Archive

  • Select all
    |
    Orginal Article
  • Orginal Article
    YANG Yang,PAN Mao,WU Gengyu,SUN Ying,LI Kuixing
    Download PDF ( ) HTML ( )   Knowledge map   Save

    In three-dimensional geological modeling, because the geological section and the medical section are essentially similar, the three-dimensional surface reconstruction methods based on contour lines that have been widely used in biomedical modeling are now introduced to geological modeling. But most algorithms from medical modeling that have been applied to geological modeling do not fit specifically for geological data. They only consider the rationality of reconstructed surface, however they concern little about the quality of surface geometry. In geological modeling, there are challenges including the complex and changeable shapes of geological objects, sparse geological section data and various origins of data sources; therefore, the methods that simply connect data could not meet the quality requirements of three-dimensional geological modeling. To overcome it, we consider solving the problem of how to reconstruct high quality triangular surfaces from sparse contour lines in this paper. According to the characteristics of geological data, a new algorithm that improves the quality of geological modeling by interpolating transitional sections is presented. The algorithm deals with geological sections that are stored as vectors and integrate them through a series of manipulations, including: matching features between contour lines that have the same geological property; building a mapping function between each matched pair; generating transitional contour lines; constructing surfaces from transitional contours and original contours. The main process can be summarized as follows: (1) matching geological feature; (2) building mapping function; (3) generating transition model; (4) constructing surface. A standard mathematical model which can resolve contour lines from parallel sections and a extended model that can resolve contour lines from cross sections are both defined in this paper. Some illustrative examples and analytical data are given at the end of this paper to prove that the surface reconstructed by this algorithm has much better quality than traditional ones.

  • Orginal Article
    LV Haiyang,SHENG Yehua,DUAN Ping,ZHANG Siyang,LI Jia
    Download PDF ( ) HTML ( )   Knowledge map   Save

    As an accurate spatial interpolation method for data in arbitrary dimensions, Radial Basis Function (referred RBF), was particularly suitable for Digital Elevation Model (referred DEM) interpolation with respect to complex terrain that no assumption is needed for the experiment data. But the interpolation model would become difficult to solve when the number of points, whose elevation is already known, used to construct RBF interpolation model is too large. This is due to the reason that the inversed RBF interpolation matrix would become too huge or too slow to be solved. To address this issue, the hierarchical RBF interpolation method based on local optimal shape parameters, was proposed in this paper and the DEM was interpolated and reconstructed in the experiment. The interpolation procedure was described as follows: first, set the minimum point number in the tree node sub-regions of the study area and define the overlap rate between the adjacent child node sub-regions. Then, construct the regional binary tree recursively from top to bottom, that means the study area was firstly divided from a complete area into two small overlapped regions, and each region could be taken as the child nodes of the binary tree. Second, use the Leave One Out Cross Validation (referred LOOCV) method to calculate the optimal shape parameters in the leaf node regions of the binary tree. As the point distributions in each sub-region are different from each other, as well as the elevation properties, it would lead to different optimal shape parameters. Next, establish the optimal RBF interpolation model, i.e. calculate the linear combination coefficients for each RBF node in the interpolation model with the optimal shape parameter. Third, calculate the elevations of the unknown points in the leaf node regions and get the elevation values using the weighted average method according to the principle of Partition of Unity. The weight of the unknown point in the child node sub-region is calculated using the distance to the center point of the sub-region. Solve the interpolation problem from the bottom to the top recursively to get the final elevation values of the unknown points. Experiments was carried out by using the DEM in some area of Yunnan Province, and the results showed that RBF hierarchical interpolation method with local optimal shape parameters had good stability and high accuracy when DEM was reconstructed from random distributed spatial elevation points, thus it can be taken as an reliable interpolation method.

  • Orginal Article
    QIAO Weifeng,LIU Yansui,WANG Yahua,XIANG Lingzhi
    Download PDF ( ) HTML ( )   Knowledge map   Save

    The current studies on urban gravity center mainly focus on two-dimensional urban gravity center that based on the planar form. Now the trend of urban vertical expansion is more and more distinctive, it is necessary to research the calculation method and analyze the variation of three-dimensional urban gravity center. Based on the analysis of the calculation method of two-dimensional gravity center, this paper deduces a new method to calculate the three-dimensional urban gravity center. It takes three-dimensional urban space as a combination that is formed by multiple stacked layers of ‘sheet’, and uses the mathematical formula of this combination’s gravity center to calculate the three-dimensional urban gravity center. Taking Nanjing as an experimental area for validation, we calculate the two-dimensional and three-dimensional urban gravity centers respectively and contrasts their changing trails. The result shows that the method proposed in this paper is easy to obtain urban entity’s three-dimensional gravity center. Also, the position of the three-dimensional urban gravity center obtained in this way is correct. Through the analysis of the variation law of the two-dimensional and the three-dimensional urban gravity centers in Nanjing, the projections of the two gravity centers have similar changing characteristics and regularities, but a certain degree of deviation between the two trails. The direction of deviation evidently corresponds to the dense regions of high-rise buildings. Taking full account of the urban expansion in the vertical direction, the three-dimensional urban gravity center provides an effective way in reflecting the characteristics and regularities of urban spatial change.

  • Orginal Article
    LIU Shuai,CHEN Jun,SUN Min,ZHAO Lingli
    Download PDF ( ) HTML ( )   Knowledge map   Save

    Epipolar geometry is a core issue in close-range digital photogrammetry, which could reduce the search range to improve both calculation efficiency and reliability of matching. Currently, epipolar constraint has achieved a wide range of applications based on the traditional pinhole projection images and satellite images. However, panoramic epipolar geometry is different from the other images because of its peculiar geometric modeling. Panorama can provide 360-degree view in one hotspot. Apart from the visualization for scene browsing, users generally pay more attention to spatial measurable information within the field of survey. The previous works on panorama mainly focused on panoramic image stitching and panoramic camera. In recent years, people started to pay attention to panoramic three-dimensional reconstruction, which is mainly applied to city buildings and other artificial objects. Implemented by the conventional imaging sequences method, it generally needs complex calculations, numerous control points and a bundle of adjustments to reconstruct the object,which lacks relevant researches and applications of spherical panoramic epipolar geometry. In fact, panorama itself is a type of modeling, if has the scalability, it could be taken as a method for landscape expression as the supplement of the existing three-dimensional object modeling in 3D GIS. Moreover, the panoramic epipolar constraint can improve the reliability, accuracy and speed of matching. However, this constrain has not been fully applied to the 3D information processing of spherical panorama. The paper focuses on the epipolar geometry for spherical panorama, and constructs the epipolar geometry based on the coplanar equation. Then, we derive the mathematical equations and their properties, thus provide a theoretical basis for the spherical panoramic epipolar line that could be used in the close-range digital photogrammetry. The experiment results show that the epipolar line is effectively validated, which can reduce the search range and obtain more useful information.

  • Orginal Article
    MA Qiwei,LIU Xi
    Download PDF ( ) HTML ( )   Knowledge map   Save

    GeoDesign leads the technological innovation at the frontier of traditional urban and rural planning. Spatial governance is an important part of urban and rural planning. Facing the difficulties regarding geographical environment, governance and other elements, it is necessary to introduce GeoDesign to formulate rational planning strategies. Under the review of literatures on spatial governance from domestic and overseas research, we firstly define “the integrated geographical unit” as the core concept of this paper. By elaborating its relationship with other relevant concepts, such as ecological function zoning and ecological units, this paper expounds the inherent connection between the integrated geographical unit and GeoDesign. Then, we analyze the dilemmas that traditional spatial planning strategy faces, and indicate the necessity of introducing the concept of integrated geographical unit. Taking this new concept as the basic carrier of spatial governance, this paper systematically formulates the key framework. It explains the division of integrated geographical units, the unitization of governance elements, and the establishment of spatial governance system. Finally, the framework is applied to the urban-rural comprehensive planning of Zhangjiajie city, and is served as an effective planning tool. In this project, the existing ecological factors on both regional and local scales are evaluated and mapped. The whole Zhangjiajie city is divided into 607 integrated geographical units according to the terrain, administrative boundary, boundary of protected areas and the evaluation of ecological importance. Finally, the retrieval tables of information and regulation strategies are established in order to manage all units. To conclude, this framework clearly demonstrates its supporting role in providing the guidelines for functional structure, industrial development, population management and transportation infrastructure construction.

  • Orginal Article
    XU Shan,ZOU Bin,PU Qiang,GUO Yu
    Download PDF ( ) HTML ( )   Knowledge map   Save

    Land use/cover changes generally have complex effects on air pollution situations. Taking Chang-Zhu-Tan urban agglomeration as an example, this study investigated how do the air pollution concentrations vary with the land use/cover changes. In this process, the land use/cover was firstly retrieved from Landsat 8 images and was consequently used to calculate and map the landscape metrics. Meanwhile, concentration surfaces of PM2.5, PM10, NO2, and O3 in January, May, August and October were generated separately with the observed data from 23 stationary sites. After that, Pearson correlation coefficient was utilized to measure the relationships between concentration surfaces and land use/cover, as well as its landscape metrics. Results reveal that the highest average NO2 concentration occurred in the built-up and road areas, while the green spaces generally had lower concentrations. This situation was almost repeated by PM2.5 concentration all through the year except in spring, but was completely opposite to that of O3. However, impacts of land use/cover on PM10 concentration are relatively undeterminable due to the locally intensive industrial activities and building constructions. Analysis of landscape metrics further demonstrates that the increased index values of Perimeter-Area Fractal Dimension (PAFRAC) and Shannon Diversity (SHDI) were basically accompanied with higher PM10 and PM2.5 concentrations, respectively. Interspersion and Juxtaposition Index (IJI) were positively correlated with the concentrations of PM10, NO2, and PM2.5, however it was found negatively correlated with O3 concentration. In addition, findings from the “Ecological Green Heart” demonstration district suggest that the optimization of land use/cover pattern contributed only slightly to the decline of air pollution concentrations in this area. Therefore, it can be concluded that the air pollution concentrations in Chang-Zhu-Tan urban agglomeration were certainly influenced by its land use/cover pattern, and rational land use development activities would be helpful for reducing the air pollution concentrations in this area.

  • Orginal Article
    YUAN Yuecheng,LIU Haijiang,LI Baolin,GAO Xizhang,XU Lili,DONG Guihua
    Download PDF ( ) HTML ( )   Knowledge map   Save

    In this paper, the spatial pattern, trend and driving forces of ecosystem change of Xinjiang from 2000 to 2010 are derived based on the remote sense data (Landsat TM/ETM+ and HJ-1 CCD). During this period, urban construction area, cropland and wetland had expanded rapidly, that increased by 30.5%、26.7% and 10.2% respectively. Meanwhile, grassland, shrub had massively decreased by 2.4% and 5.1%. Glacier area had also significantly retreated by about 1.6%. Woodland and desert were almost unchanged. Traditional oasis was the majority area of change, especially in the south and north foot of Tianshan mountains. Technical improvement of water conservancy facilities and national west part development strategy are the primary causes of transformations of grassland and shrub into cropland. Population growth is the driving force of urban construction area increase. Due to global warming, a great amount of glacier area of the percentage between 16.7% and 32.5% had disappeared since 1960s, which resulted in the increase of wetland. National eco-environment projects, e.g. Three North Shelterbelt, was established to protect woodland and desert from further deterioration. This paper presented some suggestions to keep the ecological security of Xinjiang: (1) forbidding deforestation and developing cropland in mountain area to recover its water conservation function; (2) restricting the increase of cropland in oasis because it has already exceeded the theoretical water resources carrying capacity of Xinjiang; (3) protecting the transition zone to ensure the ecological security of oasis in the piedmont plain; (4) constructing artificial grassland and utilizing the crop straw to develop animal husbandry; (5) strengthening the research under the impact of global climate change on water resources to assist future policy making.

  • Orginal Article
    YANG Fan,HUANG Lin,SHAO Quanqin,BAO Yuhai
    Download PDF ( ) HTML ( )   Knowledge map   Save

    In this paper, three prefectures in the southeast of Guizhou Province were selected as the study area. Using the method of biomass expansion factor and mean biomass, the relationships between carbon density and forest age for the 24 forest types was established. Then, the total amounts and change trends of the biomass and carbon storage of forest vegetation in the southeast of Guizhou Province from 1990 to 2010 was estimated based on forest investigation data in 2010. Furthermore, the carbon sequestration potential during the period of 2010-2050 was estimated by setting 2010 as the baseline and assuming that the area of forest vegetation remained stable and without consideration of forest rotation. The following conclusions were made in this study: (1) in 2010, the forest vegetation carbon storage in the southeast of Guizhou Province was 106.22 TgC, accounting for 63.01% carbon storage in Guizhou Province and 1.36% carbon storage in China; the average carbon density was 32.44 MgC/hm2,which was 0.93 times of the average value of Guizhou Province and 0.76 times of the average value of China. Meanwhile, the carbon density gradually increased from the west to the east. The carbon density in the east was higher than the average. (2) During the period of 1990-2000, the forest vegetation carbon storage had increased by 30.67 TgC. During the period of 2000-2010, the forest vegetation carbon storage had increased by 49.55 TgC, in which 31.09 TgC of the storage were contributed by conversion from farmland to forest. (3) Till 2050, the forest vegetation carbon storage in that area would be 153.38 TgC, which is increased by 47.16 TgC. This showed that the forest in the southeast of Guizhou Province had great carbon sequestration potential.

  • Orginal Article
    XIE Xiaohua,WANG Ruizhang,WEN Donghong,ZHANG Zhiyong
    Download PDF ( ) HTML ( )   Knowledge map   Save

    It is of great significance to analyze and evaluate the medical facilities layout. It can not only solve the contradiction between the public health demand and the medical service supplies, but also help government make rational decisions. Xiamen was selected as a pilot area in the first national census of geographic conditions. On this background, this paper takes Xiang'an District as an example and gives a comprehensive study on its medical facilities layout. Based on two kinds of data source: the data of the first national geographic conditions census and the statistical data from the department of health and other departments, an evaluation index system of medical facilities layout was constructed from three aspects: the current situation, the service level and the spatial layout optimization. The current situation of medical resources was analyzed from the view of medical and health care. The evaluation of the service level of medical facilities was performed on the basis of GIS network analysis. The spatial layout of the medical facilities was optimized by the usage of the GIS “Location Allocation Model”. Finally, this paper presented improvement suggestions and measures for medical facilities layout. The study results show: (1) the medical resources are insufficient and distribute unevenly. (2) The medical facilities vary widely between urban and rural area. Meanwhile, the medical service is in a low level. (3) Four hospitals and five health centers should be added to meet the public’s health demand. In a word, this study will be helpful for government to make decision regarding Xiang'an District’s medical facilities layout in future. In addition, it provides a feasible method to evaluate the medical facilities layout reasonableness.

  • Orginal Article
    SUN Fei,ZHANG Xia,TANG Luliang,LIU Zhang,YANG Xue,DONG Kun
    Download PDF ( ) HTML ( )   Knowledge map   Save

    The uneven spatial and temporal distribution of taxi passengers not only affects cabdrivers' income-but also has an effect on development and enhance of taxi efficiency.Since taxi is regarded as the supplementation of city public transit, it is important to improve the taxi efficiency.According to many former researches done on taxi driving strategies, the objects always aim to focus on the taxi driver, and researchers merely consider the effects of an empty taxi situation, which may affect the taxi efficiency due to the fuel consumption and time cost.In this paper, in order to improve taxis' profits and efficiency, we used the taxis' GPS big data to optimizethe evaluation model of taxi efficiency by taking its empty state into consideration, and proposed the concept of high efficiency passengers for the first time. Then, we defined and quantified the high efficiency passengers, and established a new spatial and temporal analysis method for high efficiency passengers. Finally, we extracted high efficiency passenger source information and its spatial and temporal distribution pattern from taxi driving routs.To further verify this method, we took Wuhan's taxi data asan example, extracted the high efficiency passenger source from different aspects, such as time, space and screening conditions, and found some distribution patterns of the city passengers through comparison and analysis.According to the distribution patterns, the quantity of high efficiency passengers is associated with traffic conditions, and most high efficiency passengers are distributed far from the downtown area.These facts have proved that the studies on temporal and spatial distribution of high efficiency taxi passengers can provide scientific evidence and references for improving cab drivers' income and taxi efficiency.

  • Orginal Article
    ZHANG Xirui,FANG Zhixiang,LI Qingquan,LU Shiwei
    Download PDF ( ) HTML ( )   Knowledge map   Save

    The spatio-temporal distribution of road network transportation capacity in Shenzhen City was analyzed based on floating car data. The raw floating car data was pre-processed before it was matched to the exact road. Then, the trajectory of each floating car was rebuilt. This paper calculated the travel speed of all different types of road in different time periods. Meanwhile, a new urban road capacity indicator was proposed, by which the road capacity was directly derived from the travel speed. Taking consideration of various traffic conditions and interactions between vehicles, the indices used to describe lane reduction and lane width reduction were applied to adjust the road capacity. The influence of intersections on road capacity can be ignored when taking the traffic flow as a continuous flow. Time-varying characteristics and heterogeneous spatial distribution was found in the urban road capacity. The trend of hourly road capacity was significantly different between weekdays and weekends. Road capacity kept stable in weekdays until it revealed a peak that appeared at noon in weekends. Reserve capacity changed greatly in both weekdays and weekends. And it decreased significantly at noon in weekends. The road capacity varied dramatically within different districts of the city: the road capacity in Yantian District and Nanshan District were both high, and they shared similar trends, while the road capacity in Longgang District and Bao'an District, which also shared similar trends, were in the average level of the capacity within the city, and slightly lower than the former two districts. Additionally, the road capacity of Futian District and Luohu District were in the lower level of the city. We also found that the urban road capacity was overall evidently low in the areas with higher population density and higher development level, and didn’t change much during the day. Road grade had significant influence on the road capacity and reserve capacity. For higher grade of the urban roads in Shenzhen, the capacity and the reserve capacity varied obviously with time, however there was little change in reserve capacity for lower level of the urban roads.

  • Orginal Article
    MENG Fan,YANG Xiaomei,ZHOU Chenghu
    Download PDF ( ) HTML ( )   Knowledge map   Save

    This paper studies the problem of the restoration of images corrupted by mixed Gaussian-impulse noise. In recent years, low-rank matrix reconstruction has become a research hotspot in many scientific and engineering domains such as machine learning, image processing, computer vision and bioinformatics, which mainly involves the problems of matrix completion and robust principal component analysis. The two problems namely focus on recovering a low-rank matrix from an incomplete but accurate sampling subset of its entries, or from an observed data matrix with an unknown fraction of its entries being arbitrarily corrupted, respectively. Inspired by these ideas, the problem of recovering a low-rank matrix from an incomplete sampling subset of its entries with an unknown fraction of the samplings contaminated by arbitrary errors was considered, which was defined as a problem of matrix completion from corrupted samplings and modeled as a convex optimization problem that minimizes a combination of the nuclear norm and the l1-norm in this paper. Meanwhile, a novel and effective algorithm called augmented subsection Lagrange multipliers was put forward to exactly solve the problem. For the mixed Gaussian-impulse noise removal, we regard it as the problem of matrix completion from corrupted samplings, and restore the noisy images following by an impulse-detecting procedure. Compared with some existing methods for mixed noise removal, the recovery quality of our method is dominant when the images possess low-rank features such as geometrically regular textures and similar structural contents. Especially when the density of impulse noise is relatively high and the variance of Gaussian noise is small, our method can outperform the traditional methods significantly not only in the simultaneous removal of Gaussian noise and impulse noise, and in the restoration of low-rank image matrix, but also in the preservation of textures and details of the image.

  • Orginal Article
    LI Yang,JIANG Nan,SHI Hao,SHAO Hua
    Download PDF ( ) HTML ( )   Knowledge map   Save

    Change detection with remote sensing images plays an important role in land cover mapping. With the development of science and technology, a series of new remote sensing data sources have become available, and have been significantly improved, which also brings a great challenge to the traditional remote sensing change detection methods. Unlike the other traditional methods for change detection, the present work uses Latent Dirichlet Allocation model (LDA) in learning middle-level semantic topics instead of low-level features from remote sensing images. In this paper, we use the pixels of two remote sensing images as the basic unit, while the image segments are used as the documents in the object-based image analysis methods. Firstly, we try to extract some features from these remote sensing images, such as the spectral and textural features. Then, we work on organizing the local features from these two images to obtain visual words and construct the bag of words model (BOWM) representation. Based on this, the LDA model is utilized to reveal the underlying topics, which are used to detect the change of the study area. Every document of remote sensing images has a specific topic distribution, which is related to the reference data of the study area. In this process, the pseudo changes and actual changes of these two remote sensing images can be distinguished by the topic distributions of the documents. Compared with traditional pixel-level change detection methods,the method of LDA-based model is less influenced by the spectral variance of two images, which avoids the “salt and pepper” effect by using object-based analysis method. The effectiveness of LDA-based model change detection approach was verified in experiments with the accuracy to be 85.35%, and it is also compared with techniques using Spectral Angle Mapper and Image differencing. The result shows that our studies provide a good approach to improve the accuracy and reduce the mistake rate of change detection between two images. Our work indicates that LDA model-based approach is superior to the traditional methods and the proposed method is applicable to the analysis of change area detection using Landsat-8 images.

  • Orginal Article
    SHANG Ke,YU Xinfang,YUE Cairong,WANG Qiankun,WANG Zhengxing
    Download PDF ( ) HTML ( )   Knowledge map   Save

    Plain afforestation refers to the non-crop vegetation in crop-dominated plain area. As the main forest vegetation it has provided favorable conditions for ecological environment construction. The plain afforestation in this paper mainly includes farmland shelterbelt, road shelterbelt, residence shelterbelt and wasteland shelterbelt. But due to their small patches, getting the information of plain afforestation requires high spatial resolution remote sensing imagery. And the different sizes of kinds of afforestation patches make it difficult to extract all of them at once. In addition, it is a problem, if they could be extracted all, to distinguish themselves from one another. Based on this point, the paper explores a more accurate object-oriented classification method based on Mapping Satellite-1 (MS1) imagery in Fengqiu County, Henan province, China. The innovation of this method lies in the selection of proper segmentation scale according to different kinds of plain afforestation. Build optimal segmentation levels to insure the farmland shelterbelt, road shelterbelt, residence shelterbelt and wasteland shelterbelt could be segmented from their background imagery completely. Then contrast and analyze the spectral and spatial characteristics of different afforestation to develop classification rule sets. The classification rule sets could be conveyed between levels and current class could inherit them from parent class. Then build membership function to extract the plain afforestation area hierarchically. The results showed that the plain afforestation area of Fengqiu is 152.51 km2. More specifically, the farmland shelterbelt area is 36.09 km2, the road shelterbelt area is 21.29 km2, the residence shelterbelt area is 71.56 km2, and the wasteland shelterbelt area is 23.57 km2. The classification accuracy is 93.50% and the Kappa coefficient is 0.92. It showed that the study have achieved fine classification results. And the results also verified the potential of object-oriented plain afforestation information extraction based on Mapping Satellite-1 (MS1) imagery. This method can provide a technical support for the area accurate estimation of plain afforestadion.

  • Orginal Article
    HUANG Dan,LIU Qingsheng,LIU Gaohuan,YAN Wenbo
    Download PDF ( ) HTML ( )   Knowledge map   Save

    Coal gangue is a kind of dark gray solid waste generated during mining process. Nowadays, coal gangue has become one of the biggest pollution sources to the ecological environment in mining areas. The accumulation of coal gangue not only occupies excessive land and causes serious environmental problem, but also damages the health of local people. Therefore, it is urgent to reduce the coal gangue yards in mining areas. In addition, extracting the location, shape and size information of coal gangue yards quickly and accurately is significant to environmental departments. The traditional methods of investigating coal gangue yards cost a lot of time and money. While remote sensing technologies can record the information of earth surface quickly and accurately, they have obvious superiorities in extracting coal gangue yards information. This paper takes the Dongsheng District, which locates in Ordos City of Inner Mongolia, as the study area, and utilizes SPOT-5 high resolution image as the data source. Then, this paper adopts the object-oriented method to extract coal gangue yards information from the study area. Multi-resolution segmentation and fuzzy classification algorithm are the most important steps in this method. Four appropriate segmentation scales are determined through comparisons of several tests, they are: 400, 160, 80 and 40. Next, we classify the segmented objects into different classes using the fuzzy classification algorithm that based on objects’ characteristics, such as spectrum, shape, texture and other features. The objects are further classified into eleven classes: bare area, buildings, roads, water, vegetation, shadows, dumps, coal gangue yards, coal yards, coal pits and others. The rule set used to extract different classes is built, which is aimed to provide a reference to relevant environmental departments to quickly and conveniently monitor the environment in coal mining area. In the end, we assess the accuracy of the classification results: the total accuracy is 88.78% and the user accuracy of coal gangue yards information is about 89.47%. Besides, a comparative extraction result is extracted using maximum likelihood method, whose total accuracy is 64.13% and the user accuracy of coal gangue yards information is only about 64.18%, which is much lower than the result extracted by the object-oriented method. Generally, due to the serious pollution caused by coal gangue yards, and considering the object-oriented classification method is seldom used to extract coal gangue yards information in China and abroad, this paper tries to extract coal gangue yards information using object-oriented classification method, and establish a rule set that can be applied to extract coal gangue yards information and other typical features. As we can see from the analyses, this paper has its significance in environmental protection. Relevant conclusions and analysis can be provided to the environmental protection departments as a useful reference to monitor and manage the pollution caused by coal gangue yards.