Key Laboratory of Mine Spatial Information Technologies

Jiaozuo, China

Key Laboratory of Mine Spatial Information Technologies

Jiaozuo, China
Time filter
Source Type

Cheng G.,Key Laboratory of Mine Spatial Information Technologies | Cheng G.,University of Electronic Science and Technology of China | Yu H.,Key Laboratory of Mine Spatial Information Technologies | Lu X.,Key Laboratory of Mine Spatial Information Technologies | Yang D.,Chengdu University of Technology
2010 International Conference on Mechanic Automation and Control Engineering, MACE2010 | Year: 2010

There are a lot of land and resources data. However, it is difficult to share these data due to a variety of reasons such as lacking of unified standards, common semantics, diverse sources and independent management and etc. In this paper we analyze all data for land and resources, studies the consolidation method for mass data from multi-sources of land and resources, solve several key issues such as unified framework, data indexing, mass data storage etc. Finally three database including the original database, basic database, application database, are established and above the three databases a management system is built up. These efforts contributed to "a map" project's completion and the process of land and resources information of Chongqing Municipality. ©2010 IEEE.

Yi W.-B.,Beijing Normal University | Shen L.,Beijing Normal University | Qi Y.-F.,Beijing Normal University | Qi Y.-F.,China University of Mining and Technology | And 2 more authors.
Guang Pu Xue Yu Guang Pu Fen Xi/Spectroscopy and Spectral Analysis | Year: 2011

The paper introduces the Probabilistic Latent Semantic Analysis(PLSA) to the image clustering and an effective image clustering algorithm using the semantic information from PLSA is proposed which is used for hyperspectral images. Firstly, the ISODATA algorithm is used to obtain the initial clustering result of hyperspectral image and the clusters of the initial clustering result are considered as the visual words of the PLSA. Secondly, the object-oriented image segmentation algorithm is used to partition the hyperspectral image and segments with relatively pure pixels are regarded as documents in PLSA. Thirdly, a variety of identification methods which can estimate the best number of cluster centers is combined to get the number of latent semantic topics. Then the conditional distributions of visual words in topics and the mixtures of topics in different documents are estimated by using PLSA. Finally, the conditional probabilistic of latent semantic topics are distinguished using statistical pattern recognition method, the topic type for each visual in each document will be given and the clustering result of hyperspectral image are then achieved. Experimental results show the clusters of the proposed algorithm are better than K-MEANS and ISODATA in terms of object-oriented property and the clustering result is closer to the distribution of real spatial distribution of surface.

Qi Y.,Beijing Normal University | Tang H.,Beijing Normal University | Tang H.,Key Laboratory of Mine Spatial Information Technologies | Shu Y.,Beijing Normal University | And 3 more authors.
International Geoscience and Remote Sensing Symposium (IGARSS) | Year: 2012

In this paper, we present a novel object-oriented semantic clustering algorithm for VHR panchromatic satellite images using a variant of latent Dirichlet allocation model. Firstly, an image collection is implicitly generated by partitioning a large satellite image into densely overlapped sub-images. Then, the Latent Dirichlet Allocation with a hierarchy Dirichlet process is employed to model the image collection. Gibbs sampling is adopted for parameter estimation and image clustering. Specifically, the introduction of Dirichlet process is purposed to extend the LDA to an infinite mixtures model which can estimate the number of components (e.g. clusters in image analysis) automatically. Finally, the effect of the proposed algorithm is analyzed through experiments, and the results of it with the traditional K-means method over a QUICKBIRD image are compared. © 2012 IEEE.

Li C.,Key Laboratory of Mine Spatial Information Technologies | Li C.,Henan Remote Sensing and Mapping Institute | Lu X.,Key Laboratory of Mine Spatial Information Technologies | Zhu N.,Key Laboratory of Mine Spatial Information Technologies | And 3 more authors.
Cehui Xuebao/Acta Geodaetica et Cartographica Sinica | Year: 2015

Monitoring measurement of subway in the stage of construction and operation can ensure the stability of tunnel structure and the safety of its surrounding efficiently. Although existing monitoring measures such as using convergence meter or total station can help to obtain high precision monitoring data, received deformation monitoring points are too sparse, which results in difficulty in reflecting overall deformation characteristics of tunnel. This paper proposed a method for continuously vertical section abstraction and deformation analysis for subway tunnel based on terrestrial point clouds through three-dimensional laser scanning technology applied to deformation monitoring of the tunnel, and made deformation analysis of abstracted two-period section data. The results of the research showed that global deformation of tunnel was reflected more visualized through this method and provided a reference for the dynamic monitoring of tunnel deformation. ©, 2015, SinoMaps Press. All right reserved.

Yang J.,Zhengzhou University | Yang J.,Key Laboratory of Mine Spatial Information Technologies | Yang J.,Digital Land of Key Laboratory of Jiangxi Province | Zhang Y.,Zhengzhou University | And 3 more authors.
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | Year: 2010

Haze is an important influence factor of visible light RS data's obtaining and using. Based on dark channel prior and haze image model, we study the dehaze technology from a single image. Aim at the problem of dark channel prior not work for special region of city image and traditional medium transmission computing method's disadvantage: complex, time-consuming, making use of RS image's characteristics: haze distributes relatively more uniform and depth of field change not acutely, proposes a new quick computing method on the premise of not markedly reduce dehaze effect, to realize single image fast dehaze processing. Using multiple frame images to make system experiment, and do quantitative analysis to dehaze result images' definition.

Zhang X.,Key Laboratory of Mine Spatial Information Technologies | Sun Q.,Henan Polytechnic University
2011 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce, AIMSEC 2011 - Proceedings | Year: 2011

The general land use planning is the most fundamental and specific planning. How to harmonize the interests of all parties with scientific and effective methods and optimize planning projects has become an important issue of township level land use planning project compiling and implementation. Taking Lilin Town of Jiyuan City as an example, the paper constructs the township level general land use planning project assessment index system and estimates alternatives of Lilin Town with gray correlation analysis model. The research results demonstrate that the evaluation method basing on the gray correlation analysis model realizes the integration of qualitative analysis and quantitative analysis. It shows nuance between alternatives. It gives correct and effective assessment of planning project. And it makes sure that the information content with multi-index can not be lost in the analysis procedure. It's an effective evaluation method. © 2011 IEEE.

Guan Z.,Key Laboratory of Mine Spatial Information Technologies | Niu H.,Henan Agricultural University
2011 International Conference on Multimedia Technology, ICMT 2011 | Year: 2011

In order to provide the planning basis and explore the best layout program for logistics park layout, this paper takes Jiaozuo city as an example and selects several factors, such as position, facilities, function and development potential to design a comprehensive evaluation indicator system in site selection of logistics park with the GIS platform, and then At last, the paper points out the location of five logistics parks in Zhongzhan district, Macun district, High-tech Zone, Qinyang city and Xiuwu county and obtains the best layout program of logistics parks in the method of AHP comprehensive evaluation. Field-proven results verify the design feasible and effective objectively. © 2011 IEEE.

Xue Z.,Zhengzhou University | Xue Z.,Wuhan University | Xue Z.,Key Laboratory of Mine Spatial Information Technologies | Lou Y.,Wuhan University | And 2 more authors.
Wuhan Daxue Xuebao (Xinxi Kexue Ban)/Geomatics and Information Science of Wuhan University | Year: 2012

Ambiguity resolution (AR) instantaneously is a significant way to improve the continuity and reliability for GPS kinematic deformation surveying system, and the AR is easier for longer wavelength. We propose a new method for AR in double-differenced level using a single epoch of data. Two combined signals with longer wavelength, φ -3, 4 and φ 4, -5, are used in this method. Based on the constraints of priori coordinates and the relation between the dual frequency, AR instantaneously is achieved. A robust adaptive Kalman filter is used for ensure the reliability of AR and the accuracy of position. The tolerance of position error for priori coordinate is exceeded to 50 cm and suit for kinematic deformation surveying.

Wang L.,Key Laboratory of Mine Spatial Information Technologies | Li G.,Key Laboratory of Mine Spatial Information Technologies | Li G.,Zhengzhou University | Zhang H.,65657 Army
Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering | Year: 2011

Planar target plays an important role in the calibration, data collection and single point measurement of 3D laser scanner of middle and long range. The high precision and automatic recognition of planar targets is a key problem in application of laser scanner. A new recognizing method was put forward by using return light intensity based on analyzing the character of scan data. The steps are as follows: the return light intensity was corrected to eliminate the effects of distance. The point cloud of planar target was obtained by threshold segmenting based on return light intensity. A cluster method was proposed to gather the point cloud of planar target. The area detection was adopted to eliminate those objects which were not real target. 3D coordinate of planar target center was computed by adopting return light intensity weighting method. Experimental results obtained by using Riegl's LMS Z620 show that this method can realize the full automatic recognition quickly with the accuracy of point position better than 2 mm and meet the needs of survey task.

Loading Key Laboratory of Mine Spatial Information Technologies collaborators
Loading Key Laboratory of Mine Spatial Information Technologies collaborators