest feature in horizontally-vertically polarization and vertical-vertical polarization and this feature can be used as a calibrator.

There are lots of image data in the field of remote sensing, most of which have low-resolution due to the limited image sensor. The super-resolution method can effectively restore the low-resolution image to the high-resolution image. However, the existing super-resolution method has both heavy computing burden and number of parameters. For saving costs, we propose the feedback ghost residual dense network (FGRDN), which considers the feedback mechanism as the framework to attain lower features through high-level refining. Further, for feature extraction, we replace the convolution of the residual dense blocks (RDBs) with ghost modules (GMs), which can remove the redundant channels and avoid the increase of parameters along with the network depth. Finally, the spatial and channel attention module (SCM) is employed in the end of the RDB to learn more useful information from features. Compared to other SOTA lightweight algorithms, our proposed algorithm can reach convergences more rapidly with fewer parameters, and the performance of the network can be markedly enhanced on the image texture and object contour reconstruction with better peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).

The color and contrast of objects in the image will be affected by meteorological factors, especially rain and snow will block part of the image, which will change the information contained in the image. Image restoration under bad weather conditions has practical application value. At present, most of the research focuses on the removal of fog, and the research on complex rain and snow is relatively less. Rain has more prominent features in gradient domain, and it is more distinct from non-rain image texture. In this paper, Generative Adversarial Networks is used to combine the information of image in gradient domain and spatial domain to get better performance of rain removal. Gradient aided coding is used in the generator to generate depth features that are more conducive to rain removal. In the discriminator, the gradient is used as an additional input to provide more recognizable rain and non-rain information, which enhances the discriminator’s ability to distinguish the image generated by the generator and the ground truth. By modifying the network structure of the expanded spatial pyramid pooling (ASPP), the abnormal rain removal results produced by the generator are reduced. Experimental results show that the proposed method improves the performance of rain removal and the visual quality of the generated image.

Detecting the change of texture information is very important for landslide detection. In polarimetric SAR imagery, the landslides not only have typical polarimetric features but also have rich texture features. In this study, the texture feature extraction technique based on gray scale co-occurrence matrix was applied to process two SLC Sentinel-1A C-band SAR images and two COSMO-SkyMed X-band SAR images acquired before and after landslip for the landslide detection leading to the Jomda landslide event in 2018, Tibet of China and the Qinglong landslide in 2018, Guizhou of China. Several important characteristic parameters of the gray scale co-occurrence matrix were studied, and the optimal sliding window size and the optimal step size for landslide detection were obtained through rigorous analysis and comparison. The experimental results show that the analysis of the complex texture information can effectively detect the landslide in the mountain area with high accuracy.

International audience; Deforestation has become a major problem consisting of a continuous regression of forested areas in the world, and for this purpose, an efficient detection of these changes has become more than necessary. In this work, a new method for deforestation change detection is proposed. This approach is based on a supervised fusion of local texture features extracted from SAR images. ALOS PALSAR (Advanced Land Observation Satellite Phased Array type L-band Synthetic Aperture Radar) multi-temporal data have been used in this work. Normalised radar cross-section (NRCS) and polarimetric features extracted from HH and HV polarised data allowed recognising different categories of land covers termed as NRCS classification. Grey-level co-occurrence matrix (GLCM) texture features were extracted by using a different moving window sizes applied on local regions previously obtained by binarisation of the NRCS results. A total of 300 samples of regions and five GLCM characteristics have been used here. The detection of deforestation appears clearly in the resulted images with a very satisfactory precision of the reached regions, and the obtained results of the proposed supervised approach have indeed led to very good detection results of the deforestation change.

Change detection process can be considered as a classification problem, classifying the image into change and no-change classes. Change detection in remote sensing images is an active research area in applications such as disaster management, urban planning etc. Texture is an important characteristic which can be used to identify various objects or regions in an image. Texture features along with spectral and morphological operators have been shown to have a positive impact on the accuracy of change detection in remote sensing images. Haralick, 1973 defined a set of twenty eight texture features which can be extracted from any image on a block basis. This paper explores the effectiveness of various texture features in enhancing the accuracy of change detection process. In this paper we have used three sets of texture features and their impact has been analyzed, keeping all other parameters constant.

A major yet largely unsolved problem in the semantic classification of very high resolution remote sensing images is the design and selection of appropriate features. At a ground sampling distance below half a meter, fine-grained texture details of objects emerge and lead to a large intraclass variability while generally keeping the between-class variability at a low level. Usually, the user makes an educated guess on what features seem to appropriately capture characteristic object class patterns. Here, we propose to avoid manual feature selection and let a boosting classifier choose optimal features from a vast Randomized Quasi-Exhaustive (RQE) set of feature candidates directly during training. This RQE feature set consists of a multitude of very simple features that are computed efficiently via integral images inside a sliding window. This simple but comprehensive feature candidate set enables the boosting classifier to assemble the most discriminative textures at different scale levels to classify a small number of broad urban land-cover classes. We do an extensive evaluation on several data sets and compare performance against multiple feature extraction baselines in different color spaces. In addition, we verify experimentally if we gain any classification accuracy if moving from boosting stumps to trees. Cross-validation minimizes the possible bias caused by specific training/testing setups. It turns out that boosting in combination with the proposed RQE feature set outperforms all baseline features while still remaining computationally efficient. Particularly boosting trees (instead of stumps) captures class patterns so well that results suggest to completely leave feature selection to the classifier.

Feature extraction is an important method to obtain remote sensing image information. It has significant influence on recognition, analysis, matching, fusion, segmentation of remote sensing image. Image registration is usually classified into two categories: the intensity-based method and the feature-based method. The corner-point is one of the basic features of the images, which has many information and can easily be detected. In the area of remote sensing image application, two or more images are usually mosaiced as one image. According to remote sensing image matching, a method of image matching based on Harris corner-point combined with SURF algorithm is proposed in this paper. First of all, feature points are detected using Harris algorithm, that has the ability of noise immunity and stability. Then, calculating by SURF algorithm, the main directions of the feature points are determined and the feature descriptors are generated. Ratio method is used to get initial matching, and RANSAC algorithm is used to eliminate errors and achieve accurate matching. The result demonstrates that the Harris corner-point image registration described is stable and efficient. The method can be well applied in the remote sensing image processing and geometric positioning accuracy evaluation.

This paper proposes a remote sensing (RS) image retrieval scheme by using image scene semantic (SS) matching. The low-level image visual features (VFs) are first mapped into multilevel spatial semantics via VF extraction, object-based classification of support vector machines, spatial relationship inference, and SS modeling. Furthermore, a spatial SS matching model that involves the object area, attribution, topology, and orientation features is proposed for the implementation of the sample-scene-based image retrieval. Moreover, a prototype system that uses a coarse-to-fine retrieval scheme is implemented with high retrieval accuracy. Experimental results show that the proposed method is suitable for spatial SS modeling, particularly geographic SS modeling, and performs well in spatial scene similarity matching.

The UAV remote sensing images due to its access to convenient, high resolution, low cost, low risk advantage has been more widely studied and applied to various field. However, due to the characteristics of complex, gray inconsistent, the larger distortion of UAV remote sensing image texture itself, which results the extraction of its characteristics to become one of the difficulties. In this paper, we take the UAV remote sensing image as the study object, analyzes several mainstream feature extraction algorithm. Through experiments, from the aspects of extraction rate, number, stability and distribution of the features, we analyzed and compared the performance, the advantages and disadvantages of various algorithms quantitatively and qualitatively, then proposed the feature extraction strategies for UAV remote sensing image, which have important significance for processing UAV remote sensing image.

This paper proposes a novel approach for texture-based image indexing and retrieval in the scope of very high resolution (VHR) optical imagery. Our motivation is to take into account local textural features and structures inside each image to measure its similarity to other images. These local features are extracted for a set of characteristic points from the image using the local extrema-based descriptors (LED) from which the radiometric, spatial and gradient features of the local extrema pixels (i.e. maximums and minimums) are integrated to characterize local textures. Due to the fact that VHR images usually involve a variety of local textures which may weakly verify the stationarity hypothesis, an approach based on characteristic points like extrema pixels becomes relevant and effective. We perform our experimentation using texture databases extracted from VHR Pleiades images within the application of vineyard cultivation and oyster farming study. Retrieval results yielded by the proposed strategy are very promising and competitive compared to reference methods.

International audience; A new procedure is proposed for agricultural land-use mapping that addresses a known weakness of classical per-pixel methods in situations involving mixed tree crops. The proposed scheme uses a pair of very-high resolution satellite-borne panchromatic and multispectral images and integrates classification results of two parallel and independent analyses, respectively based on spectral and textural information. The multispectral image is divided into spectrally homogeneous but non-contiguous segments using unsupervised classification. In parallel, the panchromatic image is split into a grid of square blocks on which is performed a texture-driven supervised classification. Finally, the spectral and the textural classifications are fused to generate the land-use map. This method contrasts with object-based methods that sequentially perform image segmentation and classification. Results are evaluated both quantitatively and qualitatively, based on field survey ground-truth data. The quantitative assessment is presented in terms of overall accuracy (from 80% to 100% depending on the area) and Kappa coefficients. Visual comparison of the resulting map with the ground-truth is performed, with the analysis of the binary error maps. Merging spectral and textural classifications results in finer border delimitation and improves the overall classification accuracy of agricultural land-use by 27% as compared to textural classification alone.

This paper presents a novel method for extracting road from high resolution remote sensing image based on Gaussian mixture model and Markov random field (GMM-MRF) model optimized by the iterated conditional model (ICM). In this paper, we first divide remote sensing image into 3 classes by GMM-MRF texture segmentation model, and then extract road by fuzzy connectedness. Finally, we use shape features and mathematical morphology to do the post-processing to remove false alarm area. Since fuzzy connectedness lacks regional structure factors, it can not accurately describe the pixel similarity. By introducing image texture feature to the concept of fuzzy connectedness, we can establish texture fuzzy connectedness concept to make it more accurate description of the degree of association among pixels, which reflects the characteristics of the local and regional pixel similarity. Besides, our method choose only one road seed point and can achieve better road extraction effectiveness than fuzzy connectedness without using segmentation algorithms, which usually needs more than 15 seed points. Experiments show that the proposed method can effectively eliminate the non-road areas that whose characteristics are similar to road, and it can obtain better performance for road extraction from high resolution remote sensing image compared with fuzzy c-means and mathematical morphology.

This paper presents a new feature selection method which aims to effectively and efficiently map remote sensing data. An automated texture-based modelling procedure of forest structure variables is at the core of our approach. We show that texture features that are highly correlated to genuine physical parameters of forest structure have potential for building reliable classifiers. We demonstrate the effectiveness of our modelling-based texture feature selection method in performing mapping of very high resolution forest images. Our method outperforms Random Forest variable importance in terms of classification accuracy and computational complexity.

In recent years, many approaches based on mathematical morphology have been applied in remote sensing image processing. In the paper, we proposed to use attribute profiles (APs) for textural extraction to the problem of content-based image retrieval (CBIR). In particular, four different attributes of APs with multiscale were applied to spatial information description. Then, the obtained textural images were processed by Gabor filters to generate the amplitude and energy coefficients. Finally, the extracted features along with histogram and color-moments were used for retrieval. The performance of textural descriptors were evaluated based on the UC Merced Land Use -- Land Cover data set. The experimental results show that the proposed method performs better than the popular Gabor texture.

Cataloged from PDF version of article. The object-based analysis of remotely sensed imagery provides valuable spatial and structural information that is complementary to pixel-based spectral information in classi- fication. In this paper, we present novel methods for automatic object detection in high-resolution images by combining spectral information with structural information exploited by using image segmentation. The proposed segmentation algorithm uses morphological operations applied to individual spectral bands using structuring elements in increasing sizes. These operations produce a set of connected components forming a hierarchy of segments for each band. A generic algorithm is designed to select meaningful segments that maximize a measure consisting of spectral homogeneity and neighborhood connectivity. Given the observation that different structures appear more clearly at different scales in different spectral bands, we describe a new algorithm for unsupervised grouping of candidate segments belonging to multiple hierarchical segmentations to find coherent sets of segments that correspond to actual objects. The segments are modeled by using their spectral and textural content, and the grouping problem is solved by using the probabilistic latent semantic analysis algorithm that builds object models by learning the object-conditional probability distributions. The automatic labeling of a segment is done by computing the similarity of its feature distribution to the distribution of the learned object models using the Kullback–Leibler divergence. The performances of the unsupervised segmentation and object detection algorithms are evaluated qualitatively and quantitatively using three different data sets with comparative experiments, and the results show that the proposed methods are able to automatically detect, group, and label segments belonging to the same object classes.

High resolution remote sensing imagery can provide more useful information, such as spectral, shape and texture information. However, traditional pixel-based image classification approaches may suffer the increase of within-class spectral variation with improved spatial resolution. This paper presents a novel method which combines the optimal segmentation scale with Bag-of-Visual Words (BOV) representation for object-oriented classification. More precisely, an improved estimation of scale parameter (ESP) tool is adopted to determine the optimal parameters in multi-scale image segmentation. BOV is introduced to construct the midlevel representations instead of low-level features for object description. Then Support vector machine (SVM) is used for classification. And the experiments are conducted on high spatial resolution images to validate the proposed algorithm.

Several features that can be extracted from digital images of the sky and that can be useful for cloud-type classification of such images are presented. Some features are statistical measurements of image texture, some are based on the Fourier transform of the image and, finally, others are computed from the image where cloudy pixels are distinguished from clear-sky pixels. The use of the most suitable features in an automatic classification algorithm is also shown and discussed. Both the features and the classifier are developed over images taken by two different camera devices, namely, a total sky imager (TSI) and a whole sky imager (WSC), which are placed in two different areas of the world (Toowoomba, Australia; and Girona, Spain, respectively). The performance of the classifier is assessed by comparing its image classification with an a priori classification carried out by visual inspection of more than 200 images from each camera. The index of agreement is 76% when five different sky conditions are considered: clear, low cumuliform clouds, stratiform clouds (overcast), cirriform clouds, and mottled clouds (altocumulus, cirrocumulus). Discussion on the future directions of this research is also presented, regarding both the use of other features and the use of other classification techniques.

In this paper, the latest watershed segmentation process is actually found in the object feature extraction process. In the proposed method, initially the actual visual features are usually taken from the images using the spatial spectral heterogeneity method. Afterwards, the object features are usually taken from the new watershed segmentation method in which segmented objects are usually grouped with the PSO-SVM method. With PSO-SVM, the actual SVM parameters are usually optimized to achieve higher classification accuracy. Then similar scene images from the data base are usually taken from the SS modelling. A further variety of remote sensing images are utilized in the overall performance analysis process. The particular implementation benefits show the effectiveness of proposed new watershed segmentation method in RSIR and the reached advancement in sensitivity and also recall measures. Moreover, the actual overall performance of the proposed technique is actually considered by comparing with all the existing RSIR and the typical SBRSIR methods.

This work presents a novel multisensor image fusion algorithm, which extends panchrmomatic sharpening of multispectral (MS) data through intensity modulation to the integration of MS and synthetic aperture radar (SAR) imagery. The method relies on SAR texture, extracted by ratioing the despeckled SAR image to its low-pass approximation. SAR texture is used to modulate the generalized intensity (GI) of the MS image, which is given by a linear transform extending intensity-hue-saturation transform to an arbitrary number of bands. Before modulation, the GI is enhanced by injection of high-pass details extracted from the available panchrmomatic image by means of the "a/spl grave/-trous" wavelet decomposition. The texture-modulated panchrmomatic-sharpened GI replaces the GI calculated from the resampled original MS data. Then, the inverse transform is applied to obtain the fusion product. Experimental results are presented on Landsat-7 Enhanced Thematic Mapper Plus and European Remote Sensing 2 satellite images of an urban area. The results demonstrate accurate spectral preservation on vegetated regions, bare soil, and also on textured areas (buildings and road network) where SAR texture information enhances the fusion product, which can be usefully applied for both visual analysis and classification purposes.

Range and sill are two important parameters of a variogram. Their extraction usually involves experimental fitting of variograms using models specified by the analyst and requires much use of trial and error. The objective of this paper is to design an algorithm for extracting the range and sill of a variogram automatically without fitting a model. Combined with the semivariance at the lag of one pixel (/spl gamma//sub 1/), the extracted range and sill were applied to the textural classification of a panchromatic IKONOS image over Xichang, Sichuan Province, China. Results show that any of these three parameters can lead to the increase of the classification accuracy. When all three parameters were used with the raw image data, the average kappa statistic for five window sizes increased from 0.24 to 0.76, indicating promise of the range and sill in texture classification.

The aim of this work was to develop a system based on multifeature texture analysis and modular neural networks that will facilitate the automated interpretation of satellite cloud images. Such a system will provide a standardized and efficient way for classifying cloud types that can he used as an operational tool in weather analysis. A series of 98 infrared satellite images from the geostationary satellite METEOSAT7 were employed, and 366 cloud segments were labeled into six cloud types after combined agreed observations from ground and satellite. From the segmented cloud images, nine different texture feature sets (a total of 55 features) were extracted, using the following algorithms: statistical features, spatial gray-level dependence matrices, gray-level difference statistics, neighborhood gray tone difference matrix, statistical feature matrix, Laws' texture energy measures, fractals, and Fourier power spectrum. The neural network self-organizing feature map (SOFM) classifier and the statistical K-nearest neighbor (KNN) classifier were used for the classification of the cloud images. Furthermore, the classification results of the nine different feature sets were combined, improving the classification yield for the six classes, for the SOFM classifier to 61 % and for the KNN classifier to 64%. 41 11 PART I 2662 2668 Cited By :56

Development associated with oil and gas exploration has expanded rapidly in Alberta and Northwest Territories, Canada. Such explorations result in landscape disturbances including forest cuts, seismic lines, well and waste sites. This paper describes a novel methodology for automatic extraction of well sites from Landsat-5 TM imagery. The method combines pixel-based and object-based image analyses and contains three major steps: geometric enhancement, segmentation, and well site extraction. For accuracy assessment, a small part of the image was used and the results were compared against visual counting of well sites visible in the pan-sharpened image of Landsat-8 of the same area. Results show correctness, completeness and quality factors of 87.3%, 96.2%, and 83.7%, respectively

This paper presents a semi-supervised method for learning informative image representations, which is a crucial but challenging step for remote sensing image classification. More precisely, we propose to represent an image by projecting it onto an ensemble of prototype sets sampled from a Gaussian approximation of multiple feature spaces. Given a set of images with a few labeled ones, we first extract preliminary features, e.g. color and textures, to form a low-level image description. We then build an ensemble of informative prototype sets by exploiting these feature spaces with a Gaussian normal affinity. Discriminative functions are subsequently learned from the resulting prototype sets, and each image is represented by concatenating their projected values onto such prototypes for final classification. Experiments on two high-resolution remote sensing image sets demonstrate the efficiency of the proposed method on remote sensing image classification with different classifiers.

Remote sensing technology is widely used in land cover survey. In this experiment, firstly VSVI (vegetation sample-based vegetation index) method is used to extract the forests in experiment area, and then adding texture feature to distinguish the natural forest and plantation in forests class. Then average contrast of objects (ACO) method is used to determine the best scale of chessboard segmentation when classify, and classification accuracy of different scales is compared. It is proved that the optimal segmentation scale through ACO and the best classification results have certain consistency, and achieved high classification accuracy.

This study evaluates the potential of wavelet-based texture multivariate modeling for the detection of cultivated oyster fields and their differentiation from abandoned fields in Very High Resolution panchromatic PLEIADES data. The proposed models are tested in a supervised classification context using a training database composed of extracted image patches representative of the land covers of interest. The obtained classification results exhibit high detection rate for cultivated fields. Classification errors appear however in the detection of abandoned fields. These results demonstrate the interest of such model for the characterization of inter-tidal ecosystems and opens up perspectives for their use in the management of oyster farming activities.

In order to support agricultural management of vineyards, high spatial resolution remote sensing images (less than 1 meter) enables textural representation of their periodic plantation pattern which helps for delineation. Even though this texture analysis may provide highly accurate delineation of vineyards, it may be infeasible at national scale, due to the computational complexity of texture extraction. In addition, particularly for Turkey, plantation practices for vineyards deviate from common periodic pattern, which can make those textures insufficient. In this study, we used SPOT5 images to explore their capabilities for delineation of vineyard parcels, without any a priori parcel information. As the inter-row distance and the spacing between the individual vine plants are less than the used 2.5m panchromatic, which is generated from 2×5m scenes (nadir) for panchromatic and 10m (nadir) spatial resolutions for multi-spectral bands, currently used periodicity based (Fourier) texture analysis may be vague. Therefore, we used Gabor textures (with different scales and directions) to define texture characteristics at this relatively coarse resolution, and we integrated these textures with image bands (visible, near infrared and shortwave infrared) which hold the ability to spectrally distinguish the vine plants from the remaining crops. For the vineyards parcels recognition, we classified the extracted features by a recent hierarchical clustering method based on self-organizing neural networks. We compared the performance of this proposed method to the object-based image analysis (by eCognition) which depends on multi-scale image segmentation and user-defined decision rules with corresponding thresholds.

Chlorophyll fluorescent information is closely related to the vital movement of a plant, so it can be used as a probe of the natural environment so as to quickly and accurately reflect the state of the environment around plants. A studying method of the plant leaves chlorophyll fluorescence image combining with remote sensing technology is presented in this paper. The system is designed and established to obtain the fluorescence image information of different plants in different states using an Nd:YAG solid-state laser as its excitation light source and an ICCD as the experimental image detector. The image information features are analyzed with pseudo-color enhancement, image synthesis using RGB color model and other methods. The results show that the fluorescence image can effectively reflect the texture, damage as well as the physiological state of a plant leaf, which can provide technical references for the further research on the impact of the change in environmental conditions by the fluorescence characteristics of plants.

This paper presents a method for feature extraction of high resolution remote sensing image which is based on the statistical model of the marginal distribution of wavelet coefficients. First, the wavelet is used to transform high resolution remote sensing images into frequent domain. Then, Generalized Gaussian density(GGD) is used to accurately model the marginal distribution of wavelet subband coefficients (wavelet coefficients histogram) followed by the establishment of the remote sensing image texture feature vector. Finally, the Kullback Leibler distance (KLD) is computed between the texture feature vectors as similarity measurement(SM), and the output is ordered by the result of the SM. Experimental results show that this method is effective and efficient, and the image feature can be well represented by this texture feature vector. The advantage of this method is that the SM step can be computed entirely on the estimated model parameters, which has solid theoretic background, so that it can meet the requirements of the CBIR application.

ALOS/PRISM has stereo capabilities which can be used for a great number of applications and products. The possibility and need for highly accurate calibration, validation, georeferencing and 3D object reconstruction requires a sophisticated camera model, being able to deal with all aspects of linear array CCD-based imagery. With SAT-PP (satellite image precision processing) we have developed a suite of new methods and a software package, which can be used for the 3D processing of all optical linear array CCD-based satellite sensor systems. Here we will demonstrate the functionality of the automated image matcher for the generation of digital surface models (DSM) with the help of ALOS/PRISM data. First we will briefly explain the essential features of our matcher. While subpixel accuracy is possible for very well defined features the overall accuracy across all object and image features lies between 1-5 pixels, depending primarily on surface roughness, vegetation and image texture and image quality. For the validation of our procedures and the quality control of PRISM data we have installed a testfield in the Bern/Thun area of Switzerland, comprising mountainous terrain as well as towns, forestry and open areas. We also use data from other ALOS testfields, like Okazaki, Japan.

International audience; Agricultural practices are major drivers of water flows in cultivated landscapes. Especially, the spatial arrangements and connectivities of tilled/untilled fields have a strong impact onto run off and soil erosion at the landscape and watershed scales. Very high spatial resolution satellite images offer the possibility to classify tilled vs. untilled fields at a large scale. This paper compares the importance of various VHR texture features for tillage mapping. Classical texture features such as coocurrence Haralick descriptors, Gabor and SIFT-based descriptors are studied. The random forest classifier is used to assess feature importance. A 50 cm panchromatic World View-I image is used for experiments. Very good classification accuracies of 83.4 % and 94.5 % are reached.

Many methods have been recently proposed to deal with the large amount of data provided by high-resolution remote sensing technologies. Several of these methods rely on the use of image segmentation algorithms for delineating target objects. However, a common issue in geographic object-based applications is the definition of the appropriate data representation scale, a problem that can be addressed by exploiting multiscale segmentation. The use of multiple scales, however, raises new challenges related to the definition of effective and efficient mechanisms for extracting features. In this paper, we address the problem of extracting histogram-based features from a hierarchy of regions for multiscale classification. The strategy, called H-Propagation, exploits the existing relationships among regions in a hierarchy to iteratively propagate features along multiple scales. The proposed method speeds up the feature extraction process and yields good results when compared with global low-level extraction approaches.

In our work we analyse fractal and multifractal characteristics for description and extraction of information from very high spatial resolution satellite images. In particular, we propose the degree of multifractality as a parameter for extraction of four land cover types and investigate its usefulness in comparison with the fractal dimension. Results show that degree of multifractality designated for individual fragments of images differs depending on the present land cover type. The highest multifractality level is observed for urban area, the lowest for water, which can be treated as a monofractal. In general multifractal parameter allows for automatic assignment of land cover types to specific classes. Some deviations take place in case of discrimination between agricultural areas and forests. This problem is also considered by using additional measures during the process of multifractal parameter computation. Conducted analysis shows that multifractal formalism creates additional possibilities for the description and automatic classification of satellite images.

A novel, simple, yet effective texture extraction method for high resolution remote sensing imagery classification based on visual words co-occurrence matrix is proposed in this paper. First, Local texture is represented by compressed texton learned from raw image patch with a sorting scheme and random projection. Then the sorted visual words co-occurrence matrix obtained with dictionary learning and nearest neighbor encoding is used for representing global texture. Finally, the support vector machine is applied for classification. Two imagery from Pavia city of Italy with public ground truth dataset are used in our experiments. The results show that the proposed method is effective and outperforms other existing methods.

Landslide is one of the most important natural disasters, which has wide distribution region, high frequencies of occurrence and fast movement speed. The landslide data have characteristic of highly nonlinear, fuzzy features and a large amount of data. In this paper, considering the characteristics of the landslide data and the shortage of SVM, the fuzzy support vector machine with textural features is introduced to identify landslide in remote sense image. By improving the fuzzy membership to overcome the influence of noise to the training process and improving the penalty coefficient to eliminate the negative impact of un-balanced sample size, the accuracy of the landslide recognition is further enhanced. Finally, the information of landslide can be extracted by using the remote sensing images of the disaster area. Using fuzzy support vector machines to extract the landslide is effectiveness and feasibility in remote sensing images, which is proved by instances.

It is generally difficult to classify an object type having different colors into the same class using only optical data such as a satellite or aerial image. This paper proposes a method that solves this problem by combining LiDAR data and an aerial image. The method extracts building pixels from LiDAR data and then identifies building objects on the aerial image by overlaying the LiDAR result to a segmented aerial image through the definite rule. This process plays a role in transforming building objects of LiDAR data to ones of the aerial image.

This paper explores different types of gray level co-occurrence matrix (GLCM) [2] texture features for automated detection of landslides on levees using remotely sensed Synthetic Aperture Radar (SAR). Two approaches of texture analysis are investigated: one based on a rubber band straightening transform (RBST) which has been used extensively in the past in the medical imaging community, and one based on the authors' developed approach of spiral straightening transform (SST). The transforms are used to project a circular region in the image to a rectangular representation where texture feature extraction can be applied. Straightforward linear discriminant analysis, for feature reduction and optimization, and maximum likelihood methods, for classification, are also utilized. The proposed system was tested on L-band SAR data with HH, HV, and VV polarizations collected from NASA's UAVSAR of the Mississippi River levee system between Vicksburg, MS and Clarksdale, MS, USA. The proposed approach is shown to detect all known levee landslides in the test area with a low number of false positives.

This paper proposes the classification framework based on the Bayesian theory with the single polarization multi-temporal synthetic aperture radar (SAR) and an optical data, and incorporates the proposed training sample selection (SS) methods. Within this framework, the combination with gray level co-occurrence matrix (GLCM)-based mean textural measure is investigated. The two procedures of the classification and proposed SS are united, where SS generates accurate and dispersed training samples. Extracted features from multi-temporal SAR data—namely, the average backscattering coefficient, backscatter temporal variability, and long-term coherence and reflectance values from optical data, are integrated with GLCM mean textural data in the framework. Classification results were generated by taking Osaka City, Japan, as the study area. The selected major classes were built-up areas, fields, woodlands, and water bodies. The most suitable data used for classification is the multi-temporal SAR and an optical data fusion with the mean textural, because of the supplement of different data used and the smoothing effect on the images of the texture. Moreover, the higher quality training samples obtained by using the combined SVM and NN-based SS method for training the Bayesian classifier generated the highest classification accuracies in all of tested cases.

Remote sensing is an effective tool in urban extent mapping and monitoring. In this study, a procedure to detect urban expansion is presented using SPOT5 panchromatic image with 2.5m resolution. First of all, the urban extents of different images are extracted with a PANTEX methodology, which use the anisotropic rotation-invariant textural grey-level co-occurrence measures as the presence of built-up areas. The change detection is performed on the two built-up index images using principal component analysis technique. Finally, the accuracy of this procedure is assessed with visual analysis results. The method shows good performance according to the overall accuracy of 91.18% (Kappa coefficient=0.8719).

In object-oriented remote sensing imagery classification, numerous spectral, texture, shape and contextual features can be derived and used to discriminate classes and produce finer map. The high-dimensional features may induce Hughes phenomenon that classification accuracy decreases with more features involved. To improve the classification accuracy and efficiency, a hybrid feature selection method combined the relative attribute reduction and the significance estimation of features is proposed. This method can efficiently select features and solve the problems of combination explosion. Object-oriented classification of Quickbird image shows the selected features can correctly distinguish most of the objects with an overall accuracy of 86%.

This paper introduces the oil spill monitoring in SAR image by texture analysis and spectral information. In texture analysis, it discusses the parameters of texture extraction, and makes experiment. Then it determines the 17*17 as the windows size, 90 as the angle and 5 as distance. Through neural network classification, these parameters are suitable for oil spill monitoring. It can distinguish with oil and oil-like well. Its accuracy is satisfactory. These parameters are not only used for oil spill monitoring, but also provide a foundation for deeper SAR image classification.

The new generation of spaceborne SAR instruments with meter or submeter resolution finds enormous applications for the observation of urban, industrial, in general of man-made scenes. Thus, targets are not any more observed in isolation, instead the groups of objects, e.g., house, bridge, and road, etc., need to be recognized in their spatial context. This paper proposes a feature extraction method for image patches in order to capture the spatial context. The method is based on the characteristics of the spectra of the SAR data, integrating radiometric, geometric, and texture properties of the SAR image patch. The method is demonstrated for TerraSAR-X High Resolution Spotlight data. To account for the spatial context in which a group of targets is located, it uses an image patch covering typically 200 × 200 m2 of the scene. A comparative evaluation of our descriptors and grey-level co-occurrence matrix (GLCM) texture features has been performed over a database of 6916 patches. The method allowed for the robust recognition of over 30 different scene classes, with precision between 50% and 93%. Numerical results show that our method is able to discriminate between scene classes better than GLCM texture parameters.

Because of the precision of the information extraction is lack. The paper is using the data source with quick-bird, processing the segmentation of high-resolution remote sensing images through the watershed algorithm of controlling marked, controlling the over-segmentation of watershed algorithm with the self-adaption space filter algorithm by matlab to attain a certain precision, to meet the need of land monitoring. To avoid the noise of spectra, we use the geometry properties, texture properties and so on to extract the features. Comparing with other classification, the object-oriented method is fast, high precision and high noise resisting. The research is important for land monitoring and GIS database updating and the rapid reaction.

High accurate airborne Light Detection and Range (LiDAR) is widely accepted as one kind of survey data sources. However, with the LiDAR products including Digital Elevation Model (DEM), Digital Surface Model (DSM) and intensity image, land use classifications and feature extractions were generally combined with optical images including satellite images or aerial photos using relative segmentations and feature extraction algorithms. In this paper, a multi-window texture classification and object-oriented feature extraction method is proposed using only airborne LiDAR products. Based on the experimental analysis and accuracy statistics, it is an efficient attempt in land cover classification with airborne LiDAR products.