Most Down Articles

    Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month | Most Downloaded in Recent Year|

    All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Instantaneous Attitude Determination Based on Original Multi-antenna Observations Using Adaptively Robust Kalman Filtering
    GAN Yu, SUI Lifen, LIU Changjian, DONG Ming
    Acta Geodaetica et Cartographica Sinica    2015, 44 (9): 945-951.   DOI: 10.11947/j.AGCS.2015.20140492
    Abstract2079)   HTML    PDF(pc) (1292KB)(63949)       Save
    Attitude determination directly by carrier phase observation makes optimal use of observation and attitude constraints. The phase models based on misalignment angle and multiplicative quaternion error are derived. The state models for attitude estimation with and without external angular rate sensors are both erected. The attitude errors are estimated by adaptively robust filtering, in which the adaptive factors of ambiguity and attitude error are decided respectively following the idea of multi adaptive factor filtering. The factor of attitude is determined by a three-section function containing Ratio. Adaptively robust filtering makes the best use of constraint and historical information, fusing them in the calculation of float solution. As the accuracy of float solution and the structure of covariance matrix are improved greatly, the fix solution can be searched efficiently using LAMBDA (least-squares ambiguity decorrelation adjustment) method merely, perfectly fulfilling the real-time requirement. Field test of a ship-based three-antenna attitude system is used to validate the proposed method. It is showed that direct attitude determination based on adaptively robust filtering has obvious advantages in efficiency and reliability.
    Reference | Related Articles | Metrics
    The 3D Visualization Method of Hexagonal Discrete Global Grid Data
    Acta Geodaetica et Cartographica Sinica    2013, 42 (3): 0-0.  
    Abstract561)      PDF(pc) (10270KB)(20511)       Save
    Aiming at the 3D visualization method of hexagonal discrete global grid, a new spatial operation structure (Hexagonal Quad Balanced Structure, HQBS) for hexagonal discrete grid, was designed. It used 4 codes to encodes units, defined spatial vectors for grids and realized basic operations. Based on the operations, spatial index can be easily solved. And dynamic generation algorithms, spatial visualization methods and clipping of visible area of global grid were studied. Through visualization experiments, conclusions were obtained as follows. The average generation efficiency of global dynamic grid could reach 110 units per ms to 370 units per ms, and the loading time efficiency of grid data and spatial data per layer was about 300 ms. The average refreshing level of global discrete grid loaded with spatial data was about 20 frames per second, which ensured real-time displaying requirements.
    Related Articles | Metrics
    Information Extraction Method of Alpine Glaciers with Multitemporal and Multiangle Remote Sensing
    DU Weibing, LI Junli, BAO Anming, WANG Baoshan, WANG Shuangting
    Acta Geodaetica et Cartographica Sinica    2015, 44 (1): 59-66.   DOI: 10.11947/j.AGCS.2015.20130514
    Abstract1720)   HTML    PDF(pc) (10343KB)(14361)       Save

    A glacier extraction method based on multitemporal and multiangle remote sensing images is proposed. Firstly, a "global-local" threshold segmentation method is applied to extract snow ice boundaries with multitemporal remote sensing images. Secondly, the glacier boundaries hidden by mountain shadows are restored with topographic features and multiangle information in different remote sensing images. Finally, the best glacier extents are the intersections of different glacier/snow extents. In order to validate the method, a glacier extraction is tested with 4 Landsat images during 2009-2010 in the western part of Tumur peak of the Tienshan Mountains. The results show that the proposed method performs well in extracting the glacier boundaries inside the mountain shadows with multiangle images.

    Reference | Related Articles | Metrics
    Chinese Continental Water Storage and Ocean Water Mass Variations Analysis in Recent Ten Years Based on GEACE RL05 Data
    LU Fei, YOU Wei, FAN Dongming, HUANG Qiang
    Acta Geodaetica et Cartographica Sinica    2015, 44 (2): 160-167.   DOI: 10.11947/j.AGCS.2015.20130753
    Abstract2234)   HTML    PDF(pc) (3715KB)(12835)       Save
    Chinese mainland water reserves and the variation tendency of the ocean water mass from 2003 to 2012 are recovered with the data of GRACE RL05 provided by Center for Space Research. An improved de-correlated filtering algorithm is presented. which sets the highest order coefficient to be fitted up to 55 and the border coefficient can also be directly fitted without being used as center of the sliding window. The algorithm is proposed with significant decrease in stripes compared with traditional algorithms. The results show that the area, where terrestrial water changes a lot, are the north China plain, the three gorges region, the border region of Qinghai, Xinjiang and Tibet respectively. During the recent ten years, the groundwater of north China plain reduces at the rate of 4.1±1.3 mm/a, The change of ground water and surface water are mainly between 2004 and 2008. GRACE can detect the prominent of mass change of the Three Gorges Reservoir in the form of equivalent water height, which are 52 mm、18 mm and 7 mm respectively. The ground water and terrestrial water in the border region of Qinghai, Xinjiang and Tibet have increased at the rate of 10.6±0.9 mm/a、11.6±1.1 mm/a respectively. The results of GRACE data show that the ocean mass rise trend of East China Sea, South China Sea and Yellow China Sea are 4.23±0.9 mm/a、1.33±0.9 mm/a、3.09±1.1 mm/a, respectively after the deduction of the glacial isostatic adjustment. The ocean water mass of East China Sea rises significantly faster than the other two areas.
    Reference | Related Articles | Metrics
    Automatic Analysis and Mining of Remote Sensing Big Data
    LI Deren, ZHANG Liangpei, XIA Guisong
    Acta Geodaetica et Cartographica Sinica    2014, 43 (12): 1211-1216.   DOI: 10.13485/j.cnki.11-2089.2014.0187
    Abstract5193)   HTML    PDF(pc) (1314KB)(11942)       Save
    With the diversification of the imaging methods and the growing categories, quantity, and observation frequency of remote sensing data, the ability of land-cover observation has reached an unprecedented level, which means a new era of big data in remote sensing is coming. However, the existing methods and processing techniques cannot fulfill the need of the big data application in remote sensing. Thus, to develop the automatic analysis and mining theory and techniques for remote sensing big data is among the most advanced international research areas. This paper investigates and analyses the domestic and overseas research status and progress around this field and points out its key problems and developing trends.
    Reference | Related Articles | Metrics
    Progress, Challenges and Perspectives of 3D LiDAR Point Cloud Processing
    YANG Bisheng, LIANG Fuxun, HUANG Ronggang
    Acta Geodaetica et Cartographica Sinica    2017, 46 (10): 1509-1516.   DOI: 10.11947/j.AGCS.2017.20170351
    Abstract4740)   HTML    PDF(pc) (1579KB)(10099)       Save
    3D LiDAR can perform an intensive sampling of the earth surface in a direct way, and yield the 3D point cloud that contains numerous and scattered points with the coordinates ( X, Y, Z) and attributes (e.g., intensity). As the vital 3D geospatial data for description of the world in the digital era, 3D point cloud plays an important role not only in earth science researches but also in national requirements (e.g., global change analysis, global mapping, and smart city). Inspired by sensor technologies and national requirements, 3D LiDAR has got great progresses in hardware, data processing and applications, and is facing new challenges. Following the history of 3D LiDAR, this paper first reviews the status of 3D LiDAR system, and introduces the development of key technologies in data processing. Then the typical applications of 3D LiDAR in surveying and other related fields are listed, and current challenges in point cloud processing are concluded. Finally, some future perspectives are presented.
    Reference | Related Articles | Metrics
    Research Progress and Methods of InSAR for Deformation Monitoring
    ZHU Jianjun, LI Zhiwei, HU Jun
    Acta Geodaetica et Cartographica Sinica    2017, 46 (10): 1717-1733.   DOI: 10.11947/j.AGCS.2017.20170350
    Abstract5375)   HTML    PDF(pc) (1654KB)(10024)       Save
    Deformation monitoring is one of the most mature applications of space-borne InSAR technique. Firstly, we introduce the basic principle of InSAR in the monitoring of deformation and the current SAR satellites. The deformation monitoring methods of InSAR are then classified into the groups of D-InSAR, PS-InSAR, SBAS-InSAR, DS-InSAR and MAI, which are analyzed in the aspects of technical features and application scopes. Subsequently, we analyze the research progress and deficiencies of InSAR in the investigation of urban, mining area, earthquake, volcano, infrastructure, glacier, permafrost and landslide. Finally, some advanced academic problems such as deformation monitoring in multi-demension and low coherence area, atmospheric and orbital errors mitigation, and accuracy assessment are concluded.
    Reference | Related Articles | Metrics
    An Adaptive Enhanced Lee Speckle Filter for Polarimetric SAR Image
    Acta Geodaetica et Cartographica Sinica    2014, 43 (7): 690-697.  
    Abstract1770)   HTML    PDF(pc) (9158KB)(8473)       Save

    The refined Lee filter, which is simple, efficient and robust, has been widely used in polarimetric SAR (PolSAR) processing. However, the filter has two severe defects: scallop effect and false-line effect. In this paper, we extend and improve the refined Lee filter by adding a square window and a group of linear windows. To better suppress the speckle noise as well as preserve the detail information, we adopt an adaptive window mechanism: big window is used in homogeneous areas and small window is used in heterogeneous areas. So the proposed filter can adapt actual scenes in both shape and size aspects. Both airborne and spaceborne PolSAR data are used to demonstrate its overall speckle filtering characteristics by comparing with other filters. The results show that the adaptive enhanced Lee filter has better performance in speckle suppressing and detail preserving than the refined Lee filter, and can preserve the polarimetric information very well.

    Related Articles | Metrics
    Accessibility Analysis of Road Network Supported by Isochrone Model
    HE Yakun AI Tinghua YU Wenhao
    Acta Geodaetica et Cartographica Sinica    2014, 43 (11): 1190-1196.   DOI: 10.13485/j.cnki.11-2089.2014.0183
    Abstract1703)   HTML    PDF(pc) (1815KB)(7760)       Save

    An isochrone is a visual representation of time accessibility which refers to a particular point in the road network. Features of road network and traffic conditions should be considered when generating isochrones. Accessibility rules can be found through analyzing the morphological features of isochrones. This article systematically studied the definition, characteristics and generation methods of isochrones. We proposed the flow method to generate isochrones, which was analogous to the process of water drop spreading along the wood texture. Accessibility expansion paths were obtained on the basis of the network rasterization model, considering unique constraints of isochrones extension, such as road conditions, moving criteria and time sections. Then we used the extending convex hull and angle bisector displacement to generate isochrones. Since the algorithm was based on field theory, we could flexibly load space constraints for any part of interested zones. This advantage made it convenient to generate real-time isochrones. Similar to extracting geomorphic traits from contour lines, we found accessibility rules by analyzing the arrangement form, density, bending form, bending direction and stretching direction of isochrones which was generated by the above approach. After that, we inferred accessibility rules.

    Reference | Related Articles | Metrics
    The Functional Gradient Description Method of Space Coordinate Transformation
    DUAN Pengshuo LIU Gengyou GONG Youliang HAO Xiaoguang WANG Nazi
    Acta Geodaetica et Cartographica Sinica    2014, 43 (10): 1005-1012.   DOI: 10.13485/j.cnki.11-2089.2014.0145
    Abstract1326)   HTML    PDF(pc) (927KB)(7710)       Save

    This?study?proposes?the?conception?of?coordinate?transformation?gradient?field,?which?can?realize?the?space?coordinate?transformation?from?small?angle?to?arbitrary?angle?and?from?static?to?dynamical.?

    Based?on?the?equivalent?of?the?unit?quaternion?rotation?matrix?and?the?Rodrigo?matrix,?this?paper?reveals?the?mathematical?relationship?between?the?spatial?coordinate?transformation?and?the?functional?

    gradient?and?derives?an?arbitrary?coordinate?transformation?formula?expressed?by?functional?gradient?in?space.?The?results?indicate?that?the?essence?of?spatial?coordinate?transformation?is?potential?field

    ?in?mathematic?and?we?can?unify?all?the?space?coordinate?transformations?by?using?the?conception?of?field,?which?is?the?theoretical?foundation?for?the?further?study?of?time?continuous?space?coordinate

    ?transformation?and?this?study?also?gives?a?new?solution?for?the?attitude?determination?of?motion?carriers.

    Reference | Related Articles | Metrics
    An Overview on Data Mining of Nighttime Light Remote Sensing
    LI Deren, LI Xi
    Acta Geodaetica et Cartographica Sinica    2015, 44 (6): 591-601.   DOI: 10.11947/j.AGCS.2015.20150149
    Abstract4097)   HTML    PDF(pc) (1051KB)(6963)       Save

    When observing the Earth from above at night, it is clear that the human settlement and major economic regions emit glorious light. At cloud-free nights, some remote sensing satellites can record visible radiance source, including city light, fishing boat light and fire, and these nighttime cloud-free images are remotely sensed nighttime light images. Different from daytime remote sensing, nighttime light remote sensing provides a unique perspective on human social activities, thus it has been widely used for spatial data mining of socioeconomic domains. Historically, researches on nighttime light remote sensing mostly focus on urban land cover and urban expansion mapping using DMSP/OLS imagery, but the nighttime light images are not the unique remote sensing source to do these works. Through decades of development of nighttime light product, the nighttime light remote sensing application has been extended to numerous interesting and scientific study domains such as econometrics, poverty estimation, light pollution, fishery and armed conflict. Among the application cases, it is surprising to see the Gross Domestic Production (GDP) data can be corrected using the nighttime light data, and it is interesting to see mechanism of several diseases can be revealed by nighttime light images, while nighttime light are the unique remote sensing source to do the above works. As the nighttime light remote sensing has numerous applications, it is important to summarize the application of nighttime light remote sensing and its data mining fields. This paper introduced major satellite platform and sensors for observing nighttime light at first. Consequently, the paper summarized the progress of nighttime light remote sensing data mining in socioeconomic parameter estimation, urbanization monitoring, important event evaluation, environmental and healthy effects, fishery dynamic mapping, epidemiological research and natural gas flaring monitoring. Finally, future trends of nighttime light remote sensing and its data mining have been proposed from four aspects including new data source, knowledge discovery, in-situ observation, and national/global geographic conditions monitoring.

    Reference | Related Articles | Metrics
    Indoor Positioning with Smartphones:The State-of-the-art and the Challenges
    CHEN Ruizhi, CHEN Liang
    Acta Geodaetica et Cartographica Sinica    2017, 46 (10): 1316-1326.   DOI: 10.11947/j.AGCS.2017.20170383
    Abstract3000)   HTML    PDF(pc) (2435KB)(6843)       Save
    Indoor positioning is one of the core technologies of artificial intelligence (AI) in the future and will play a pivotal role in the upcoming era of AI. Currently, indoor positioning is one of the hot research topics in academic and industrial society. Google, as one of the leading information technology (IT) companies, has listed visual positioning service (VPS) as one of the core technologies. Apple has endeavored to prompt iBeacon, the low energy Bluetooth technology for indoor positioning. In cooperation with a Finnish company, IndoorAltas, Baidu launched an indoor positioning program with a magnetic matching approach. All these initiatives and new technologies have shown the significance and necessaries of indoor positioning. However, affected by the complexity of the indoor spaces, it is still challenging to achieve accurate, effective, full coverage and real-time positioning solution indoors. With the popularity of smart phones and the rapid development of MEMS sensors in recent years, many methods have been proposed to use the smartphone built-in sensors and RF radios for indoor positioning. In this paper, we focus on indoor positioning technologies for smartphones and classify the different technologies into two categories, namely the radio frequency (RF) technologies and the sensors technologies. The state-of-the-art of the technologies has been reviewed. The pros and cons of the technologies have been commented in the context of different application scenarios. Moreover, the challenges of indoor positioning have also been pointed out and the directions of the future development of this area have been discussed.
    Reference | Related Articles | Metrics
    Photogrammetry and Deep Learning
    GONG Jianya, JI Shunping
    Acta Geodaetica et Cartographica Sinica    2018, 47 (6): 693-704.   DOI: 10.11947/j.AGCS.2018.20170640
    Abstract4997)   HTML    PDF(pc) (4176KB)(6813)       Save
    Deep learning has become popular and the mainstream in types of researches related to learning,and has shown its impact on photogrammetry.According to the definition of photogrammetry,a subject that researches shapes,locations,sizes,characteristics and inter-relationships of real objects from optical images,photogrammetry considers two aspects,geometry and semantics.From the two aspects,we review the history of deep learning and discuss its current applications on photogrammetry,and forecast the future development of photogrammetry.In geometry,the deep convolutional neural network (CNN) has been widely applied in stereo matching,SLAM and 3D reconstruction,and has made some effect but needs more improvement.In semantics,conventional empirical and handcrafted methods have failed to extract the semantic information accurately and failed to produce types of “semantic thematic map” as 4D productions (DEM,DOM,DLG,DRG) of photogrammetry,which causes the semantic part of photogrammetry be ignored for a long time.The powerful generalization capacity,ability to fit any functions and stability under types of situations of deep leaning is making the automated production of thematic maps possible.We review the achievements that have been obtained in road network extraction,building detection and crop classification,etc.,and forecast that producing high-accuracy semantic thematic maps directly from optical images will become reality and these maps will become a type of standard products of photogrammetry.At last,we introduce two current researches related to geometry and semantics respectively.One is stereo matching of aerial images based on deep learning and transfer learning; the other is fine crop classification from satellite special-temporal images based on 3D CNN.
    Reference | Related Articles | Metrics
    Review of GNSS PPP and Its Application
    ZHANG Xiaohong, LI Xingxing, LI Pan
    Acta Geodaetica et Cartographica Sinica    2017, 46 (10): 1399-1407.   DOI: 10.11947/j.AGCS.2017.20170327
    Abstract3713)   HTML    PDF(pc) (1456KB)(6759)       Save
    In this paper, we summarized the development of precise point positioning (PPP)technologies and its applications. Key technologies and methodologies for PPP float solution, ambiguity-fixing PPP, real-time PPP and multi-GNSS PPP were intensively analyzed and discussed. Typical PPP applications were summarized and demonstrated. Finally, we illustrated the prospect of PPP and pointed out problems to be solved for PPP development and applications in the coming years.
    Reference | Related Articles | Metrics
    Neural Network Aided Adaptive UKF Algorithm for GPS/INS Integration Navigation
    TAN Xinglong, WANG Jian, ZHAO Changsheng
    Acta Geodaetica et Cartographica Sinica    2015, 44 (4): 384-391.   DOI: 10.11947/j.AGCS.2015.20140216
    Abstract2099)   HTML    PDF(pc) (5763KB)(6529)       Save
    The predicted residual vectors should be zero-mean Gaussian white noise, which is the precondition for multiple fading factors adaptive filtering algorithm based on statistical information in GPS/INS integration system. However the abnormalities in observations will affect the distribution of the residual vectors. In this paper, a neural network aided adaptive unscented Kalman filter (UKF) algorithm with multiple fading factors based on singular value decomposition(SVD) is proposed. The algorithm uses the neural network algorithm to weaken the influence of the observed abnormalities on the residual vectors. Singular value decomposition instead of unscented transformation is adopted to suppress negative definite variation in priori covariance matrix of UKF. Since single fading factor in poor tracking of multiple variables has the limitation, multiple fading factors to adjust the predicted-state covariance matrix are constructed with better robustness so that each filter channel has different adjustability. Finally, vehicle measurement data are collected to validate the proposed algorithm. It shows that the neural network algorithm can prevent the observed abnormalities from affecting the distribution of the residual vectors, expanding the applied range of the adaptive algorithm. The neural network algorithm aided SVD-UKF algorithm with multiple fading factors is able to remove influences of state anomalies on condition of the observed abnormalities. The accuracy and reliability of the navigation solution can be improved by this algorithm.
    Reference | Related Articles | Metrics
    Acta Geodaetica et Cartographica Sinica   
    Abstract887)      PDF(pc) (31962KB)(6285)       Save
    Related Articles | Metrics
    Distributed Collaborative Geographic Modeling Task Decomposition Method Based on HTN Planning
    Acta Geodaetica et Cartographica Sinica    2013, 42 (3): 0-0.  
    Abstract678)      PDF(pc) (10490KB)(5775)       Save
    In order to effectively solve the problem of static integrating mode of models in distributed collaborative geographic modeling environment, this paper proposes several decomposition principles of geographic modeling tasks such as function structure, computational complexity, organization multiplicity, and spatiotemporal scales by analyzing the decomposable process of distributed collaborative geographic modeling tasks. Hierarchical Task Network (HTN) planning is adopted to reach formalized expression of the geographic modeling tasks, in the meanwhile, Ordered Task Decomposition (OTD) is also applied to design recursive decomposition algorithm of modeling tasks. Ultimately, the modeling tasks are tessellated, decomposed and expanded to subtask network. With the adoption of SWAT model as an experimental case, HTN-based geographic modeling task planner was developed and realized. The experiment shows that the decomposition method of distributed collaborative geographic modeling tasks possesses preferable flexibility, intelligence and adaptability.
    Reference | Related Articles | Metrics
    Combining the Pixel-based and Object-based Methods for Building Change Detection Using High-resolution Remote Sensing Images
    ZHANG Zhiqiang, ZHANG Xinchang, XIN Qinchuan, YANG Xiaoling
    Acta Geodaetica et Cartographica Sinica    2018, 47 (1): 102-112.   DOI: 10.11947/j.AGCS.2018.20170483
    Abstract1840)   HTML    PDF(pc) (13524KB)(5381)       Save
    Timely and accurate change detection of buildings provides important information for urban planning and management.Accompanying with the rapid development of satellite remote sensing technology,detecting building changes from high-resolution remote sensing images have received wide attention.Given that pixel-based methods of change detection often lead to low accuracy while object-based methods are complicated for uses,this research proposes a method that combines pixel-based and object-based methods for detecting building changes from high-resolution remote sensing images.First,based on the multiple features extracted from the high-resolution images,a random forest classifier is applied to detect changed building at the pixel level.Then,a segmentation method is applied to segement the post-phase remote sensing image and to get post-phase image objects.Finally,both changed building at the pixel level and post-phase image objects are fused to recognize the changed building objects.Multi-temporal QuickBird images are used as experiment data for building change detection with high-resolution remote sensing images,the results indicate that the proposed method could reduce the influence of environmental difference,such as light intensity and view angle,on building change detection,and effectively improve the accuracies of building change detection.
    Reference | Related Articles | Metrics
    Contour Cluster Shape Analysis for Building Damage Detection from Post-earthquake Airborne LiDAR
    HE Meizhang, ZHU Qing, DU Zhiqiang, ZHANG Yeting, HU Han, LIN Yueguan, QI Hua
    Acta Geodaetica et Cartographica Sinica    2015, 44 (4): 407-413.   DOI: 10.11947/j.AGCS.2015.20130785
    Abstract1535)   HTML    PDF(pc) (1722KB)(5344)       Save

    Detection of the damaged building is the obligatory step prior to evaluate earthquake casualty and economic losses. It's very difficult to detect damaged buildings accurately based on the assumption that intact roofs appear in laser data as large planar segments whereas collapsed roofs are characterized by many small segments. This paper presents a contour cluster shape similarity analysis algorithm for reliable building damage detection from the post-earthquake airborne LiDAR point cloud. First we evaluate the entropies of shape similarities between all the combinations of two contour lines within a building cluster, which quantitatively describe the shape diversity. Then the maximum entropy model is employed to divide all the clusters into intact and damaged classes. The tests on the LiDAR data at El Mayor-Cucapah earthquake rupture prove the accuracy and reliability of the proposed method.

    Reference | Related Articles | Metrics
    Hyperspectral Image Classification Based on the Weighted Probabilistic Fusion of Multiple Spectral-spatial Features
    ZHANG Chunsen, ZHENG Yiwei, HUANG Xiaobing, CUI Weihong
    Acta Geodaetica et Cartographica Sinica    2015, 44 (8): 909-918.   DOI: 10.11947/j.AGCS.2015.20140544
    Abstract1551)   HTML    PDF(pc) (14814KB)(5338)       Save

    A hyperspectral images classification method based on the weighted probabilistic fusion of multiple spectral-spatial features was proposed in this paper. First, the minimum noise fraction (MNF) approach was employed to reduce the dimension of hyperspectral image and extract the spectral feature from the image, then combined the spectral feature with the texture feature extracted based on gray level co-occurrence matrix (GLCM), the multi-scale morphological feature extracted based on OFC operator and the end member feature extracted based on sequential maximum angle convex cone (SMACC) method to form three spectral-spatial features. Afterwards, support vector machine (SVM) classifier was used for the classification of each spectral-spatial feature separately. Finally, we established the weighted probabilistic fusion model and applied the model to fuse the SVM outputs for the final classification result. In order to verify the proposed method, the ROSIS and AVIRIS image were used in our experiment and the overall accuracy reached 97.65% and 96.62% separately. The results indicate that the proposed method can not only overcome the limitations of traditional single-feature based hyperspectral image classification, but also be superior to conventional VS-SVM method and probabilistic fusion method. The classification accuracy of hyperspectral images was improved effectively.

    Reference | Related Articles | Metrics