Table of Content

20 November 2023, Volume 52 Issue 11

Previous Issue    Next Issue

Review

Development status and trends of Imaging Geodesy

LI Zhenhong, ZHU Wu, YU Chen, ZHANG Qin, YANG Yuanxi

2023, 52(11):  1805-1834.  doi:10.11947/j.AGCS.2023.20230003

Asbtract ( )   HTML ( )   PDF (19962KB) ( )  

References | Related Articles | Metrics

The utilization of remote sensing satellites has led to a significant increase in the use of imagery for acquiring Earth-related data. These satellites offer high observational accuracy and spatio-temporal resolutions, making them valuable tools for obtaining geodetic parameters, such as the shape and size of our planet. This advancement has not only propelled the field of Geodesy but has also given rise to a new discipline known as Imaging Geodesy. Imaging Geodesy has become an interdisciplinary science of Geodesy, Remote Sensing, Photogrammetry and Computer Vision, and has played an important role in the fields of disaster reduction, environmental protection and new energy development. In this paper, the development, definition, key technologies, main contents and development trends of Imaging Geodesy are summarized. With the development of remote sensing satellites and corresponding image processing technologies, the developmental history of Imaging Geodesy can be divided into four stages, i.e. beginning, leaping, in-depth innovation, and comprehensive application. According to the locations of its research objects, Imaging Geodesy's research contents include: observing the Earth's atmosphere, monitoring the Earth's surface, and determining the physical structure of the Earth's interior. To illustrate the practical applications of Imaging Geodesy, five scenarios are presented: generation of digital elevation models, monitoring of atmospheric water vapor, detection and monitoring of active landslides, investigation of earthquake cycles and monitoring of soil moisture. One major challenge of Imaging Geodesy is how to fuse and process the big data from multiple sources in near real time. It is believed that this paper would assist geodesy scholars in better understanding Imaging Geodesy, enabling them to integrate this emerging field into their teaching and research and to contribute to national strategies and project developments.

Geodesy and Navigation

Multi-station joint processing model for seafloor geodetic coordinate time series

SUN Yue, XUE Shuqiang, HAN Baomin, XIAO Zhen

2023, 52(11):  1835-1843.  doi:10.11947/j.AGCS.2023.20220203

Asbtract ( )   HTML ( )   PDF (4273KB) ( )  

References | Related Articles | Metrics

The repeated observation of seafloor geodetic network can be used to study the seafloor plate technic and the process of marine disaster such as seafloor earthquake. However, affected by observation condition, power supply and other factors, it is hard to achieve continuous observation for a long time. To solve the displacement compensation and site offset calculation problems in the replacement of old and new underwater geodetic stations in time series observations, the center point method can be used to calculate the displacement relative to the virtual center point coordinates of the underwater geodetic station network, and then construct the underwater geodetic coordinate the series to monitor underwater tectonic movement. For the same problem. Referring to the maintenance way of the terrestrial reference frame, we directly use the time series observation data of the seafloor geodetic network that may have discontinuities, and propose a multi station joint processing model of the seafloor geodetic coordinates based on the reference protocol epoch, in other words, in a regional geodetic network the coordinates of each station are treated as local parameters, and the velocity is used as a common parameter. The new proposed method is not only suitable for the geodetic dynamic reference frame maintenance, but also can be conducive to the implementation of fine quality control of the coordinate time series of each geodetic station in the regional network. The experimental results show that, the difference of annual velocity estimation difference of seafloor geodetic network between the two methods is about 3 mm/a. The new proposed method is a substitute for the center point method, and the robust estimation results are more reliable. This study provides a way for maintaining the national seafloor space benchmark.

Underwater gravity FKF matching enhancement algorithm based on local SCHA modeling

HUANG Yan, LI Shanshan, LI Xinxing, SONG Xingguang, FAN Diao, WAN Hongfa

2023, 52(11):  1844-1857.  doi:10.11947/j.AGCS.2023.20220609

Asbtract ( )   HTML ( )   PDF (7966KB) ( )  

References | Related Articles | Metrics

An underwater gravity matching navigation method based on federal Kalman filter (FKF) and spherical cap harmonic analysis (SCHA) modeling of local gravity field is proposed. Firstly, based on the well posed boundary value problem, the gravity gradient complex combination observation of FKF subsystem filter is constructed. Then, adjusted spherical harmonic analysis (ASHA) is used to optimize the spherical crown harmonic modeling method of local gravity field, so as to quickly establish a more accurate moving window spherical crown harmonic model between the local ocean gravity field centered on the matching point and the spatial position. Based on this model, the measurement equation of sub-filter is established. Finally, the prediction residual vector is used to design an adaptive information distribution factor to fuse the state estimation and covariance of each sub-filter to obtain the optimal estimator of inertial navigation position error. The experimental results show that the gravity FKF matching algorithm modeled by SCHA keeps the positioning error of 24-hour navigation within 1.1 n miles, and the navigation positioning accuracy is improved by more than 85%; The positioning accuracy of 10 day long navigation has been improved by 88.7%. The algorithm can overcome the defect of the inertial navigation system due to the accumulation of time error to some extent, improve the navigation and positioning accuracy of the system, and increase the robustness of the matching algorithm.

RTS state smoothing of GRACE Level-2 data

FENG Yong, CHANG Guobin, QIAN Nijia, WEI Zhengqiang, HUAN Yueyang, YANG Yifan

2023, 52(11):  1858-1872.  doi:10.11947/j.AGCS.2023.20220656

Asbtract ( )   HTML ( )   PDF (25336KB) ( )  

References | Related Articles | Metrics

The global surface mass variation obtained by using the unconstrained gravity recovery and climate experiment (GRACE) Level-2 spherical harmonic coefficient inversion has obvious north-south striping noise, which seriously affects the accuracy of regional surface mass anomaly estimation. The decorrelation and denoising kernel (DDK) filter introduced signal covariance matrix and regularization factor to deal with spherical harmonic coefficients to obtain spatial constrained solutions in order to better weaken striping errors and retain more real geophysical signals. DDK filtering ignores the correlation of spherical harmonic coefficients in time, and uses the state space (SS) model to represent the relation between spherical harmonic coefficients in adjacent months, and then realizes noise reduction through Kalman filtering, which is the state space DDK filtering method (SS-DDK). In the SS-DDK method proposed in this paper, the state vector only contains spherical harmonic coefficients, and the covariance matrix reflecting the strip error statistics is used as the observation noise covariance matrix in the state space model. The power law model is used to design the process noise covariance matrix, and the variance component factors are solved by iterative method. Finally, the RTS smooth solution was output instead of the Kalman filter solution as the final data processing result. The results show that there is no significant striping error in SS-DDK results worldwide. The root mean square deviation (RMSD) of the abnormal quality difference between each constraint solution and mascon solution was calculated. The RMSD of SS-DDK is 10.36 cm, which is smaller than that of any DDK filter. By comparing the equivalent water column height, annual amplitude and RMSD of all constraint solutions in the five regions for 135 months, it is found that in Greenland, the signal distortion caused by SS-DDK is less, only 49.8 cm. In other regions, SS-DDK's striping and retention capabilities are somewhat similar to those of DDK3—5 filtering, and superior to all DDK filtering in some time periods. An uncertainty analysis of the estimation results shows that the global uncertainty size of the SS-DDK solution is 2.20 cm, which is between DDK2 and DDK3 in the selected regions. From the point of view of geoid degree error, the noise level of SS-DDK solution is lower than that of DDK4—8, and the signal retention ability is comparable to DDK2—3. The addition of simulation experiments further demonstrates the good performance of SS-DDK in terms of de-striping and signal retention.

GNSS real-time monitoring technology of expansive soil slope

HUANG Guanwen, CHEN Zi, XU Yongfu

2023, 52(11):  1873-1882.  doi:10.11947/j.AGCS.2023.20220562

Asbtract ( )   HTML ( )   PDF (6102KB) ( )  

References | Related Articles | Metrics

Expansive soil landslide is harmful to the project because of its universality, fragmentation, repetition, concealment and other characteristics. The long-term real-time deformation monitoring is the premise for the prevention and control of expansive soil disasters. On the basis of the first generation of expansive soil slope GNSS monitoring technology and experiment, the research team made two improvements:① A layered GNSS/total station integrated monitoring device is designed to realize layered real-time monitoring of expansive soil slope. ② A GNSS real-time monitoring technology of expansive soil slope with comprehensive multi-source parameters is proposed to improve the reliability and accuracy of real-time deformation monitoring results. Relevant technologies and equipment have been applied in the demonstration of expansive soil highway slope in Ningming, Guangxi, and the dynamic response characteristics and induced sliding reasons of GNSS deformation and multi-source monitoring data have been analyzed. An expansive soil landslide was successfully monitored, and the research results are replicable and popularized.

A drought index derived from a combination of GNSS GRACE/GRACE-FO and meteorological data

YAO Chaolong, CHEN Yongxin, LUO Zhicai, LI Qiong, YE Xuemiao, WEN Jinjie

2023, 52(11):  1883-1891.  doi:10.11947/j.AGCS.2023.20220484

Asbtract ( )   HTML ( )   PDF (14628KB) ( )  

References | Related Articles | Metrics

Developing the combined drought index (CDI) integrating multi-source data is of important significance for accurate, objective and comprehensive drought monitoring and assessment. In this study, we built a novel CDI reflecting hydro-meteorological variables in Southwest China based on the principle component analysis. The proposed CDI integrates drought indices derived from Global Navigation Satellite System (GNSS) vertical displacements and time-variable gravity fields from Gravity Recovery and Climate Experiment (GRACE)/GRACE Follow-On (GRACE-FO) as well as the commonly used meteorological composite index (CI) in China. The results show that compared to the individual CI index and the drought indices based on GNSS, GRACE/GRACE-FO data, correlation coefficients between the proposed CDI and self-calibrating palmer drought severity index (scPDSI) improved significantly, with the maximum value of 0.84; the number of sites with improved correlations for the individual drought indices account for 100%, 93%, and 67%, respectively;the averaged correlation coefficients of all studied sites increased from 0.48, 0.34, 0.57 to 0.64, respectively. The results indicate the effectiveness of integrating drought information containing in multi-source data in the proposed CDI index, which could help to improve regional drought monitoring.

Photogrammetry and Remote Sensing

Remote sensing image fusion method combining improved Laplacian energy and parameter adaptive dual-channel unit-linking pulse coupled neural network

GONG Xunqiang, HOU Zhaoyang, LÜ Kaiyun, LU Tieding, XIA Yuanping, LI Weijun

2023, 52(11):  1892-1905.  doi:10.11947/j.AGCS.2023.20220541

Asbtract ( )   HTML ( )   PDF (46615KB) ( )  

References | Related Articles | Metrics

The fusion of backscattering information of SAR images and spectral information of optical images is one of the important means to improve the accuracy of land cover classification, and multi-scale transform is an effective fusion method. However, the fusion rules of multi-scale transform method are usually designed based on local feature information and pulse coupled neural network models, and there are some problems such as limited ability to extract structural and detailed information, complex parameter settings of pulse coupled neural network and poor spatial correlation. To this end, a remote sensing image fusion method based on improved Laplacian energy and parameter adaptive dual-channel unit-linking pulse coupled neural network (ULPCNN) is proposed in this paper. This method combines the component substitution method and the multi-scale transform method. Firstly, the multi-spectral image is transformed by IHS to obtain the intensity component I, and then the intensity component I and SAR image are decomposed by non-subsampled shearlet transform (NSST) to obtain high and low frequency sub-bands.Secondly, a fusion rule combining weighted local energy and weighted sum of eight-neighborhood-based modified Laplacian is used for low frequency sub-bands, a fusion rule of the parameter adaptive dual-channel ULPCNN method is used for the high frequency sub-bands, the multi-scale morphological gradient of the high-frequency sub-band is used as the link strength, and the adaptive representation of other parameters is realized according to the OTSU threshold and image strength. Finally, the NSST inverse transform and the IHS inverse transform are performed in turn to obtain the fusion image, and the random forest classifier is selected to classify the fusion image for land cover. The experimental results show that the proposed method has the overall best performance in eleven fusion evaluation indexes and land cover classification accuracy compared with 13 other methods. The overall accuracy and Kappa coefficient of land cover classification improved by 8.350% and 0.107, respectively, in area 1, and by 6.896% and 0.091, respectively, in area 2 compared with those of the original multi-spectral images.

Multi-source remote sensing image bidirectional consistent registration based on learning feature

ZHANG Yongxian, MA Guorui, ZI Shuanjin, MEN Hang

2023, 52(11):  1906-1916.  doi:10.11947/j.AGCS.2023.20220412

Asbtract ( )   HTML ( )   PDF (26864KB) ( )  

References | Related Articles | Metrics

A robust registration method with bidirectional consistent transformation is proposed to solve the problem of multi-source remote sensing image relatively poor registration effect due to large nonlinear radiation and geometric distortion. First, the fine-tuned ResNet101 network model was utilized to extract images learning features. To improve the reliability of the corresponding feature matching, we designed a bidirectional consistency feature matching model in the feature matching stage. Then, robust registration was achieved by using a parametric regression transformation model with weight based on a small lightweight network. In our experiments, we tested the proposed algorithm using Google Earth images, satellite images, UAV images and Google Earth-satellite-UAV images, and compared it with the several typical methods. The results show that the proposed method has advantages in the accuracy, efficiency and robustness, and achieves automatic registration accuracy almost within 2 pixels.

A method for crack detection and sample generation based on low rank representation and deep learning

ZHAO Xuhui, XIE Mengjie, YANG Biao, YANG Gang, GAO Zhi

2023, 52(11):  1917-1928.  doi:10.11947/j.AGCS.2023.20220490

Asbtract ( )   HTML ( )   PDF (7021KB) ( )  

References | Related Articles | Metrics

With the rapid development of society, large infrastructures such as roads, tunnels, and bridges are built, significantly improving people's living standards. But many new or existing infrastructures bring tremendous workload and challenge traditional manual-based security inspection. Therefore, it is of great urgency to automatically monitor infrastructures' health status and map anomalies accordingly. In this paper, we focus on bridges and propose a pavement crack detection method via synergizing low rank representation (LRR) and deep learning techniques to address the problems of low intelligence and insufficient generalization of existing methods. In the first stage, we automatically discriminate most crack frames from the long sequence with a consistent pavement base by LRR. Then we localize the cracks and obtain pixel-wise masks with post-processing based on grayscale and geometry clues in images. In the second stage, we formulate the problem as a semantic segmentation task and propose a network leveraging multi-level features and atrous spatial pyramid pooling (ASPP) for robust performance in various scenes. Finally, we train this network with generated pixel-wise samples from LRR. Extensive experiments on a wide range of pavements demonstrate that our method significantly outperforms many state-of-the-art approaches in terms of both accuracy and automaticity, which can also be adopted in other scenarios.

Geometric positioning accuracy improvement method without ground control points for global orthorectification of GF-3

LI Xin, JIANG Boyang, WANG Taoyang, ZHANG Guo, CUI Hao, CHENG Qian

2023, 52(11):  1929-1940.  doi:10.11947/j.AGCS.2023.20220512

Asbtract ( )   HTML ( )   PDF (11515KB) ( )  

References | Related Articles | Metrics

The GF-3 satellite is the first C-band multi-polarization high-resolution synthetic aperture radar (SAR) satellite. However, the initial positioning accuracy of GF-3 satellite images is unsatisfaction, it is difficult to directly meet the application requirements of large-area mapping. This paper proposes a large-area SAR orthoimage production method without ground control points (GCP), which significantly improves the geometric positioning accuracy and processing efficiency for SAR image processing. Firstly, the initial positioning accuracy of single-scene SAR images is improved by geometric recalibration. Secondly, the SAR-SGFM matching algorithm is used combined with the multi-node parallel matching strategy to automatically extract the tie points. The image geometric model is refined by the large-area adaptive block adjustment method and the radiometric equalization of adjacent images is realized by using the radiometric consistency processing algorithm. Based on the production and experimental verification of global SAR orthoimages based on the method in this paper, the absolute positioning accuracy of SAR orthoimage is better than 10 meters (1 pixel), the relative positioning accuracy is better than 1 pixel and the radiation of adjacent images is excessively smooth. The results show that the proposed method is effective and feasible in the production of large-scale SAR orthorectification image.

An unsupervised meta learning method for hyperspectral images few-shot classification

GAO Kuiliang, LIU Bing, YU Anzhu, XU Baiqi, HU Wei, HU Jiawei

2023, 52(11):  1941-1952.  doi:10.11947/j.AGCS.2023.20220410

Asbtract ( )   HTML ( )   PDF (5167KB) ( )  

References | Related Articles | Metrics

Aiming at the problem of hyperspectral images (HSIs) few-shot classification, an unsupervised meta learning method is proposed in this paper. This method can utilize unlabeled samples for unsupervised meta learning, significantly reducing the dependence on a large number of labeled samples while effectively improving the accuracy of HSIs few-shot classification. Firstly, based on the idea of self-supervised learning, multiple different augmentation features of the same sample are generated through principal component analysis and data augmentation methods, to form a large number of different tasks and perform meta-training on the designed model. Then, a few labeled samples randomly selected from target HSIs are used to fine-tune the model, and all labeled samples are used for classification test to evaluate the few-shot classification performance of the model. Moreover, the voting strategy is introduced in the fine-tuning and classification phase, to further improve classification accuracy. The proposed method can perform sufficient unsupervised meta-training under the condition of zero labeled sample, breaking through the bottleneck and limitation of the supervised meta learning methods requiring a large number of source labeled samples. Experiments on three public datasets show that the proposed method can obtain better classification results than existing advanced methods in the few-shot scenario.

The method of variable scale mesh primitive extraction for monomeric and structural reconstruction of buildings

LIU Haibing, QU Yingjie, YAN Qingsong, DENG Fei

2023, 52(11):  1953-1961.  doi:10.11947/j.AGCS.2023.20220275

Asbtract ( )   HTML ( )   PDF (8869KB) ( )  

References | Related Articles | Metrics

The existing region-growing algorithm extracts planar primitives inaccurately and irregularly, ignoring the geometric structures with smaller scales. The method of variable scale mesh primitive extraction for monomeric and structural reconstruction of buildings is proposed in this paper, which uses a multi-scale region-growing algorithm to extract the corresponding planar primitives from the geometric structures of different scale sizes of the mesh, improving the accuracy and completeness of planar primitive extraction. The topological quality of planar primitives is further improved by topology optimization of planar primitives, and the reconstruction accuracy of polygonal surface model is enhanced. And the area-priority strategy is used to improve the merging efficiency of co-planar primitives. The experimental results show that this method can extract the planar primitives more accurately, preserve the small-scale geometry of the buildings, and generate a more compact and structural polygonal surface model of the buildings.

Cartography and Geoinformation

Theoretical system and potential research issues of spatial similarity relations

YAN Haowen

2023, 52(11):  1962-1973.  doi:10.11947/j.AGCS.2023.20220695

Asbtract ( )   HTML ( )   PDF (1289KB) ( )  

References | Related Articles | Metrics

Spatial similarity relation is widely used in description and matching of spatial objects, retrieval and renewal of spatial databases, and spatial recognition and spatial reasoning. However, there exist only few trivial achievements in spatial similarity relations, for spatial similarity relations are usually comprehensive and complex, and they cannot be described and expressed formally and cannot be calculated conveniently, either. Therefore no theoretical system of spatial similarity relations has been constructed by far. To fill the gap, this paper proposes a theoretical system for spatial similarity relations. Based on the system, this paper firstly presents the definition, classification systems, features and influence factors of spatial similarity relations, and then addresses the calculation methods of spatial similarity relations at the same scale space and different scale spaces, respectively. Further, it presents some applications of spatial similarity relations. Finally, it gives a number of potential research issues in spatial similarity relations. This work is a useful complementary of the theory of spatial relations and possibly makes the research in spatial similarity relations more rigorous, deeper and more systematic in future.

A vessel trajectory data compression method combining spatio-temporal and semantic features

LIU Haiyan, GUO Xuan, LIU Junnan

2023, 52(11):  1974-1982.  doi:10.11947/j.AGCS.2023.20210658

Asbtract ( )   HTML ( )   PDF (1647KB) ( )  

References | Related Articles | Metrics

A large amount of vessel trajectory data with a wide coverage and strong timeliness has been accumulated in the big data era, whose spatio-temporal and semantic state changes can be represented by some trajectory points. To increase trajectory retrieval efficiency and reduce storage and transmission burden, this paper proposes a trajectory compression method upon trajectory spatio-temporal features and navigation semantic features. First, spatio-temporal and semantic features of vessel trajectory are analyzed, and a trajectory data compression method is proposed. Then, trajectory points with significant spatio-temporal and semantic features are extracted by Douglas-Peucker and sliding window methods to construct spatio-temporal and semantic ranks, respectively. To synthesize these features, the weighted fusion method is introduced to combine these ranks, thus ranking the trajectory points in order. Finally, vessel trajectory can be compressed by calculating reserved point number from compression ratio. The proposed method is verified through comparative analysis of efficiency and quality, and a compression case. The experiments indicate that the method could not only reduce redundancy significantly, but also retain the dynamic semantics and spatio-temporal morphological features of driving, thus providing a solid foundation for trajectory mining.

An adaptive display approach to saving energy of electronic maps with consideration of visual hierarchy

WU Mingguang, CHENG Ziming

2023, 52(11):  1983-1993.  doi:10.11947/j.AGCS.2023.20220460

Asbtract ( )   HTML ( )   PDF (21139KB) ( )  

References | Related Articles | Metrics

The high energy consumption of electronic map display is one of the problems that needs to be solved urgently in the current map design and application field. Aiming at the problem that the existing electronic map energy-saving display methods are difficult to maintain visual hierarchy, this paper summarizes three visual hierarchy structures of map colors, designs a quantitative expression model for visual hierarchy, and proposes an adaptive energy-saving display optimization method for electronic maps. This method considers both visual hierarchy quality and map energy consumption, defines the map energy saving problem as a “quality-energy consumption” dual-objective optimization problem, uses a heuristic search algorithm to find energy-saving color schemes, and significantly reduces display power consumption with slight changes to map appearance. This method is compared with the semantically-enriched method, and a map reading experiment is designed using electronic maps of different scales. The results show that the proposed method is superior to the comparison method in terms of effectiveness, efficiency and color consistency, and can be widely used in the energy-saving display of electronic maps and mobile navigation maps to improve the battery life of the equipment.

A recognition approach for compound grid pattern of urban road networks

WANG Andong, WU Fang, GONG Xianyong, ZHAI Renjian, LIU Chengyi, QIU Yue, ZHANG Hanxue

2023, 52(11):  1994-2006.  doi:10.11947/j.AGCS.2023.20220528

Asbtract ( )   HTML ( )   PDF (24952KB) ( )  

References | Related Articles | Metrics

As the skeleton of urban cities, the spatial pattern recognition of road networks is of great significance for map generalization, spatial data mining, and multi-scale representation. This paper presents an approach to recognizing the compound grid pattern of road networks with local heterogeneity based on road meshes. Firstly, the multilevel cognitive characteristics of the linear and grid pattern of road meshes are analyzed, and the multilevel cognitive order, which from basic mesh, compound mesh to regular pattern, is proposed. Secondly, the recognition methods of inclusion relationship, parallel relationship, and linear pattern between road meshes are designed considering the composability, linearity, and extensibility of compound linear pattern. Finally, the linear patterns are combined and decomposed to extract the compound grid pattern of road meshes. Experiments show that the proposed method is effective for compound grid pattern recognition with the agreements of human spatial cognitive characteristics.

Summary of PhD Thesis

Spatio-temporal continuous sensing method for high-resolution impervious surface mapping in the urban agglomeration

HUANG Min

2023, 52(11):  2007-2007.  doi:10.11947/j.AGCS.2023.20220191

Asbtract ( )   HTML ( )   PDF (777KB) ( )  

Related Articles | Metrics

Research on antarctic ice sheet change and influencing factors based on satellite altimetry technology

YANG Quanming

2023, 52(11):  2008-2008.  doi:10.11947/j.AGCS.2023.20220427

Asbtract ( )   HTML ( )   PDF (784KB) ( )  

Related Articles | Metrics

Adjusting, merging, and spatial downscaling for satellite precipitation estimates over Chinese mainland

SHEN Zhehui

2023, 52(11):  2009-2009.  doi:10.11947/j.AGCS.2023.20220435

Asbtract ( )   HTML ( )   PDF (782KB) ( )  

Related Articles | Metrics

Intelligent detection of target in complex nearshore scenes based on SAR image

GENG Xiaomeng

2023, 52(11):  2010-2010.  doi:10.11947/j.AGCS.2023.20220450

Asbtract ( )   HTML ( )   PDF (809KB) ( )  

Related Articles | Metrics

Research on the development of typical urban agglomerations and their impact on vegetation changes considering impervious surface

TANG Yun

2023, 52(11):  2011-2011.  doi:10.11947/j.AGCS.2023.20220457

Asbtract ( )   HTML ( )   PDF (777KB) ( )  

Related Articles | Metrics

Deep learning based attribute learning for optical remote sensing image classification

XU Wenjia

2023, 52(11):  2012-2012.  doi:10.11947/j.AGCS.2023.20220469

Asbtract ( )   HTML ( )   PDF (785KB) ( )  

Related Articles | Metrics

Multi-source laser scanning data integration processing and application of key technologies for expressway reconstruction and expansion

LI Shengfu

2023, 52(11):  2013-2013.  doi:10.11947/j.AGCS.2023.20220487

Asbtract ( )   HTML ( )   PDF (778KB) ( )  

Related Articles | Metrics

Super-resolution persistent scatterer interferometry

ZHANG Hao

2023, 52(11):  2014-2014.  doi:10.11947/j.AGCS.2023.20220511

Asbtract ( )   HTML ( )   PDF (784KB) ( )  

Related Articles | Metrics