Table of Content

25 June 2025, Volume 0 Issue 6

Previous Issue   

Influence of stochastic model processing strategies for seafloor geodetic control point positioning

LÜ Zhipeng

2025, 0(6):  1-5.  doi:10.13474/j.cnki.11-2246.2025.0601

Asbtract ( )   PDF (2126KB) ( )  

References | Related Articles | Metrics

GNSS-A joint positioning technology is the main way to determine the coordinates of seafloor geodetic control points. The position error of transducer is considered to be a non-ignorable error source in the process of GNSS-A joint positioning. To solve this problem, the following three parameter estimation methods can be used:①least-squares (LS) estimation, which ignores the influence of transducer position error; ②improved least-squares (ILS) estimation, which incorporates the transducer position error into the random part of the acoustic ranging error; ③total least-squares (TLS) estimation, which introduces the transducer position error into the underwater acoustic positioning model. Through Monte Carlo simulation, the above three parameter estimation methods are analyzed from the aspects of estimation bias, effectiveness and computational efficiency. The results show that the LS estimation principle is simple and the computational efficiency is the highest. The TLS estimation has the smallest estimation deviation and is the most effective, but it has the lowest computational efficiency and poor convergence reliability. As a compromise scheme, the ILS estimation reduces the estimation bias and improves the validity compared with the LS estimation, improves the computational efficiency and enhances the convergence reliability compared with the TLS estimation.

Progress and trend of 3D modeling method of seabed topography based on multi-beam bathymetry technology

WU Hui, ZHANG Huiran, ZHU Weiqiang

2025, 0(6):  6-11,17.  doi:10.13474/j.cnki.11-2246.2025.0602

Asbtract ( )   HTML ( )   PDF (2507KB) ( )  

References | Related Articles | Metrics

Multi-beam sounding technology provides a high-precision, high-efficiency and high-resolution 3D representation for seabed topography surveying, which is a necessary implementation of the national marine strategy. However, the complexity and uncertainty of the marine environment brings significant challenges to the collection, processing and analysis of seabed topographic information. The quality of 3D visualization depends on the advancement of data acquisition hardware, computer software and graphic processing algorithms. Hence, seabed topography demonstrates important theoretical significance and practical research value. This paper discusses the current status of research, advanced algorithms and accuracy assessment in the 3D modeling of seabed topography. Firstly, we outline the latest progress in domestic and international research on seabed topographic 3D modeling and modeling quality evaluation indicators. Then we analyze and compare the performance of three open-source algorithms under the data of a local area in the northwestern South China Sea. Finally, the promising development trends of seabed topographic 3D modeling are summarized.

Deep learning-based method for foundation environmental monitoring of offshore platform

ZHANG Chao, XIONG Chunbao, LIAN Sida

2025, 0(6):  12-17.  doi:10.13474/j.cnki.11-2246.2025.0603

Asbtract ( )   HTML ( )   PDF (7682KB) ( )  

References | Related Articles | Metrics

Structural health monitoring (SHM) of offshore platform and ancillary pipelines pose challenges, including low efficiency of manual labor, high time costs, and reliance on subjectivity of technicians with existing knowledge. To address these issues, an intelligent, deep learning (DL)-based algorithm for monitoring the foundation subsea environment of offshore platform was proposed. This approach can prevent manual subjective factors from affecting image interpretation and enable early detection of foundation environmental disasters using an all-weather automated real-time offshore platform. Firstly, experiments were conducted to determine the most appropriate basic network structure for real-time classification of subsea 3D sonar images using computer vision(CV) algorithms based on DL that are presently in use. Secondly, the channel-priority convolutional attention (CPCA) module was employed for the improvement of the experimentally selected VGG-11 algorithm, and the effectiveness of the CPCA-VGG algorithm was verified by the Grad-CAM algorithm. The experimental results demonstrate that the CPCA-VGG algorithm assessment criteria achieve: Acc_Top-1 97.35%,Acc_Top-5 100.00%, mean precision and mean recall is 98.62% and 98.44%, when it was applied in offshore platform foundation environment classification. This algorithm can better meet the practical engineering needs of real-time monitoring of various environments based on offshore platforms and preliminary early warning of disasters.

Study on the geolocation accuracy of SAR corner reflectors in the mountain and canyon region: a case study of a giant hydropower station reservoir head area

FAN Jinyong, LIAO Haisheng, CHEN Jian, HE Xin, LUO Huiheng, HUANG Rong, YANG Lei, LI Linze, CHEN Yaowen, JIANG Liming, HUANG Ronggang

2025, 0(6):  18-23.  doi:10.13474/j.cnki.11-2246.2025.0604

Asbtract ( )   HTML ( )   PDF (3699KB) ( )  

References | Related Articles | Metrics

Corner reflectors(CR)serve as a crucial tool for high-precision interferometric synthetic aperture radar (InSAR) monitoring, with their reflective performance and geolocation accuracy playing a key role in InSAR deformation monitoring and result interpretation. Existing research on CR geolocation accuracy focuses on flat terrain, lacking studies addressing complex topographical settings. This paper presents a comprehensive method for CR geolocation accuracy analysis, combining SAR geolocation and radar cross section (RCS) analysis techniques, and validated using the CR array deployed at a mountainous reservoir head area of a giant hydropower station located within a river canyon. Results indicate that out of the 10 corner reflectors (CRs) in the reservoir head area, 8 exhibits good accuracy, while 2 demonstrates suboptimal precision. The RCS of the 8 high-precision CRs increases by over 5 dBm² after installation, with an average increase of 10.24 dBm², representing an average growth of 66.2%, and the average SAR geolocation errors in the azimuth and range directions are -0.601 and -0.013 m, respectively. The accuracy of the 2 remaining CRs is limited due to the foreshortening effect, with SAR geolocation errors in the azimuth direction of 5.83 and -9.02 m, and range errors of 1.37 and -0.73 m respectively, highlighting that terrain complexity should be taken into consideration when deploying CRs in mountainous canyon regions. The findings of this study provide the first evaluation of the applicability of SAR geolocation in mountain and canyon scenarios and offer crucial insights into the accuracy of the CR array at the giant hydropower station reservoir head area, providing important references for high-precision InSAR deformation monitoring and result interpretation in mountainous canyon regions.

Chlorophyll-a concentration inversion and eutrophication assessment in the Beijiang River Basin

GU Yuze, DENG Ruru, LI Jiayi, GUO Yu, HUA Zhenqun, KUANG Zhiyuan, HUANG Di

2025, 0(6):  24-29,72.  doi:10.13474/j.cnki.11-2246.2025.0605

Asbtract ( )   HTML ( )   PDF (3343KB) ( )  

References | Related Articles | Metrics

Chlorophyll-a can directly characterize phytoplankton biomass to a certain extent, so the key to remote sensing monitoring of water body eutrophication lies in the inversion of chlorophyll-a concentration. In this paper, we constructed a remote sensing inversion model based on the radiative transfer mechanism, and took the Sentinel-2 data from the Beijiang River Basin in July-August 2022 as an example of chlorophyll-a concentration inversion, which reduced the influence of other components. The results show a high degree of accuracy, with a coefficient of determination of 0.84 and an average relative error of 0.22 μg/L, and a root mean square error of 1.58 μg/L. Evaluation of eutrophication, characterization of the spatial distribution of chlorophyll-a concentration, and analysis of the causes of eutrophication were also carried out for five obvious eutrophic river sections. The overall eutrophication in the study area was mild, mainly in the middle trophic state, and eutrophication existed in some water bodies, mainly distributed in some tributaries and reservoirs and bays, among which the situation in the Changhu Reservoir was the most serious, with the integrated trophic state index TLI reaching 65.22, which was in the middle eutrophication state.

Application of GPM and TRMM precipitation products in estimating rainfall erosivity in Hengduan Mountains

DUAN Qiyan, CHEN Guokun, FENG Junxin, ZHANG Kaiqin, WANG Ying

2025, 0(6):  30-36,77.  doi:10.13474/j.cnki.11-2246.2025.0606

Asbtract ( )   PDF (23311KB) ( )  

References | Related Articles | Metrics

Rainfall erosivity is a key indicator to characterize the potential of rainfall and its runoff to cause soil erosion, and is often obtained through field data. However, in the vast plateau mountainous areas, meteorological stations are extremely scarce and unevenly distributed, resulting in poor data representativeness. How to select appropriate precipitation products has become a major problem in regional soil conservation prevention and control. To address this, this study takes the Hengduan Mountain area in northwestern Yunnan as an example, and combines ground-based field data to evaluate the applicability of three precipitation products, IMERG, T3B42 and TP1km, on annual, seasonal and monthly scales, and analyzes the spatio-temporal distribution characteristics of rainfall erosivity. The results show that: ①IMERG provides the most accurate rainfall estimates across all time scales;②On the annual scale, both IMERG and T3B42 tend to overestimate rainfall erosivity, while TP1km underestimates it; on the monthly scale, all three products underestimate it; ③Rainfall erosivity generally decreases from southwest to northeast. As a representative precipitation product of the global precipitation measurement(GPM), IMERG offers reliable rainfall erosivity information for this region.

Landslide hazard identification based on the object detection algorithm YOLOv9:taking Yongxin county as an example

TU Liping, CHEN Meiqiu, LENG Peng

2025, 0(6):  37-42,102.  doi:10.13474/j.cnki.11-2246.2025.0607

Asbtract ( )   PDF (5997KB) ( )  

References | Related Articles | Metrics

Landslide disaster is one of the most serious geological disasters,which causes huge property losses and casualties every year.Traditional image-based manual investigation is heavy in workload and low in efficiency.This study takes Yongxin county as the research area,firstly,uses the YOLOv9 object detection algorithm to build a landslide recognition model based on 207 landslide samples constructed by high-resolution aerial images,and then evaluates the accuracy of the model.Finally,the landslide of the whole county is identified and the landslide results identified are analyzed.The results show that the accuracy of the model is 0.98,the recall rate is 0.97,and the mAP is 0.95.There are 312 common landslides in the county,and 46 are misjudged by the model through comparison and field investigation,and the accuracy of model recognition is 85.26%.It can be seen that YOLOv9,an object detection algorithm,can effectively identify landslides in the southern region,providing an effective solution for large-scale identification of small-scale landslides in the south.

Landslide dynamic hazard assessment based on InSAR and information-logistic regression coupling model

WANG Chenyu, PENG Junhuan, XUE Yueming, LI Xu, ZHANG Yan

2025, 0(6):  43-48.  doi:10.13474/j.cnki.11-2246.2025.0608

Asbtract ( )   HTML ( )   PDF (10667KB) ( )  

References | Related Articles | Metrics

In view of the issues of significant discrepancies, poor timeliness, and false negative errors in the results of various landslide hazard assessment models.This paper takes Xiangyun county, Yunnan province as the study area.Firstly, compares the performance of four models:information(I), information-logistic regression(I-LR), long short-term memory(LSTM) and support vector machine(SVM), to determine the most suitable model for landslide hazard assessment. Then, the SBAS-InSAR method is used to process the Sentinel-1 data from both ascending and descending orbits between August 2019 and July 2023, and the surface slope deformation rate is calculated. Finally, the landslide hazard classification and slope deformation rate are combined using a correction matrix to generate the dynamic landslide hazard map.The results show that the I-LR model has better prediction accuracy and stability than the other three models.The landslide dynamic hazard map, generated by combining the I-LR model landslide hazard classification and the InSAR slope deformation rate classification, demonstrates better identification of unstable deformation areas. The proportion of low hazard areas is reduced by 10.35%, while the proportions of lower, medium, and high hazard areas increase by 6.30%, 2.45%, and 1.60%, respectively. This enhances both the timeliness and accuracy of landslide hazard assessment results.

Laser point cloud and multi-spectral image fusion combining Hough transform and semantic feature points

ZHANG Yingying, ZANG Yufu, SHI Jiajun, XIAO Xiongwu

2025, 0(6):  49-54.  doi:10.13474/j.cnki.11-2246.2025.0609

Asbtract ( )   PDF (7024KB) ( )  

References | Related Articles | Metrics

In urban land object recognition and classification, environmental monitoring, and cultural heritage recording and protection, airborne LiDAR point cloud and multi-spectral images are two important remote sensing data. However, existing multi-modal data fusion methods have difficulty in effectively integrating the two cross-modal data. Therefore, this paper proposes a method for fusing LiDAR point clouds with multi-spectral images by combining Hough transform with semantic feature points. Line-CNN deep learning network is used to extract line features, and Hough transform is employed to detect rectangular boxes and generate corresponding semantic feature points, thus achieving precise matching fusion of multimodal data based on feature points. Experiments results show that the matching accuracy of this method reaches as high as 97.98% in four different scenarios, and the fusion correlation coefficient exceeds 90%, which proves that the method has excellent robustness and high precision, and provides a new solution for multi-source remote sensing data fusion.

Hyperspectral image classification based on two-step smoothing and feature weighting

XU Qi, YANG Jiawei, WANG Jiyan

2025, 0(6):  55-61.  doi:10.13474/j.cnki.11-2246.2025.0610

Asbtract ( )   PDF (4049KB) ( )  

References | Related Articles | Metrics

A hyperspectral image classification method based on two-step smoothing and feature weighting is proposed to address the problem of various image filtering based spatial spectral joint classification methods being difficult to preserve weak edges of the image while denoising. Firstly, the original hyperspectral image is preprocessed by minimum maximum normalization, and then principal component analysis is used to reduce the dimensionality of the hyperspectral image. Next, using windowed domain transformation recursive filtering to obtain feature images with weakened noise while preserving weak edges, and then smoothing the feature images again through L0 gradient minimization to further suppress noise and enhance edges. After that, each feature image is weighted by variance. Finally, support vector machine is used for classification. Experiments were conducted on two datasets, and the classification accuracy of this method improved by 14.06% and 25.75% compared to spectral feature-based methods, and by 0.76%～4.3% and 1.5%～5.69% compared to various filtering algorithms in this field. Moreover, the classification results better reflect the true land cover categories.

Colorized 3D reconstruction technology integrating multi-source and multi-view data

ZHANG Lijun, GAO Yunhan, ZOU Xiaofan, SHI Hang, XIE Yangmin

2025, 0(6):  62-67.  doi:10.13474/j.cnki.11-2246.2025.0611

Asbtract ( )   PDF (5938KB) ( )  

References | Related Articles | Metrics

With the growing demands of digitalization, data acquired from a single sensor has become inadequate for complex modeling tasks, and single-view approaches are inherently prone to data sparsity and occlusion issues. To address this problem, this paper proposes two sets of 3D reconstruction systems, which are equipped with multiple sensors including LiDAR, monocular cameras, and IMU, and can be respectively applied to multi-view data collection in both indoor and outdoor environments. Furthermore, this paper also presents a colorized 3D reconstruction technology based on the fusion of multi-source and multi-view data. The prerequisite is to obtain the coordinate system transformation relationships among various sensors through joint calibration. Then, the visual-inertial coupling system is utilized for motion estimation to acquire accurate postures and trajectories. Based on this, the single-view laser point clouds are optimized for distortion removal and assigned with true colors. Finally, multi-view point cloud stitching is carried out based on the mixed information of color and geometry to obtain the true-color 3D model of the scanned object. Tests and verifications have been conducted in both indoor and outdoor scenarios. The experimental results show that the 3D reconstruction accuracy of this method is higher than that of advanced algorithms, with the modeling error reaching the centimeter level. Additionally, the algorithm has higher robustness.

Improved point cloud registration algorithm based on ICP algorithm and bursa model

ZHANG Mingmin, HU Qiubao, HUANG Tuanchong, LIU Yicheng, ZHENG Jinxin

2025, 0(6):  68-72.  doi:10.13474/j.cnki.11-2246.2025.0612

Asbtract ( )   PDF (1696KB) ( )  

References | Related Articles | Metrics

This paper proposes an improved point cloud registration algorithm based on the iterative closest point(ICP)algorithm to address the issue that the Bursa model is only suitable for small angle point cloud registration.Firstly, rough registration of the point cloud is performed using the ICP algorithm, and the source point set is iteratively rotated and translated until the convergence result meets the requirements for using the Bursa model.Then, based on the principle of indirect adjustment, the Bursa model is used to achieve accurate registration of the source point set.The experiment shows that the root mean squared error(RMSE)for accurate registration results of ICP-Bursa algorithm is less than 0.010 m, which not only compensates for the limitations of the applicability of the Bursa model, but also improves the registration accuracy of the traditional ICP algorithm by 97.8%, 95.8%, and 96.5% in the X-axis, Y-axis, and Z-axis directions, respectively.

A style transfer method for shipwrecks and crashed aircraft based on whitening and coloring transformation

YAN Baiyu, ZHAI Guojun, BIAN Shaofeng

2025, 0(6):  73-77.  doi:10.13474/j.cnki.11-2246.2025.0613

Asbtract ( )   PDF (4527KB) ( )  

References | Related Articles | Metrics

Deep learning algorithms have been widely applied in the field of image classification. However, the limited availability of side-scan sonar images containing target objects poses a significant challenge in meeting the training demands of these algorithms, often leading to issues like overfitting. Style transfer has emerged as an effective method for augmenting training samples. This paper investigates and reconstructs the iterative processes of the WCT and PhotoWCT style transfer algorithms. Based on the characteristics of Unpooling and Upsampling, we propose modifications to the WCT algorithm across different feature layers of the decoder, resulting in the development of the WCST style transfer algorithm, which is more suited for side-scan sonar imagery.Using the WCST algorithm, realistic pseudo side-scan sonar images containing target objects were generated to meet the training requirements of image classification networks. In subsequent image classification experiments, datasets generated by WCST and PhotoWCT were used to train ResNet50. The results demonstrated that WCST outperformed the other methods in all accuracy metrics, highlighting its effectiveness in augmenting high-quality training sets for side-scan sonar image classification.

Multi-factor joint UWB ranging stochastic model

MA Sunchao, LIU Hui, QIAN Chuang, CHEN Yibiao, JI Yuanfa

2025, 0(6):  78-83.  doi:10.13474/j.cnki.11-2246.2025.0614

Asbtract ( )   PDF (1906KB) ( )  

References | Related Articles | Metrics

Due to the complex and changeable indoor environment, the UWB stochastic model based on single factor has its own advantages and disadvantages. In order to further refine the existing model and improve the positioning accuracy of UWB in complex scene, this paper proposes a joint stochastic model based on communication distance, signal-to-noise ratio and power difference on the basis of analyzing the factors related to UWB ranging quality. The stochastic model takes into account all noise factors and has strong environmental adaptability. The experimental results show that the multi-factor combined stochastic model has better anti-noise performance than the single factor stochastic model, the static positioning accuracy can be improved by 40% compared with the equal weight model, and the dynamic positioning results are closer to the real trajectory.

Locomotive positioning method in underground coal mines using fusion of RSSI and TDOA

ZHAO Bin, FU Shuai, GAO Lixia, LI Sensen

2025, 0(6):  84-89,122.  doi:10.13474/j.cnki.11-2246.2025.0615

Asbtract ( )   PDF (1425KB) ( )  

References | Related Articles | Metrics

To address the problem of precise locomotive positioning in the switch area for mine switch machines under wireless control, this paper proposes a long-range radio (LoRa) assisted positioning method that integrates received signal strength indication (RSSI) and time difference of arrival (TDOA). First, an improved path loss factor is used to establish the RSSI ranging model, and a hybrid filtering method combining Kalman filtering, Gaussian filtering, median filtering, and mean filtering is applied to reduce noise interference. Then, the weighted centroid trilateration algorithm is used to initially determine the locomotive's coordinates. Finally, the TDOA Taylor series iteration method is employed to optimize the positioning accuracy. Experimental results show that after hybrid filtering, the ranging error within a 25 m range is less than 1.5 m, and the optimized positioning accuracy of the locomotive's coordinates reaches within 0.1 m. Experimental verification demonstrates that the fusion algorithm improves positioning accuracy compared to the single RSSI positioning algorithm, providing a new solution for accurate locomotive positioning in the switch areas and enhancing the safety and reliability of the mine's turnout machine wireless control system.

Extraction of landslide influence factors based on Relief-F feature preference and modeling analysis of susceptibility to landslides

FANG Lu, XING Yin

2025, 0(6):  90-96.  doi:10.13474/j.cnki.11-2246.2025.0616

Asbtract ( )   PDF (4083KB) ( )  

References | Related Articles | Metrics

In order to solve the problems of insufficient accuracy of the existing landslide susceptibility evaluation model and the limitations of a single decision-making model, an integrated PSO-GA-RF integrated model with an integrated intelligent combination algorithm to optimize RF is proposed. The well-known filtering feature selection method(Relief-F algorithm)is used to rank the weights of landslide-causing factors, eliminate redundant features, and optimize the classification results, thus reducing the problem of relying on subjective judgments to extract the influencing factors, and lowering the human error. The PSO-GA-RF integrated model combines the advantages of multiple algorithms to optimize the parameters of the RF model, which simplifies the tedious process of parameter selection and reduces the error. The experimental results show that the PSO-GA-RF integrated model outperforms the RF and GA-RF models in terms of prediction performance and efficiency.

An integrated edge-gated and multi-scale spatial attention model for drainage pipeline defect segmentation

CHEN Dengfeng, ZHAO Hanghui, LIU Shipeng, MENG Tunliang, WANG Zepeng

2025, 0(6):  97-102.  doi:10.13474/j.cnki.11-2246.2025.0617

Asbtract ( )   PDF (1450KB) ( )  

References | Related Articles | Metrics

The aging of urban underground drainage pipelines has led to frequent occurrences of pipe damage, blockages, and other issues. Manual inspection methods struggle to meet the growing demand for detection, while existing intelligent detection technologies still have room for improvement in achieving higher intersection over union(IoU)when addressing irregularly shaped defects and intricate boundaries. This study proposes a semantic segmentation model for drainage pipelines named PGGNet to enhance defect boundary recognition performance. The gated edge attention model(GEA) in PGGNet integrates edge features through the Laplacian edge detection algorithm, significantly improving the ability to capture defect boundaries. Meanwhile, the multi-scale guided spatial attention-state space model(MGSA-SSM)combines a state-space model with MGSA of multi-scale mechanisms to guide the model in capturing both global contours and local details of defects across different scales, thereby enhancing the recognition capability for complex boundaries. Experimental results demonstrate that PGGNet outperforms mainstream algorithms, achieving an mPA of 94.32% and an mIoU of 93.08%, which meets the requirements for automated defect detection in drainage pipelines.

Monitoring and analysis of coastline change and land subsidence in the Yellow River Delta

GAO Haoliang, LI Dewei, LI Pengpeng, LI Xiaohong, DI Guishuan

2025, 0(6):  103-108,122.  doi:10.13474/j.cnki.11-2246.2025.0618

Asbtract ( )   PDF (9102KB) ( )  

References | Related Articles | Metrics

In response to the severe land subsidence and escalating coastal erosion risks near the coastline of the Yellow River Delta, this paper proposes an integrated monitoring and analyzing framework of coastline change and land subsidence based on DS-InSAR and general high tide line method, combined with the vertical section method. The paper carries out the monitoring and analysis of coastline change and land subsidence in the Yellow River Delta from 2020 to 2024. The results show that land subsidence in the Yellow River Delta is concentrated along the eastern coast, forming four significant subsidence funnels (A,B,C,D), with a maximum subsidence rate of -350 mm/a. Due to the reclamation and stabilization of the artificial coastline, the coastline is basically stable in zone A. Zone B is close to the estuary of the Yellow River, with dramatic changes in the siltation, erosion and recession of the coastline, and the innermost part of the coastline is about 4 km away from the center of the subsidence. The overall siltation and erosion of the coastline in zone C is 0.91 km, about 8 km from the center of subsidence. The coastline of zone D is slowly eroding, with the innermost part of the coastline about 0.15 km from the dyke and 9 km from the center of subsidence. The results of the study have a reference value for the comprehensive management of the coastline.

The road network method of trajectory data extraction coupled with multi-level grid features

ZHANG Yunfei, ZHONG Tianyu

2025, 0(6):  109-114.  doi:10.13474/j.cnki.11-2246.2025.0619

Asbtract ( )   PDF (4563KB) ( )  

References | Related Articles | Metrics

Currently, the extraction and updating of road network has been one of the key factors affecting urban construction and development. At the same time, with the continuous development of driverless technology, the construction of high-precision road network is one of the key research contents of many scholars. Existing road network extraction methods based on track data have little semantic information for grid feature mining. Therefore, this paper proposes a road network extraction method of track data coupled with multi-level grid features. Firstly, the original track data is preprocessed, and multi-level grid features of the track data are calculated based on grid, including track similarity, grid track point density, etc. Then,based on multi-level grid features,the random forest model is used for feature training,and the key grid is classified and recognized. Finally,the key grid is extracted based on morphology. In this paper,the walking track data is used for model training,and the vehicle track data is used for model migration verification.The experimental results show that the proposed method has better performance than other road network extraction methods.

Construction and simulation of intersections in high-definition maps: conversion and mapping from shapefile to OpenDRIVE

YING Shen, QIU Muyuan, WANG Runze, HE Shan, JIANG Yuewen, BAI Yiduo

2025, 0(6):  115-122.  doi:10.13474/j.cnki.11-2246.2025.0620

Asbtract ( )   PDF (3859KB) ( )  

References | Related Articles | Metrics

To achieve high-level autonomous driving, sufficient real map data are required to assist in simulation testing and in-the-loop testing of intelligent connected vehicles(ICV). Shapefile (SHP) as the standard format for surveying and mapping data collection, exhibits significant differences from high-definition (HD) maps and can not meet the needs of autonomous driving scenario simulations. To fully utilize existing surveying and mapping data, this paper takes the most complex intersection structure in the road network as an example and proposes a conversion mapping from SHP to OpenDRIVE. It establishes a comprehensive road intersection element model, extends the OpenDRIVE specification, and clarifies the element mapping relationship between SHP and OpenDRIVE. Based on real shapefile data from Chongqing, this paper realizes the construction of HD map intersection scenarios using the proposed conversion mapping. The effectiveness of this method is verified through scenario simulations, providing a new reference path for the exploration and practice of HD map construction.

Optimized extraction of photovoltaic power stations based on object image analysis and Sentinel images

ZHOU Chaohui, LI Linze, ZHANG Jicheng, MAO Hongzhi, HAN Tao

2025, 0(6):  123-129.  doi:10.13474/j.cnki.11-2246.2025.0621

Asbtract ( )   PDF (6727KB) ( )  

References | Related Articles | Metrics

To achieve the energy goal of carbon peak and carbon neutrality, the construction of photovoltaic (PV) power stations has been growing rapidly, and the statistics of distribution and scale of PV power stations are beneficial to energy management and planning. Existing methods of applying remote sensing image data for PV power stations extraction suffer from the lack of extraction fineness and the loss of small-area PV power stations. In this study, an object-based image analysis method is adopted to extract spectral, index and geometric features using Sentinel-2 and Sentinel-1 image data, establish a random forest extraction model, and analyze the optimal segmentation parameters for multi-scale segmentation in different terrains. The optimal global segmentation parameters are segmentation scale, shape factor and compactness of 50, 0.7 and 0.5 respectively. The model established in this paper obtaines an accuracy of 98.21% for PV plant users and 95.85% for producers on the validation set. Finally, the distribution map of PV power stations in Hubei province in 2024 is drawn, and the installed area of PV power stations in the province is 230.8 km².

The deformation monitoring and prediction of ultra-high voltage transmission channels using combined SBAS-InSAR and DS-InSAR

WANG Shenli, LIU Yi, HAN Hao, DU Yong

2025, 0(6):  130-135,141.  doi:10.13474/j.cnki.11-2246.2025.0622

Asbtract ( )   PDF (25364KB) ( )  

References | Related Articles | Metrics

This paper combines SBAS-InSAR and DS-InSAR technologies to monitor and predict the deformation of the extra-high voltage transmission corridor in Wufeng county, aiming to improve the safety of the transmission line and the disaster warning capability. Firstly,combining these two techniques, a multi-scale deformation monitoring model is established, which provides finer data support for risk assessment of transmission lines. Then, this paper introduces a long short-term memory (LSTM) neural network model for time series prediction of ground subsidence trends. By training and testing the Sentinel-1A satellite data from October 2023 to October 2024, the LSTM model shows high prediction accuracy, with the maximum absolute error of 3.28 mm, the minimum absolute error of 0.13 mm, and the root-mean-square error (RMSE) of 1.32 mm, which verifies the validity and reliability of the model in ground deformation prediction. The study shows that the LSTM model is able to capture the long-term trend of subsidence changes and provide strong support for the maintenance of transmission corridors and disaster warning.

Application of LiDAR and gimbal camera driven UAV tree barrier hazard detection technology in distribution network inspection

WEI Hong, KUANG Songling, LI Yangfan, FENG Fan, YANG Tao, TANG Xing

2025, 0(6):  136-141.  doi:10.13474/j.cnki.11-2246.2025.0623

Asbtract ( )   PDF (3561KB) ( )  

References | Related Articles | Metrics

In the process of electric power distribution network inspection, the traditional UAV inspection mode often has a lag, which makes it difficult to discover and deal with the hidden tree obstacles in the inspection channel in a timely manner, leading to the impact on the operational safety of distribution lines. To solve this problem, this study proposes a real-time hidden danger detection technology that integrates LiDAR and PTZ camera, realizing real-time detection and analysis of tree obstacles in the inspection channel by carrying LiDAR and high-precision camera on the UAV and integrating the YOLO model of genetic K-mean anchor frame clustering. The system can automatically identify and locate tree obstacles, and accurately photograph the hidden parts through the gimbal camera to generate a real-time report on the hidden problems. Through testing in complex environments, the results show that the system is able to significantly improve the timeliness and accuracy of hidden trouble detection and significantly shorten the time from discovery to action. It is concluded that the proposed real-time hidden danger detection technology significantly improves the efficiency and safety of distribution network inspection, provides strong support for the intelligent management of electric power distribution networks, and has a wide range of application prospects.

Real-time path planning for flood rescue operations using InSAR in Poyang Lake flood disaster

LIU Xiangtong, LU Renhui, ZHANG Fengxue, XI Alei, LU Zhengxun

2025, 0(6):  142-146.  doi:10.13474/j.cnki.11-2246.2025.0624

Asbtract ( )   PDF (7006KB) ( )  

References | Related Articles | Metrics

During flood disasters, real-time acquisition of inundation information in the affected areas is crucial for formulating rescue plans and optimizing evacuation routes. In response to the limitations of optical remote sensing technologies during floods, this paper selects SAR imagery, which is unaffected by weather conditions. Sentinel-1A imagery from the 2020 Poyang Lake flood, covering Lianhu town in Poyang county and Zhouxi town in Duchang county is used. The data undergoes processes such as radiometric calibration and geocoding, and after obtaining the polarization data, an object-oriented approach is applied. digital elevation model (DEM) data is incorporated to remove mountain shadows during decision-making. The final water body vector map is generated, and path analysis is performed by combining road vector data with the water body map to plan real-time evacuation routes, ultimately identifying the optimal evacuation route that avoids flooded areas. The experimental results show that the real-time evacuation route effectively avoids flooded road areas, while also selecting the shortest path, meeting the requirements for flood rescue operations in path planning.

Application of multi-technology integration supporting construction project approval optimization

MA Li, LI Xiao, ZHANG Chi, YANG Guang

2025, 0(6):  147-150,167.  doi:10.13474/j.cnki.11-2246.2025.0625

Asbtract ( )   PDF (2663KB) ( )  

References | Related Articles | Metrics

Construction project planning and management surveying usually adopts the operation mode of RTK and total station,the surveying and mapping data production efficiency is low,the results are not intuitive and the utilization rate is low.This paper takes a project in Guangzhou as an example to explore the support and application of UAV oblique photography,3D laser scanning and BIM modeling technology to optimize the reform of examination and approval.UAV oblique photography can efficiently complete 1∶500 topographic map measurement through multi-angle air-based observation,generate high-precision orthophoto maps and real-life 3D models,and use BIM to build a 3D model,through the application of BIM measuring instrument,the visual lofting is realized.Based on the laser point cloud data,the 3D model of BIM completion is generated and compared with the 3D model of BIM construction,support the acceptance examination and approval with high efficiency.The experimental results show that the method of multi-technology fusion can meet the requirements of examination and approval reform and has significant application value.

Optimization of natural resource information management in the context of digital government construction: from management to governance

LIN Xiaofei, WANG Furong, CUI Bei, LU Xinya

2025, 0(6):  151-155.  doi:10.13474/j.cnki.11-2246.2025.0626

Asbtract ( )   PDF (1561KB) ( )  

References | Related Articles | Metrics

The construction of a digital government is a significant initiative to adapt to the technological revolution and industrial transformation, and to promote the modernization of national governance. It is currently driving the transition from informationalized management to governance in the management of natural resources. This article takes the natural resources department of N city as an example, detailing the limitations of the current traditional informationalized management model in terms of stakeholder coordination, fragmented construction management, and element coverage. It constructs an action framework for the transition from informationalized management to governance and proposes a three-dimensional governance content of “concept-content-capability”. By building a scenario-based element set, a management element map, and an intelligent governance platform, it explores the implementation path of local natural resources informationalized governance.

Analysis on spatial distribution characteristics of immovable cultural relics in the Yellow River basin(Shaanxi)

LI Dawei, XU Cailian, HUANG Jie, LI Jizhen, TANG Tian

2025, 0(6):  156-161,174.  doi:10.13474/j.cnki.11-2246.2025.0627

Asbtract ( )   PDF (12430KB) ( )  

References | Related Articles | Metrics

The Yellow River basin in Shaanxi province is one of the important birthplaces of the Chinese nation and Chinese civilization.To fully grasp the spatial distribution characteristics of cultural relics protection units in this region is the prerequisite and basis for carrying out cultural relics protection work.Using GIS spatial analysis method,this paper analyzes the spatial distribution characteristics and influencing factors of immovable cultural relics in the Yellow River basin of Shaanxi province.The results show that the cultural relics are widely distributed in space,and there is a high-density gathering area in Xi'an.Cultural relics are rich,covering all types of heritage forms,especially the number of ancient sites is the largest.In terms of time,cultural relics and monuments span a long time,and there are remains in each period.The overall distribution of cultural relics is highly correlated with elevation,slope and main water system.

Spatio-temporal data warehouse and analysis tools for infectious disease monitoring and early warning

LI Chengren

2025, 0(6):  162-167.  doi:10.13474/j.cnki.11-2246.2025.0628

Asbtract ( )   PDF (4837KB) ( )  

References | Related Articles | Metrics

The process of infectious disease transmission contains a large amount of spatio-temporal information. In order to further explore the value of spatio-temporal information and enhance the monitoring and early warning capabilities of infectious diseases, this paper integrates basic spatio-temporal data and spatio-temporal data of infectious disease transmission to construct a spatio-temporal data warehouse and analysis tool for infectious disease monitoring and early warning. The key technologies, such as unified spatial code encoding based on spatial three-dimensional grids, address recognition and error correction based on machine learning, and spatio-temporal aggregation analysis in the WebGIS environment, are studied to achieve the analysis and visualization of infectious disease data distribution and inference results, providing refined risk area early warning and decision support capabilities for infectious disease monitoring and early warning.

Monitoring site optimization in the intelligent farmland protection scenario in Zhejiang province

WU Xuelin, LI Jie, DAI Weitong, QIAN Rongrong

2025, 0(6):  168-174.  doi:10.13474/j.cnki.11-2246.2025.0629

Asbtract ( )   PDF (4181KB) ( )  

References | Related Articles | Metrics

Zhejiang province has implemented the “Intelligent Cultivated Land Protection” system, leveraging the province-wide, extensive, and elevated tower resources, combined with "towers+video terminals+AI algorithms" to comprehensively adopt both human and technological surveillance measures. Traditionally, two-dimensional site selection schemes based on experiential judgment have suffered from low accuracy, inefficiency and high subjectivity, while coverage rate and cost-effectiveness are key metrics for evaluating the quality of surveillance network design. In this context, this paper utilizes high-precision 3D real-world data and viewshed analysis algorithms, combined with 3D simulation technology, to construct a visual mapping dataset of candidate surveillance points and cultivated land plots. By studying greedy algorithms, genetic algorithms, and simulated annealing algorithms, this paper proposes a hybrid approach that combines simulated annealing with genetic algorithms, using an improved greedy algorithm to provide high-quality initial solutions for the genetic algorithm. This hybrid genetic algorithm (GA-SA) enhances the accuracy and cost-effectiveness of surveillance site selection. Additionally, a cultivated land plot surveillance visualization system is developed based on the Cesium 3D engine, providing critical visualization support tools for cultivated land management and protection.

The spatial relationship between transportation accessibility and economic linkages of ice and snow tourism

KONG Lingjia, HE Gan, LÜ Lina

2025, 0(6):  175-179.  doi:10.13474/j.cnki.11-2246.2025.0630

Asbtract ( )   PDF (2652KB) ( )  

References | Related Articles | Metrics

Based on the road and railway traffic and economic data of Heilongjiang in 2015, 2019 and 2023, an evaluation model is established to measure the strength of transportation accessibility and tourism economic linkage, and then the coupling and coordination relationship and spatial pattern between them are discussed. The results show that: ①There is a significant difference in traffic accessibility between east and west, but it is improved year by year. The west is better than the east, and the relative difference is 463.033 reduced to 377.176. ②The tourism economic relationship presents a “core-edge” polarization pattern, with Harbin as the radiation center, forming a high intensity relationship with Qiqihar and Suihua, and the marginal region has a significant attenuation. ③The coordination of transportation and tourism economic system is insufficient, the coupling coordination level is concentrated in the barely coordination and the verge of imbalance, and the main mode is medium transportation accessibility-low tourism economy (M-L). Therefore, the government and relevant departments should speed up the construction of transportation in the eastern region, drive the development of tourism economy with transportation, and provide continuous impetus for the growth of regional tourism economy.

Spatio-temporal logic design of geographic information for vehicle infrastructure cooperative system

FENG Jia, XING Chong, YAN Song, DAI Shuai

2025, 0(6):  180-184.  doi:10.13474/j.cnki.11-2246.2025.0631

Asbtract ( )   PDF (2736KB) ( )  

References | Related Articles | Metrics

The vital section in vehicle infrastructure cooperative system would be the logically interaction connection between the vehicle,infrastructure and the traffic rule.Considering the roughly distinguishing on vehicle trajectory and incomprehensive cover of traffic rule,to realize a meticulous supervise on the traffic behaviors in a normal traffic environment,a method to form digital traffic component based on GDSS and TRK has been designed under the conception which named of TSDA,also the traffic rule has been carried out in a spatio-temporal way.The spatial transportation geographic network is established on decimeter level,where the experiments about over speed,inverse travelling,traffic signal violation and trespass have been implemented under kinds of scenes,meanwhile the vehicle violation trajectory is labeled in high precision electronic map.Experiments result show that the preset over speed violation is identified in scene 1; the preset over speed violation and traffic signal violation is identified in scene 2; the preset partial inverse travelling and traffic signal violation is identified in scene 3; the preset inverse travelling,traffic signal violation and trespass is identified in scene 4.All the preset violation is caught.