Region segmentation is a basic and important procedure in region-based classification of remote sensing images. Compared with single-scale segmentation, multiscale segmentation can obtain different structure information and shows good performance in classification. Nonetheless, in the previous multiscale algorithms, different scales are regarded as having equal contributions to classification, thus, multiscale segmentation can contain some unsuitable scales, which affects the classification accuracy. To overcome this drawback and sufficiently utilize structural information, a weighted multiscale region-level sparse representation classification (WMRSRC) algorithm is proposed. In the WMRSRC algorithm, different weights are utilized for the region-level features of different scales. The weights are determined by the segmentation quality, which is evaluated by interregion and intraregion heterogeneity measures (Local Moran’s I and variance, respectively). Once the region weights on different scales are determined, the weighted joint sparse representation model is used to classify the multiscale regions. Through three classification experiments based on high-spatial resolution remote sensing images, we find that the proposed WMRSRC algorithm gives better results than other state-of-the-art algorithms.
Impervious surface area (ISA) plays an important role in monitoring urbanization and related environmental changes, and has become a hotspot in urban and environmental studies. Xuzhou City, located in northwest Jiangsu Province, China, is chosen as the study area, and two scenes of China-Brazil Earth Resources Satellites images and one scene of HJ-1 image are employed to estimate ISA percentage and analyze the change trend from 2001 to 2009. Using a linear spectral mixture model (LSMM) and nonlinear backpropagation neural network (BPNN) method, all pixels are decomposed to derive four fraction images representing the abundance of four endmembers: vegetation, high-albedo objects, low-albedo objects, and soil. The ISA percentage is then derived by the combination of high- and low-albedo fraction images after removing the influence of water. Some high spatial resolution images are selected to validate the ISA estimation results, and the experimental results indicate that the accuracy of BPNN is higher than LSMM. By comparing the urban ISA abundances derived by BPNN from three dates, it is found that the ISA of Xuzhou City has increased rapidly from 2001 to 2009, especially in the northeast and southeast regions, corresponding to the urban planning scheme and fast urbanization. Compared to other medium remote sensing images, the revisit cycle of HJ-1 multispectral image is only two days, demonstrating the potential of such data for ISA extraction in urbanization, disaster, and other related applications.
This paper presents a dynamic classifier selection approach for hyperspectral image classification, in which both spatial and spectral information are used to determine a pixel’s label once the remaining classified pixels’ neighborhood meets the threshold. For volumetric texture feature extraction, a volumetric gray level co-occurrence matrix is used; for spectral feature extraction, a minimum estimated abundance covariance-based band selection is used. Two hyperspectral remote sensing datasets, HYDICE Washington DC Mall and AVIRIS Indian Pines, are employed to evaluate the performance of the developed method. The classification accuracies of the two datasets are improved by 1.13% and 4.47%, respectively, compared with the traditional algorithms using spectral information. The experimental results demonstrate that the integration of spectral information with volumetric textural features can improve the classification performance for hyperspectral images.
A modified multiple endmember spectral mixture analysis (MMESMA) approach is proposed for high-spatial-resolution hyperspectral imagery in the application of impervious surface mapping. Different from the original MESMA that usually selects one endmember spectral signature for each land-cover class, the proposed MMESMA allows the selection of multiple endmember signatures for each land-cover class. It is expected that the MMESMA can better accommodate within-class variations and yield better mapping results. Various unmixing models are compared, such as the linear mixing model, linear spectral mixture analysis using the original linear mixture model, original MESMA, and support vector machine using a nonlinear mixture model. Airborne 1-m resolution HySpex and ROSIS data are used in the experiments. For HySpex data, validation based on 25-cm synchronism aerial photography shows that MMESMA performs the best, with the root-mean-squared error (RMSE) of the estimated abundance fractions being 13.20% and the correlation coefficient (R2) being 0.9656. For ROSIS data, validation based on simulation shows that MMESMA performs the best, with the RMSE of the estimated abundance fraction being 4.51% and R2 being 0.9878. These demonstrate that the proposed MMESMA can generate more reliable abundance fractions for high-spatial-resolution hyperspectral imagery, which tends to include strong within-class spectral variations.
KEYWORDS: Hyperspectral imaging, Optical engineering, Data analysis, Roads, Remote sensing, Principal component analysis, Absorption, Information science, Distance measurement, Data storage
Band clustering and selection are applied to dimensionality reduction of hyperspectral imagery. The proposed method is based on a hierarchical clustering structure, which aims to group bands using an information or similarity measure. Specifically, the distance based on orthogonal projection divergence is used as a criterion for clustering. After clustering, a band selection step is applied to select representative band to be used in the following data analysis. Different from unsupervised clustering using all the pixels or supervised clustering requiring labeled pixels, the proposed semi-supervised band clustering and selection needs class spectral signatures only. The experimental results show that the proposed algorithm can significantly outperform other existing methods with regard to pixel-based classification task.
Texture and shape analysis offer interesting possibilities to characterize the structural heterogeneity of classes in the high
spatial resolution satellite imagery. In this paper, texture features are generated based on the Gaussian Markov random
field (GMRF) model, and shape features are measured using geometric moments. Then feature selection is implemented
according to the class separability. To reduce the border blurring effect introduced by texture features, the unsupervised
classification algorithm involved ordered procedures is proposed, in which linear objects are extracted using spectral and
shape features firstly, then other objects are detected using the combination of spectral, texture, and shape features. The
proposed classification method is implemented using QuickBird imagery. For comparison, the standard K-means method
with spectral data is used as a benchmark. The experimental results show that the ordered classification method with the
combination of spectral, texture, and shape information performed better than conventional methods.
KEYWORDS: Safety, Geographic information systems, Roads, Databases, Data modeling, Analytical research, Data storage, Data backup, Data communications, Visualization
As the most important technical support to digital transportation and intelligent transportation system (ITS),
Geographical Information System (GIS) has become an important tool for traffic safety assessment, management and
accident prevention. In this paper, the key techniques, system design method and implementation strategy of Traffic
Safety Analysis and Assessment System (TSAAS) is investigated based on the integration of GIS and traffic safety
models. TSAAS takes road segment as basic units and uses node sets and directed edge sets to describe road network.
Event driven spatial data model is adopted to organize information about traffic accidents in order to link accidents with
road network data. In order to solve the problem of data storage, Microsoft SQL Server2000 is used as the basic database
platform and SuperMap SDX+ large spatial database engine is used. Traffic safety analysis modeling is usually based on
many random accident events, and the results are expressed by certain numerical criteria. Taking two typical traffic
safety models: black point model and traffic safety assessment model as examples, the integration of traffic models with
GIS is explored in detail. Finally the implementation strategy of TSAAS is investigated, and the secondary development
scheme based on ComGIS product, SuperMap Objects, is recommended.
In order to discover those significant spectral features that are of effectiveness to target identification, some Data Mining
algorithms were used to the data sets from USGS spectral library and OMIS hyperspectral remote sensing image. The
candidate feature sets were generated by traditional spectral feature extraction approaches at first, and then clustering,
statistical analysis and decision tree were used to characterized feature recognition and target identification model
design. Derivative spectrum has the superiority of enhancing the characteristic spectral features in contrast with other
algorithms. The recognition decision tree based on the knowledge and rules can identify and discriminate targets using
the discovered spectral features. The experiment showed that the proposed characterized spectral features recognition
approach based on Data Mining algorithm was suitable to hyperspectral remote sensing information processing.
Hyperspectral remote sensing is capable of reflecting the detailed spectrum of ground objects; thereby it can be used for anomaly identification, quantitative retrieval, state diagnosis and fine classification. Wavelet transformation, which is viewed as 'mathematical microscope' with the capability of multi-resolution analysis, can be used for dimensionality reduction and feature extraction to hyperspectral remote sensing data, especially feature extraction at different scales. The data sets used in this study include: spectral data of several ground objects in USGS spectral library, and spectral data of some pixels in an image captured by the airborne image spectrometer OMIS II. Spectral absorption features of ground objects are quite important for ground object recognition. Wave troughs of spectral curve, which represent strong spectral absorption at some specific wavelengths, are extracted and analyzed quantitatively using wavelet transformation. Spectral angle (SA) is selected as similarity measure indicator because of its effectiveness to hyperspectral remote sensing data. The experiment results demonstrate that multi-resolution analysis of wavelet transformation provides excellent performance in spectral feature extraction and spectral similarity measure, so it can be used to target identification and image classification effectively.
Taking Xuzhou city as an example, the urban green space categories system are established using multi-temporal/-source
remotely sensed images. After classification adopted decision tree and object-oriented methods, the urban green space
pattern changes are captured and evolution rules are analyzed based on the landscape pattern indices on the patch/class
and landscape metrics. In addition, the economic/social statistics are listed for quantitative analyzing dynamic evolution.
Finally, the all driving factors impacting urban green space pattern are analyzed using the principal component analysis.
Hyperspectral Remote Sensing (HRS) is one of the most significant recent achievements of Earth Observation Technology. Classification is the most commonly employed processing methodology. In this paper three new hyperspectral RS image classification methods are analyzed. These methods are: Object-oriented FIRS image classification, HRS image classification based on information fusion and HSRS image classification by Back Propagation Neural Network (BPNN). OMIS FIRS image is used as the example data. Object-oriented techniques have
gained popularity for RS image classification in recent years. In such method, image segmentation is used to extract the regions from the pixel information based on homogeneity criteria at first, and spectral parameters like mean vector, texture, NDVI and spatial/shape parameters like aspect ratio, convexity, solidity, roundness and orientation for each region are calculated, finally classification of the image using the region feature vectors and also using suitable
classifiers such as artificial neural network (ANN). It proves that object-oriented methods can improve classification accuracy since they utilize information and features both from the point and the neighborhood, and the processing unit is a polygon (in which all pixels are homogeneous and belong to the class). HRS image classification based on information fusion, divides all bands of the image into different groups initially, and extracts features from every group according to the properties of each group. Three levels of information fusion: data level fusion, feature level fusion and decision level fusion are used to HRS image classification. Artificial Neural Network (ANN) can perform well in RS image
classification. In order to promote the advances of ANN used for HIRS image classification, Back Propagation Neural Network (BPNN), the most commonly used neural network, is used to HRS image classification.
With the coming of age of field spectroscopy as a non-destructive means to collect information on the physiology of vegetation, there is a need for storage of signatures, and, more importantly, their metadata. Without the proper organisation of metadata, the signatures itself become limited. In order to facilitate re-distribution of data, a database for the storage & distribution of hyperspectral signatures and their metadata was designed. The database was built using open-source software, and can be used by the hyperspectral community to share their data. Data is uploaded through a simple web-based interface. The database recognizes major file-formats by ASD, GER and International Spectronics. The database source code is available for download through the hyperspectral.info web domain, and we happily invite suggestion for additions & modification for the database to be submitted through the online forums on the same website.
Spectral similarity measure plays important roles in hyperspectral Remote Sensing (RS) information processing, and it can be used to content-based hyperspectral RSimage retrieval effectively too. The applications of spectral features to Remote Sensing (RS) image retrieval are discussed by taking hyperspectral RS image as examples oriented to the demands of massive information management. It is proposed that spectral features-based image retrieval includes two modes: retrieval based on point template and facial template. Point template is used usually, for example, a spectral curve, or a pixel vector in hyperspectral RS image. One or more regions (or blocks with area shape) are given as examples in image retrieval based on facial template. The most important issues in image retrieval are spectral features extraction and spectral similarity measure. Spectral vector can be used to retrieval directly, and spectral angle and spectral information divergence (SID) are more effective than Euclidean distance and correlation coefficient in similarity measure and image retrieval. Both point and pure area template can be transformed into spectral vector and used to spectral similarity measure. In addition, the local maximum and minimum in reflection spectral curve, corresponding to reflection peak and absorption valley, can be used to retrieval also. The width, height, symmetry and power of each peak or valley can be used to encode spectral features. By comparison to three approaches for spectral absorption and reflection features matching and similarity measures, it is found that spectral absorption and reflection features are not very effective in hyperspectral RS image retrieval. Finally, a prototype system is designed, and it proves that the hyperspectral RS image retrieval based on spectral similarity measure proposed in this paper is effective and some similarity measure index including spectral angle, SID and encoding measure are suitable for image retrieval in practice.
Noises are inevitable in Hyperspectral Remote Sensing (HRS) image, it is very important to design effective filter to reduce the impacts of noises and enhance image quality and information content. Based on the characteristics of HRS image, three filtering strategies, including image dimension filtering, spectral dimension filtering and three-dimensional filtering, are proposed in this paper. The principle of image dimension filtering is similar to traditional image filtering from spatial and frequency domain. The image of each band is viewed as an independent set and filtering operation is used to it. Some filters, including mean filter, medium filter and frequency filter, are used to reduce noises in every band. The key idea of spectral dimension filtering is to take every pixel as the processing target, and the gray value (or albedo) of the pixel on all bands will form a spectral vector. Filter is used to the spectral vector of every pixel, and mean filter with different scales is tested in this paper. Three-dimension filtering is different from the former two methods by its spatial and spectral dimension processing simultaneously. It views HRS image as a large data cube with row, column and layer (band), so filter is based on data cube. In this paper the 3×3×3 cube is used as filtering template, and that means those neighbors of adjacent bands of a pixel on a given band will be used to filter, so both spatial and spectral information is considered in this new method. Finally, some examples are experimented and quality assessment of sole band, similarity measure to some pixels and other statistical indexes are used to assess the performance, and then related conclusions and suggestions are given.
Landsat TM image is the most popular and universal RS information source, and got wide uses in different fields such as resource investigating, environment monitoring, urban planning, disaster preventing and as on. Although TM image has got wide applications, its use in mining area is still in experiment and beginning stage because mining area is a kind of special and complex geographic region. One of the most important issues is to study the information charaéteristics and determine the most effective band combinations oriented to given region and task. In this paper, Xuzhou mining area, located in Northern Jiangsu Province, is taken as the studying area, and Terrestrial Surface Evolution (TSE) as the studying task. According to the specific condition of studying area, the information characteristics of each band of TM image and relations between different bands are analyzed by selecting different sampling area, and relative rules are given. After that, band combination is discussed and the information content is used as the judging rule. Because more bands will require more computer resource and is low speed and cost consuming, three-band combination is used widely. It is found that in all three-band combination schemes, the combination of Band 3, Band 4 and Band 5 is the most effective. Finally, Genetic Algorithm (GA) is used to the band selection in multi-band RS image, and it proved that GA is an effective method to determine the optimal band combination, especially for multi-spectrum and super-spectrum RS information source, and GA is also a good optimized algorithm in Geoscience.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.