Table of Content

20 October 2023, Volume 52 Issue 10

Previous Issue    Next Issue

Review

Review of visual SLAM environment perception technology and intelligent surveying and mapping application

ZHANG Jixian, LIU Fei

2023, 52(10):  1617-1630.  doi:10.11947/j.AGCS.2023.20220240

Asbtract ( )   HTML ( )   PDF (3053KB) ( )  

References | Related Articles | Metrics

Visual SLAM(simultaneous localization and mapping) technology is one of the core technologies of modern intelligent equipment environment perception. It is an important factor driving the development of modern surveying and mapping production mode to intelligent surveying and mapping. Focusing on the visual SLAM environment perception technology, this paper combs the brief technical framework, important algorithms and mapping application mode of typical visual SLAM environment perception in the past 30 years according to the five aspects of feature method, direct method, visual fingerprint database, semantic SLAM and brain-like SLAM; summarizes and analyzes the development trend of visual SLAM environment perception technology in intelligent environment interaction perception, crowdsourcing instant information processing, and diversified perception data service; discusses the application mode of visual SLAM environment perception technology in interactive navigation and positioning, digital twin city construction, real-time surface monitoring and interpretation, crowdsourcing map POI production, unattended geological disaster monitoring and deep space exploration supported by independent interactive ability. At present, the surveying and mapping industry is in a period of major development and transformation. With the rapid combination of visual SLAM environment perception technology and artificial intelligence technology, it will further enable the transformation of surveying and mapping production mode and improve the level of intelligent production and service.

Geodesy and Navigation

Analyzing the geolocation precision of TDOA using formation-flying cluster of three microsatellites

SONG Xiaoyong, MAO Yue, ZONG Wenpeng, WANG Long, FENG Laiping

2023, 52(10):  1631-1639.  doi:10.11947/j.AGCS.2023.20220269

Asbtract ( )   HTML ( )   PDF (9995KB) ( )  

References | Related Articles | Metrics

Geolocating of the radio-frequency(RF) emitters with formation-flying cluster of microsatellite has become an efficient means to monitor the non-cooperative RF targets on the earth's surface, and the key technique involved is to geolocate the emitters with space-based TDOA measurement. The main factor impacting the space-based TDOA measurement is analyzed in this paper. Two TDOA geolocation methods, namely the single epoch geolocation with the constraint of geodetic height and multi-epoch geolocation are presented for the formation-flying cluster of three microsatellites, and the precisions are validated by simulation test. The results show that the precision of the single epoch geolocation method of TDOA and the multi-epoch geolocation can meet 510 and 110 m, respectively, when the non-cooperative targets on sea surface are monitored by the equilateral triangular formation-flying microsatellites. The geolocation error becomes more remarkable for targets near the satellite ground-track when the equilateral triangular formation satellites adopt the combined configuration with one satellite at a higher latitude and the other two at lower ones.

Robust GNSS/SINS positioning based on the SE₂(3)-EKF framework

LI Xin, MENG Shuolin, HUANG Guanwen, ZHANG Qin, LI Hanxu

2023, 52(10):  1640-1649.  doi:10.11947/j.AGCS.2023.20220526

Asbtract ( )   HTML ( )   PDF (6055KB) ( )  

References | Related Articles | Metrics

For GNSS/SINS integrated navigation, the large errors, such as attitude misalignment angle, will cause the inconsistent coordinates definition of state error and large linearization error, thus the performance of traditional filtering and positioning is reduced, especially in the complex GNSS observation environment. In this paper, the attitude, velocity, and position states are reconstructed as a special SE₂(3) group element, considering the bias of gyro and accelerometer, a group-vector mixed error model is formed, and then one GNSS/SINS robust filtering algorithm (RLIEKF) based on left invariant measurement is studied. The superiority of the proposed method is validated via the vehicle integrated navigation experiment with large misalignment angle error and GNSS outliers in urban environment. The experimental results show that, compared with traditional EKF method, the attitude angle error is considered in time update and GNSS measurement update of the proposed RLIEKF, thus it has a fast convergence speed under different large misalignment angles, without complicated and long-time attitude alignment steps, which can better deal with the problem such the interrupt GNSS signal during a short time. Because the accuracy of innovation is significantly improved, thus it is more robust to complex observation environment, and with a fast computational efficiency, therefore it has excellent engineering practical value.

Optimization algorithm for analytical downward continuation based on improved radial derivative

MA Jian, ZHAI Zhenhe, FENG Changqiang, GUAN Bin, WANG Yunpeng, LI Duan

2023, 52(10):  1650-1660.  doi:10.11947/j.AGCS.2023.20220625

Asbtract ( )   HTML ( )   PDF (5622KB) ( )  

References | Related Articles | Metrics

Analytical continuation algorithm is an important continuation method for the potential field, which has important application value in the construction of the (quasi-) geoid or vertical deflection models based on the second or third geodetic boundary-value theory. Compared with Poisson continuation, the analytical continuation algorithm is simpler and faster. The calculation of the radial derivative is crucial for the analytical continuation algorithm. However, the traditional method for the radial derivative of the analytical continuation introduces a certain approximation error. An improved method for radial derivative is proposed in this paper. The optimization of the analytical continuation algorithm is then realized. In this research, it is proved by spherical harmonic method that the improved radial derivative is closer to the theoretically true radial derivative than the traditional one. The conclusion is displayed by the longitude and latitude profiles. The test of a large mountainous area conducted in central China shows that the accuracy of the improved radial derivative is 32.45% higher than that of the traditional radial derivative. When the errors contained in the gravity data are 1, 2, 3 and 4 mGal, the downward continuation accuracies of analytical continuation based on the improved radial derivative is 29.04%, 19.48%, 10.12% and 2.65% higher than that of the traditional analytical continuation, respectively. Theoretical analysis and test proves the effectiveness of the analytical downward continuation based on the improved radial derivative, which is useful in the geodetic boundary-value problem.

Combining spatio-temporal weighting with reanalysis data for filling in GNSS PWV time series

ZHAO Qingzhi, DU Zheng, YAO Yibin, YAO Wanqiang

2023, 52(10):  1661-1668.  doi:10.11947/j.AGCS.2023.20220241

Asbtract ( )   HTML ( )   PDF (4101KB) ( )  

References | Related Articles | Metrics

Precipitable water vapor (PWV) is one of the most critical parameters in the troposphere, and the long time series of continuous PWV has an essential impact on long-term climate change studies. However, due to the influence of external factors, the current long time series of PWV acquired by GNSS have missing data or poor resolution, which cannot meet the application needs of long time series analysis. This paper proposes a spatio-temporal weighted (STW) method to fill in the PWV long time series to address this problem. This method considers both the spatio-temporal variability of water vapor over GNSS stations and assigns different weights to the spatio-temporal variability of PWV according to the station locations. An experiment tested the STW using the Crustal Movement Observation Network of China (CMONOC) and the ECMWF 5th generation global atmospheric reanalysis dataset ERA5. The results show that the proposed STW method outperforms the traditional linear interpolation and period model methods in terms of missing data and PWV long time series resampling at different time scale resolutions and can obtain more reliable, accurate, and complete PWV long time series.

A multi-beam outlier automatic filtering algorithm combining uncertainty and density clustering method

WANG Junsen, JIN Shaohua, BIAN Gang, CUI Yang, LONG Zhenyu

2023, 52(10):  1669-1678.  doi:10.11947/j.AGCS.2023.20220579

Asbtract ( )   HTML ( )   PDF (6425KB) ( )  

References | Related Articles | Metrics

Based on the reproduction of CUBE filtering algorithm, this paper proposes a multibeam automatic outlier filtering algorithm combining uncertainty and density clustering method in reference of CUBE's assimilation model. In this paper, we use the DBSCAN to cluster the bathymetry values, use Kalman filter to estimate bathymetry values of the node, and select the bathymetry hypothesis with minimum uncertainty as true bathymetry values of the node. The measured data and simulation results show that the CUBE filtering algorithm cannot completely eliminate the continuous outliers, while the algorithm in this paper can clean up the continuous outliers better. Our algorithm is clear, simple and reliable, and can clean up many outliers in the case of poor data quality, which possesses practical engineering application value.

Photogrammetry and Remote Sensing

Motion state monitoring and estimation of ship target based on optical satellite video

WANG Taoyang, HONG Jianzhi, ZHANG Guo, JIANG Yonghua, LI Xin, DONG Tiancheng, HAN Yuqi, WANG Jingyin, YANG Yapeng, XU Congan

2023, 52(10):  1679-1692.  doi:10.11947/j.AGCS.2023.20220257

Asbtract ( )   HTML ( )   PDF (12822KB) ( )  

References | Related Articles | Metrics

Optical satellite video can continuously monitor moving targets, which has become a current research hotspot. However, most of the current researches only focus on image-side object detection, tracking and trajectory extraction, and do not make full use of the imaging geometric parameters for high-precision quantitative estimation of the target motion state. To solve this problem, this paper proposes a method for quantitative estimation of ship target motion state based on optical satellite video. Firstly, the first frame of satellite video is accurately orientated. Then, the video is stabilized through inter-frame registration. Aiming at the problem of low positioning accuracy of the rectangular anchor tracking method, a robust tracking method for surface ships considering rotation and scale estimation is proposed for target tracking of satellite video. Finally, the geometric model is used to estimate the ground motion trajectory, speed and direction of the target through object mapping. The effectiveness of the method in this paper is verified by carrying out simultaneous observation experiments between satellites and ships on the sea based on Jilin-1 optical video satellite. Under the condition of sparse control points, the experimental results show that the geometric positioning accuracy of the ship target is 1.60 meters, the speed accuracy is 0.18 m/s, and the direction accuracy is 4.05°, which is significantly improved compared with similar methods.

GLFFNet model for remote sensing image scene classification

WANG Wei, DENG Jiwei, WANG Xin, LI Zhiyong, YUAN Ping

2023, 52(10):  1693-1702.  doi:10.11947/j.AGCS.2023.20220286

Asbtract ( )   HTML ( )   PDF (10393KB) ( )  

References | Related Articles | Metrics

Traditional scene classification models cannot perform multi-scale key feature extraction in remote sensing images in a lightweight and efficient manner. Deep learning methods generally have shortcomings such as large amount of calculation and slow convergence speed. In view of the above problems, this paper makes full use of the ability of CNN structure and Transformer structure to extract features at different scales, and proposes a feature extract module, named global and local features fused (GLFF) block. Based on this module, a lightweight remote sensing image scene classification model, GLFFNet, is designed, which has better local information and global information extraction ability. In order to verify the effectiveness of GLFFNet, this paper uses the open-source remote sensing image datasets RSSCN7 and SIRI-WHU to verify the complexity and recognition ability of GLFFNet and other deep learning networks. Finally, GLFFNet achieves recognition accuracy of up to 94.82% and 95.83% on RSSCN7 and SIRI-WHU datasets, respectively, which is better than other state-of-the-art models.

Semantic segmentation method of 3D scenes using dynamic graph CNN for complex city

ZHANG Rongting, ZHANG Guangyun, YIN Jihao

2023, 52(10):  1703-1713.  doi:10.11947/j.AGCS.2023.20220466

Asbtract ( )   HTML ( )   PDF (12771KB) ( )  

References | Related Articles | Metrics

In photogrammetry and remote sensing community, 3D mesh is one of the final user products, which is widely applied in urban planning, navigation, etc. However, there are few works on semantic complex 3D mesh urban scene segmentation based on deep learning methods. Thus, a semantic segmentation method of 3D scenes using dynamic graph CNN for complex city (3Dcity-net) is proposed. By using mesh-inherent features containing 3D spatial information and texture information, a composite feature vector is proposed to represent each face in 3D mesh. To reduce the influence on semantic segmentation by the noise and redundant information in texture information, a principal component analysis (PCA) module is embedded in to the proposed 3D city-net. In order to alleviate the problem of semantic segmentation precision decrease caused by the unbalanced sample data, the focal loss function is used to replace the cross-entropy loss function. The Hessigheim 3D mesh data are utilized to perform experiments. The results of experiments show that the proposed method can obtain competitive semantic segmentation results on 3D mesh. The overall accuracy, Kappa coefficient, mean precision, mean recall, mean F₁ score, and mean IoU is 81.5%, 0.776, 73.0%, 58.4%, 62.6%, and 49.8%, respectively. Comparing to two state-of-the-art methods, the overall accuracy increases by 0.9%, and 8.3%, respectively.

Spatially enhanced spatio-temporal fusion model for heterogeneity regions

PI Xinyu, ZENG Yongnian, WANG Pancheng

2023, 52(10):  1714-1723.  doi:10.11947/j.AGCS.2023.20220519

Asbtract ( )   HTML ( )   PDF (16360KB) ( )  

References | Related Articles | Metrics

With the development of remote sensing technology, remote sensing data has been increased rapidly. However, due to the limitation of sensors and the influence of cloud and rain weather, it is difficult for a single sensor to obtain remote sensing images with high spatial-temporal resolution, which affects the study of global and regional environmental change to a certain extent. The development of spatio-temporal fusion theory and technology of remote sensing image provides an effective way to solve this problem. In recent years, a number of spatio-temporal fusion algorithms have been proposed. However, there are still challenges to spatio-temporal fusion for accuracy and spatial detail of heterogeneity areas. Therefore, this paper proposes a spatially enhanced spatio-temporal fusion model for heterogeneity regions. Firstly, based on the principle of spectral mixing analysis and the assumption of spatial characteristics invariance of remote sensing data, the low-resolution spectral changes are downscaled to high-resolution. Secondly, based on the assumption of spectral invariance relationship of remote sensing data with different resolutions, the final fusion image is obtained. The experimental results show that compared with the commonly used STARFM and FSDAF models, the spatially enhanced spatio-temporal fusion model for heterogeneity regions can not only predict the phenological change information of different ground features effectively, but also preserves the spatial details of the ground surface and enhances the spatial characteristics and fusion effect in heterogeneous surface area; The mean values of root mean square error (RMSE), correlation coefficient (r) and structural similarity index (SSIM) of the spatially enhanced spatio-temporal fusion model reached 0.024, 0.898 and 0.897, respectively. Compared with the commonly used STARF and FSDAF models, the mean value of RMSE decreased by 6.71% and 4.33%, respectively; the average value of r increased by 1.95% and 1.74%, respectively; the average value of SSIM increased by 2.33% and 2.08%, respectively. The proposed spatially enhanced spatio-temporal fusion model for heterogeneity regions has the advantages of high fusion accuracy, simple and easy operation, especially in the heterogeneous surface coverage area. Therefore, the spatially enhanced spatio-temporal fusion model for heterogeneity regions has good prospects in remote sensing applications.

A multi-feature clustering-based hierarchical filtering method for airborne LiDAR point clouds in complex landscapes

GUO Jiaojiao, CHEN Chuanfa, YAO Xi, LIU Yan, LIU Yating, LIU Panpan

2023, 52(10):  1724-1737.  doi:10.11947/j.AGCS.2023.20220371

Asbtract ( )   HTML ( )   PDF (8676KB) ( )  

References | Related Articles | Metrics

Airborne LiDAR point cloud filtering is the key step in point cloud processing, and its computational accuracy significantly affects the granularities of subsequent applications. However, it is difficult for the existing filtering algorithms to effectively distinguish object points from ground points in complex areas. Thus, a multi-feature clustering-based hierarchical filtering method is proposed in this paper. The proposed method first performs multi-feature point cloud clustering based on the geometric and physical information of point clouds; then, a ground-cluster identification method was used to accurately capture ground points in the area with breaklines; finally, the ground reference surface was constructed through the initial ground points, and the multi-scale hierarchical filtering was employed to further identify missed ground points. The new method was used to handle the point clouds in four different areas, and the filtering results were comprehensively compared with six state-of-the-art filtering algorithms. Results show that the new method has the lowest average total error, the best filtering performance and the highest stability.

Full-scale feature aggregation network for high-resolution remote sensing image change detection

JIANG Ming, ZHANG Xinchang, SUN Ying, FENG Weiming, RUAN Yongjian

2023, 52(10):  1738-1748.  doi:10.11947/j.AGCS.2023.20220505

Asbtract ( )   HTML ( )   PDF (9105KB) ( )  

References | Related Articles | Metrics

Using remote sensing imagery to detect changes is crucial for understanding land surface dynamics. In recent years, deep learning-based methods have become a focus area owing to their excellent feature extraction and representation ability. The fusion of multi-scale feature information is the key to improving change detection performance in fully convolutional network-based structural methods. Most of the previous methods use skip connection or dense connection structure, which improves the accuracy of change detection methods to a certain extent. However, such methods only fuse features at the same scale and lack sufficient information from multiple scales to achieve satisfactory results. In this paper, a full-scale feature aggregation network (FSANet) is proposed to solve the problem of remote sensing image change detection. Firstly, the features of the bi-temporal images are extracted using a siamese network, then the features are efficiently concatenated using a full-scale feature concatenation structure, and to prevent feature redundancy, the features are refined using a feature refinement module. Finally, to optimize model training, a multiscale supervision strategy is used. Multiple additional detections are output in the decoder, which calculate the final loss value together. To check the reliability of FSANet, we tested it on two public datasets, the LEVIR-CD and SVCD datasets. The experimental results show that the method outperforms other mainstream change detection methods, while having a good balance between accuracy and complexity.

Robust hyperspectral image clustering integrating total Bregman divergence and bipartite graph

LIU Han, WU Chengmao, LI Changxing

2023, 52(10):  1749-1759.  doi:10.11947/j.AGCS.2023.20220637

Asbtract ( )   HTML ( )   PDF (9106KB) ( )  

References | Related Articles | Metrics

In view of the high computational complexity and low clustering accuracy of traditional graph based spectral clustering algorithms, which are difficult to apply to large-scale data clustering, this paper proposes a graph based clustering algorithm to deal with hyperspectral image classification problems by using the similarity measurement between anchor points and data points, which is called robust hyperspectral image clustering integrating total Bregman divergence and bipartite graph (RTBBG). Firstly, the spatial information of hyperspectral image is added in the construction of bipartite graph, which makes full use of the rich spatial information of hyperspectral image. Secondly, the total Bregman divergence is used to optimize the traditional Euclidean distance as a similarity measure between data points and anchors, which makes the constructed bipartite graph more stable and enhances the robustness of the algorithm. Finally, K-means algorithm is used to directly cluster the spectra to obtain the final clustering results. The effectiveness of the algorithm is verified by testing on three large-scale hyperspectral datasets.

Cartography and Geoinformation

A spatio-temporal interpolation method based on Yang Chizhong filtering

YANG Jie, LIU Qiliang, FENG Tianqi, DENG Min

2023, 52(10):  1760-1771.  doi:10.11947/j.AGCS.2023.20220443

Asbtract ( )   HTML ( )   PDF (3103KB) ( )  

References | Related Articles | Metrics

Spatio-temporal interpolation is a fundamental task of spatio-temporal data analysis. Modeling of spatio-temporal dependencies in geospatial data plays a key role in spatio-temporal interpolation. When geospatial data is non-stationary and sparsely distributed, modeling of spatio-temporal dependencies is still challenging. On that account, this study developed a spatio-temporal interpolation method based on Yang Chizhong filtering. This method combined statistical and geometric methods to model spatio-temporal dependencies in geospatial data. Specifically, Yang Chizhong filtering and spatio-temporal product-sum model were first employed to construct the spatio-temporal fundamental variation function that quantitatively describes spatio-temporal dependencies in geospatial data. Then, an optimal linear unbiased estimation model for spatio-temporal data interpolation was built using the spatio-temporal fundamental variation function. We utilized simulated dataset, annual average temperature dataset in mainland China from 2000 to 2009 and daily average PM_2.5 concentration dataset in Beijing from May 2014 to April 2015 for experimental verification. Experimental results on both simulated and real-world datasets showed that the proposed method outperforms the three state-of-the-art methods, e.g., spatio-temporal Kriging, point estimation model of biased hospitals-based area disease estimation, and lightweight ensemble methods. The proposed method does not require the assumption of spatio-temporal stationarity, and can better adapt to sparsely distributed geospatial data.

Considering the spatial multi-scale neighborhood effect and time dependence into cellular automata model for urban growth simulation

WANG Haijun, CHANG Ruihan, LI Qiyuan, ZHOU Xiaoyan, WANG Quan, ZENG Haoran, LIU Yining, YUE Zhaoxi

2023, 52(10):  1772-1783.  doi:10.11947/j.AGCS.2023.20220244

Asbtract ( )   HTML ( )   PDF (8415KB) ( )  

References | Related Articles | Metrics

Under the strategic background of promoting new-type urbanization and implementing territorial space planning in the new era, urban growth research has gradually become a hot issue. The current urban growth simulation based on cellular automata (CA) lacks the analysis of multi-scale neighborhood effect of urban space, and the expression of time-dependent influence of long-term urban evolution process in transformation rules is not perfect, which simplifies the spatio-temporal dependence of urban growth. Future planning implementation scenarios cannot be simulated and deduced to serve national spatial planning. To solve the above problems, this paper constructs a CA model of urban growth (hereinafter referred to as Deep-CA), which takes spatial multi-scale neighborhood effect (3DCNN) and time dependence into account (ConvLSTM). Firstly, 3DCNN combining ordinary convolution and empty convolution is used to extract the multi-scale neighborhood effect of urban space. Then, ConvLSTM neural network is used to assimilate historical information, and the time dependence of long time series is considered. Thus, the suitability probability of urban growth is obtained. The land use data and its driving factors in Beijing from 1995 to 2015 are used to verify the scientific nature and applicability of the proposed CA model. The data from 1995 to 2010 are used for model training to simulate the urban scope in 2015. At the same time, the accuracy of simulation results is compared with the three traditional methods: artificial neural network-CA, logistic regression-CA and maximum entropy-CA. Compared with the traditional CA model, the simulated FoM index of Deep-CA in Beijing increases by about 4% in 2015, the simulation effect of Deep-CA on urban global and local morphology is good, and the patch fragmentation is low. The experimental results show that Deep-CA can accurately obtain long-term spatio-temporal dependence, thus further improving the simulation authenticity of urban growth CA model.

High-definition map generation method for safe driving areas at intersections

HOU Qiaochu, LI Bijun, ZHANG Hongjuan, CAO Yongxing

2023, 52(10):  1784-1796.  doi:10.11947/j.AGCS.2023.20220516

Asbtract ( )   HTML ( )   PDF (9225KB) ( )  

References | Related Articles | Metrics

The high-definition map can provide accurate and reliable global perception and positioning information for autonomous vehicles. Therefore, it is of great significance to vehicle decision planning. However, the proposed high-definition map models generally lack reasonable and effective geometric constraints and expressions on the connected areas of intersections. Aiming at the turning driving task of vehicles at the intersection, on the one hand, based on the safe driving rules at the intersection, on the other hand, to ensure the safe passage of vehicles at the intersection, this paper proposes a method for generating high-definition maps of safe driving areas at intersections. This method aims to make up the information gap in the intersection area of the current high-definition map in the urban structured road scene. The generated safe-driving area can serve for vehicle decision planning of different automation levels and improve the safety and standardization of vehicles passing at intersections. Finally, this paper uses the real intersection data of Wuhan city to verify the proposed method. The experimental results show that in 90% of cases, the proposed method can generate the intersection safe-driving areas at experimental intersections. It proves the rationality and validity of the method in this paper.

Summary of PhD Thesis

Mean sea surface modeling and fine sea level change from multi-satellite altimetry data

YUAN Jiajia

2023, 52(10):  1797-1797.  doi:10.11947/j.AGCS.2023.20220271

Asbtract ( )   HTML ( )   PDF (732KB) ( )  

Related Articles | Metrics

Spatio-temporal pattern mining for users' access interest on public map service platforms

DONG Guangsheng

2023, 52(10):  1798-1798.  doi:10.11947/j.AGCS.2023.20220284

Asbtract ( )   HTML ( )   PDF (731KB) ( )  

Related Articles | Metrics

Research on interaction between urban public transportation and land use using big data

GU Yanyan

2023, 52(10):  1799-1799.  doi:10.11947/j.AGCS.2023.20220310

Asbtract ( )   HTML ( )   PDF (730KB) ( )  

Related Articles | Metrics

Simulating spatio-temporal dynamics of forest carbon stocks in Guizhou Plateau by CBM-CFS3

TANG Yuzhi

2023, 52(10):  1800-1800.  doi:10.11947/j.AGCS.2023.20220379

Asbtract ( )   HTML ( )   PDF (752KB) ( )  

Related Articles | Metrics

Extraction and feature analysis of vegetation phenology information from medium-high resolution remote sensing data

RUAN Yongjian

2023, 52(10):  1801-1801.  doi:10.11947/j.AGCS.2023.20220386

Asbtract ( )   HTML ( )   PDF (750KB) ( )  

Related Articles | Metrics

Synergistic use of multi-source information for urban land areas extraction and spatial-temporal evolution analysis: a case study of the Malay Archipelago areas

YANG Fengshuo

2023, 52(10):  1802-1802.  doi:10.11947/j.AGCS.2023.20220393

Asbtract ( )   HTML ( )   PDF (757KB) ( )  

Related Articles | Metrics

Research on classification method of hyperspectral remote sensing image under random projection framework

JIA Shuhan

2023, 52(10):  1803-1803.  doi:10.11947/j.AGCS.2023.20220399

Asbtract ( )   HTML ( )   PDF (731KB) ( )  

Related Articles | Metrics

Research on seamless positioning theory and method for multi-source information fusion

WANG Changqiang

2023, 52(10):  1804-1804.  doi:10.11947/j.AGCS.2023.20220401

Asbtract ( )   HTML ( )   PDF (731KB) ( )  

Related Articles | Metrics