Huapeng Zhang

Land Use/Cover Change in Mining Areas Using Multi-source Remotely Sensed Imagery

This paper assessed the advantages of monitoring and analyzing Land Use/Cover Change (LUCC) in mining areas via multi-source remotely sensed data. Comparing with the traditional and object-oriented classification methods, the support vector machine classifier is used to land cover classification based on Landsat TM/ETM+ and ASTER data. The landscape pattern indices on patch/class and landscape metrics are chosen to analyze and assess LUCC in mining areas and the land cover changes are derived. Finally, a framework of integrating multi-source and multi-temporal RS information for LUCC in mining areas is proposed.

Comparison of Vegetation Index from ASTER, CBERS and Landsat ETM+

Normalized difference vegetation index (NDVI), as the most important index derived from the red and near infrared spectrum scope of multi-spectral remotely sensed data, plays important roles to remote sensing applications in different fields. Three data sources operated by different vendors are chosen to compare the NDVIs derived from them and discover mutual relationships. The three sensors are ASTER, CBERS and Landsat ETM+. Before NDVIs are computed, image registration, geometric correction and atmospheric correction are conducted. The comparison is conducted from three levels: global level at the whole image scene, local level at some specific areas, and special object level by using related statistical indexes, and some useful suggestions are given based on the comparison.

On the filtering of hyperspectral remote sensing image

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.

Land cover classification in mining areas using Beijing-1 small satellite data

Land cover classification is conducted using the panchromatic and multi-spectral data of Beijing-1 small satellite data in the western part of Xuzhou coal mining area. Firstly, fusion images obtained from different pixel fusion methods are used to land cover classification using SVM classifier. Secondly, feature level fusion is implemented by extracting texture information from panchromatic data and NDVI from multi-spectral data, by which texture and spectral features form new vectors to SVM classifier. Finally, Decision level fusion is experimented by adopting Dempster-Shafer evidence theory for classifier combination. The experimental results show that the fusion of panchromatic and multi-spectral data of Beijing-1 small satellite is effective to land cover classification, and the decision level fusion algorithm outperforms other methods in terms of classification accuracy.

Performance Assessment of IHS Fusion for Remote Sensing Images Based on Multiple Attribute Decision Making

Base on the traditional IHS (Intensity-Hue-Saturation) fusion and weighted IHS fusion algorithm, the adaptive weighted IHS information fusion based on local mean is discussed in this paper. Because the advantages and disadvantages of fusion algorithm have direct influences on the effect of remote sensing information fusion, the multiple attribute decision making method is proposed for assessing fusion algorithm. Finally, the effects of the different fusion IHS algorithm for remote sensing images are assessed using the decision making method for comparing the fusion effect. It proves that the proposed multi-attribute decision-making approach performs quite well for assessing the fusion algorithms.

Analysis to Urban Landscape Pattern Change Based on Multi-Temporal CBERS Imagery

The landscape pattern change of Xuzhou city was analyzed based on multi-temporal CBERS images by quantitative analysis to landscape pattern index of Xuzhou city in 2001, 2005 and 2007. Image classification and data fusion were conducted at first, and then the multi-temporal and multi-scale data of CBERS sensors was used for landscape pattern analysis and comparison. The changes of vegetation landscape were discussed based on NDVI data as a special interest. It proves that CBERS data is suitable for urban landscape analysis as the effective complementarity of other information sources.

Monitoring urban impervious surface area change using CBERS and HJ-1 remote sensing images

Impervious surface plays an important role in monitoring urbanization and related environmental changes. CBERS and HJ-1 satellite images were employed to impervious surface extraction. Xuzhou City, located in the northwestern of Jiangsu Province, China, was chosen as the case study area. Using linear spectral mixture model (LSMM) and multi-layer perception (MLP) neural network, all pixels were decomposed to the four fraction images representing the abundance of four endmembers: vegetation, high-albedo objects, low-albedo objects and soil. Then, the impervious surface area was derived by the combination of high- and low-albedo fraction images after removing the influence of water body. Furthermore, some high spatial resolution images were selected to validate the impervious surface estimation results of the two methods. Experimental results indicate that the accuracy of MLP neural network is higher than LSMM. By comparing the urban impervious surface area based on the MLP neural network from three remote sensing images, the change pattern of impervious surface area was studied. In the past years, the impervious surface has increased rapidly in Xuzhou City, especially in the northeast and southeast regions.

A comparison and evaluation of four vegetation analysis approaches based on remote sensing imagery

Some analytical approaches have been developed and widely used for vegetation remote sensing, among which four popular methods are vegetation analysis via NDVI and other VIs, vegetation analysis using the vegetation abundance derived from unmixing, vegetation analysis by land cover classification, and the greenness component derived from K-T transform. There four approaches are used to extract vegetation information from Landsat TM image taking Xuzhou City as an example, and their performance is compared. Association analysis among vegetation types, NDVI values, vegetation abundance and greenness is conducted at first. It is found that the association among NDVI, vegetation abundance and greenness is quite obvious. Vegetation coverage ratio is derived based on different vegetation extraction approaches, and their consistency is analyzed. It is found that the unmixing-based approach outperforms others in terms of vegetation coverage ration estimation. By comparing the performance and effectiveness of four approaches, some suggestions are given for selecting suitable analytical approaches.

Multi-objective processing of ASTER image for urban environmental analysis

A framework of multi-objective processing and analysis of ASTER data for urban environmental analysis was proposed at first, and related key techniques were discussed. Five levels of multi-objective information processing were discussed. The first level is visualization-level combination, in which the simple combination of results of different objectives is used for visualization or better representation. The second level is coefficient-level combination, and it aims to derive some new parameters by the combination of results for different objectives. The third level is collaboration-level combination, in which the output from one process is feed into the other processes and to improve the performance. The fourth level is association-level combination with the aim of finding those association rules among the results of different processes by statistics and data mining. The fifth level is collaboration decision-level integration, and this level aims to monitor, analyze, manage and protect urban environment by integrating above data, rules, parameter and models. The multi-objective processing and analysis of ASTER data will bring more benefits for urban environment Remote Sensing applications than ever, and this framework and related information processing methods could be used to other fields further.

Pattern change and dynamic evolution of urban green space based on multi-temporal remote sensing images: a case study of Xuzhou City

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.