Message Board

Respected readers, authors and reviewers, you can add comments to this page on any questions about the contribution, review,        editing and publication of this journal. We will give you an answer as soon as possible. Thank you for your support!

Verification Code
Display Method:
GIS Framework for Smart Cities
RS-ODMS: An Online Distributed Management and Service Framework for Remote Sensing Data
Thinking and Challenges of Crowd Dynamics Observation from the Perspectives of Public Health and Public Security
Deep Learning and Remote Sensing Data Analysis
A Review of Recent Researches and Reflections on Geospatial Artificial Intelligence
Sensing Urban Dynamics by Fusing Multi-sourced Spatiotemporal Big Data
Applications and New Trends of Machine Learning in Urban Simulation Research
Survey of Point-of-Interest Recommendation Research Fused with Deep Learning
Complicated Geospatial Flow Processing with Scientific Workflow
Spatial-Textal Correlation Analysis Based on Crowdsource Geospatial Data
Review of Interpolation, Reconstruction and Prediction Methods for Heterogeneous and Sparsely Distributed Geospatial Data
Place Model and Big Geo-Data Supported Place Sensing
Bilevel Convolutional Neural Networks for 3D Semantic Segmentation Using Large-scale LiDAR Point Clouds in Complex Environments
Cox Regression Analysis of National Terrorist Attacks Considering Spatial and Temporal Factors
Grid Pattern Recognition in Road Networks Based on Graph Convolution Network Model
Predicting Personal Next Location Based on Stay Point Feature Extraction
Identification of Traffic Index Time Series Pattern by Using Convolution Neural Network
Pedestrian Trajectory Prediction Model Based on Self-Attention Mechanism and Group Behavior Characteristics
An Optimization Method of Spatial Data Loading for 3D WebGIS
Articles online first have been peer-reviewed and accepted, which are not yet assigned to volumes /issues, but are citable by Digital Object Identifier (DOI).
Display Method:
Characteristics of the Computer Game Map
Application of EM Algorithm in the Parameter Estimation of P-norm Mixture Mode
Articles just accepted have been peer-reviewed and accepted, which are not yet assigned to volumes /issues, but are citable by Digital Object Identifier (DOI).
Display Method:
Applications of the UAVs in the Antarctic Scientific Research: Progress and Prospect
LI Teng, ZHANG Baogang, CHENG Xiao, ZHANG Yuanyuan, HUI Fengming, ZHAO Tiancheng, QIN Weijia, LIANG Jianhong, Yang Yuande, LIU Xuying, LI Xinqing
 doi: 10.13203/j.whugis20200098
[Abstract](261) [PDF 1818KB](39)
Unmanned Aerial Vehicle; Antarctic Expedition; Climate Change; Photogrammetry; Glaciology; Ecology; Geomorphology

Start in 1957 Monthly

ISSN 1671-8860

CN 42-1676/TN




Special Recommend

XU Qiang

Understanding and Consideration of Related Issues in Early Identification of Potential Geohazards

  Objectives  In China, geohazards are wide-ranging. Traditional artificial investigations have found nearly three hundred thousand locations of potential geohazards. However, the recent occurred catastrophic geohazards are not within these determined locations. Widely identification of potential geohazards become one of the most important jobs for geohazard prevention and mitigation.  Methods  We propose some suggestions to promote early identification for potential geohazards.  Results  (1) Recently, various remote sensing techniques play an significant role in geohazard identification, but each technique has its limitation to recognize geohazards with different types and characteristics. Only integrated technologies, mutual complementation and verification, can effectively solve the problem. (2) Combination between traditional geological surveys and modern technologies (LiDAR, aerial and semi-aerial geophysical exploration, etc.) can improve the efficiency and accuracy for identification of the most difficult and unstable slops.(3) The deep machine learning is expected to realize the intelligent automatic identification of geohazards. Currently, it shows good performance in new geohazards with significant spectral and texture characteristics, while the accuracy of automatic identification for other types, such as ancient landslides and normal potential geohazards, is still not enough.  Conclusions  More efforts are in urgent need for further research in related fields.

SUI Haigang

Detecting Building Façade Damage Caused by Earthquake Using CBAM-Improved Mask R-CNN

  Objectives  Building damage information can provide an important basis for the decision making of rapid post-earthquake assessment. Traditional building damage detection techniques mainly focus on the roof surface, thus many damaged buildings with an intact roof surface but collapsed middle floors may be neglected. We propose a method of building façade damage detection based on deep learning and multiresolution segmentation algorithm.  Methods  The method which integrates the instance segmentation and multiresolution segmentation algorithm is applied to detecting the post-earthquake building façade damage. The first thing is to collect the ground images of post-earthquake buildings in the field and perform the data augmentation. Secondly, we use the convolutional block attention module (CBAM) to improve Mask R-CNN. Then the dataset is input to the improved model for training, and finally a multiresolution segmentation algorithm is adopted to post-process the building façade damage detection results output by the CBAM-Improved Mask R-CNN.  Results  The experimental results show: (1) Collecting ground images of buildings in the field and performing image augmentation can effectively guarantee the necessary training sample size of the instance segmentation model. (2) The Mask R-CNN improved by CBAM attention mechanism significantly improves the post-earthquake building facade damage detection capabilities, which realizes the precise extraction of damage information from complex building façade backgrounds. (3) In addition, using the multiresolution segmentation algorithm to post-process the building facade damage detection results can obviously solve the blurred boundary problems caused by the accumulation of convolutional layers.  Conclusions  The proposed method can significantly improve the capability of post-earthquake building façade damage detection when compared to the traditional methods, which also raises the Mask R-CNN's accuracy, precision, recall and F2-score to a certain degree. It can be inferred that the proposed method has the strong potential to be applied to the post-earthquake building façade damage detection and therefore provides an important technical means for detecting the comprehensive and detailed building damage detection caused by earthquake.

DU Zhiqiang

Knowledge Graph Construction Method on Natural Disaster Emergency

Natural disasters occur frequently and pose a huge threat to China. Disaster prevention, mitigation, and disaster relief are eternal topics of human survival and development. However, in the field of disaster relief and emergency response, the relevant data increase sharply while the critical knowledge of emergency is obviously lacking. The "data-information-knowledge" transformation capacity is insufficient to meet the urgent needs of disaster prevention and reduction. Firstly taking natural disasters as the core, and around four elements of natural disaster events, disaster emergency tasks, disaster data, and methods, this paper proposes a knowledge graph construction method by combining a top-down approach and a bottom-up approach. Then, concept layer of knowledge graph is built from top to down, and the conceptual framework is formed through ontology modeling. Data layer of knowledge graph is built from bottom to top, and the relationship between entities is established through data acquisition, knowledge extraction, fusion, and storage. Finally, a flood disaster emergency knowledge graph is built to verify the validity of the proposed method. The concept layer in flood disaster emergency knowledge graph defines the conceptual levels, the attributes and the semantic relationships of flood disaster events, disaster emergency tasks, disaster data, and methods. The data layer in flood disaster emergency knowledge graph realizes the extraction of entities and relationships from multi-source data. After the knowledge fusion process, 3 054 nodes and 12 689 relationship edges are obtained and stored in the Neo4j graph database. The flood disaster emergency knowledge graph realizes the transformation from multi-source data to interrelated knowledge.

LÜ Guonian

Role of Geometric Algebra in High Dimensional Space Representation of Geographic Information

Geographic information space is a high-dimensional space combining virtual and real. Geographic information system (GIS) based on European geometry plays an important role in the development of geographic information science. However, because the expression of GIS geographic objects and phenomena in European-style space depends on object coordinates and the adopted coordinate system, it is difficult for the expression, calculation and analysis of geographic objects to form a multi-dimensional unified operation rule and framework, which increases the algorithm's complexity and reduces the efficiency of algorithm analysis. Geometric algebra is a kind of combination algebra based on dimensional operation. Space can be defined as the operation between vector sets. The dimension of space is directly determined by the algorithm, which realizes the unification of high-dimensional geometric calculation and analysis. Based on the unified calculation and analysis framework of geometric algebra, GIS can better express and analyze high-dimensional objects, and then improve the ability of expressing complex geographical objects and dynamic geographical phenomena, analyzing spatiotemporal multi-scale objects and integration of different scale geographical models. This lays the theoretical foundation for the development of GIS towards holographic maps with real-time dynamics, virtual-real fusion, full perspective, full elements and full content expression.

LU Pengjie

Auto-detection and Hiding of Sensitive Targets in Emergency Mapping Based on Remote Sensing Data

  Objectives  Emergency remote sensing mapping can provide support for decision-making in disaster assessment or disaster relief, and therefore plays an important role in disaster response.Traditional emergency remote sensing mapping methods use the decryption algorithms based on manual retrieval and image editing tools when processing sensitive targets. Although the traditional methods can achieve target recognition, they are inefficient and cannot meet the immediate requirements of disaster relief, which are unable to be released or applied in time. The main objective is to propose a method for auto-detecting and hiding of sensitive targets in emergency remote sensing mapping to accelerate the rapid production and release emergency remote sensing products.  Methods   Because of the huge size of remote sensing images, it is not realistic to directly hide sensitive targets. We propose a two-stage processing method automatic target detection and hiding of sensitive targets method, which consists of two neural network models: target detection model and generative adversarial network model. Firstly, Mask R-CNN, a well-known and effective target detection method, was used to detect sensitive targets from massive remote sensing data and generate target coordinates and Masks. Then, Deepfill model, one of GAN(generative adversarial networks) models, can ignore other normal areas and directly hide sensitive objects in the local area based on the coordinates and Masks information. The aircraft objects in the remote sensing image was used as an application example to verify the feasibility of our method, furthermore, we added the reconstruction of loss function, candidate frame optimization of region recommendation network, Mask optimization algorithm, and attention mechanism reconstruction based on the characteristics of the aircraft objects. Mask R-CNN model and Deepfill model have different training principles, so we trained and tuned them separately, and finally combine the trained models. We randomly extracted images from RSOD(remote sensing object detection) and DOTA(a large-scale dataset for object detection in aerial images) to form a new dataset. A total of 1 607 images were obtained for Mask R-CNN model training, and 9 502 images were used for Deepfill model training. All these samples are divided into training set and verification set according to the ratio of 0.8: 0.2. The performance of the Mask R-CNN model was evaluated by precision, recall rate, missing detect rate and F1-score; the performance evaluation indicators of the Deepfill model are PSNR(peak signal to noise ratio) and SSIM(structural similarity).  Results   46 images were extracted separately from the original dataset to test the performance of the trained models. In the target detect stage, the accuracy of the benchmark model was 98.13%, the recall rate was 44.21%, the missed detection rate was 55.79%, and the F1-score was 60.96%. Many targets were not detected. For comparison, the accuracy of our method reaches 94.65%, the recall rate reaches 81.89%, which is 85.23% higher than the benchmark model; the missed detection rate reaches 18.11%, which is 67.54% lower than the benchmark model; the F1-score reaches 87.81%, which is 44.05% higher than the benchmark model. In the inpainting stage, the average PSNR in this method reaches 32.26, and the average SSIM value is 0.98.  Conclusions   In the proposed method, the recall rate and F1-score of aircraft targets in remote sensing images have been significantly improved, the inpainting processing effect is reasonable and natural, and the overall time of the emergency remote sensing mapping process is saved, indicating that the two-stage model works well. In the future, it can further expand the detection and processing of other sensitive targets, accelerate the production and release efficiency of disaster emergency response map products, and thus improve the ability of disaster prevention and relief.


Key Technologies of Seamless Location in Emergency Rescue

  Objectives  Emergency location is one of the key technologies for emergency rescue of major emergencies such as earthquake, fire, mine accident and so on. However, at the present stage, the research on the theory and technology of emergency location is still not systematized, the rapid construction method of seamless benchmark and collaborative location model for emergency location are not robust enough, and the lack of positioning terminals has become an urgent problem to be solved.  Methods   Firstly, we expound the research status at home and abroad according to the three commonly used emergency positioning modes of GNSS(global navigation satellite system), autonomous positioning and local area network electromagnetic wave positioning.Secondly, based on the technologies of emergency CORS(continuously operating reference stations) and UWB(ultra wide band) networking, a general emergency seamless positioning solution for many kinds of disasters is constructed. Then, the key technologies such as low power consumption of emergency positioning terminal manufacturing, synchronous information acquisition and efficient calculation of embedded firmware are overcome, and hardware equipment such as GNSS/UWB base station is developed. And, the emergency location service system is designed and developed, which solves the problems of emergency position networking, personnel location and on-site scheduling. Finally, the message transmission protocol of emergency navigation and location service system is proposed, which promotes the development of emergency rescue equipment standardization.  Results   Through the research on the key technologies such as the manufacture of emergency location terminals such as GNSS/UWB base station, the development of emergency location and location service system based on cloud platform, and the formulation of message transmission protocol of emergency navigation and location service system, we put forward a seamless positioning solution for indoor and outdoor under emergency conditions, which solves the problems of rapid construction of indoor and outdoor seamless positioning datum, personnel positioning and command scheduling in emergency.  Conclusions   The purpose is to create an emergency-oriented indoor seamless positioning technology system and innovate the existing emergency positioning technology methods.

DU Qingyun

Adaptive Cartographic Techniques for Disaster Emergency Services

  Objectives  In disaster emergency services, the spatial-temporal distribution maps of geographic entities, thematic information statistical mapping, etc. have become important auxiliary decision-making methods. In the face of unpredictable, complex and changing situations of disaster prevention and reduction, disaster emergency mapping services require rapid response, real-time updates to comprehensively and dynamically reflect the information of all aspects of emergency and disaster reduction work.   Methods   In order to fully meet the content and efficiency requirements of emergency disaster reduction work, we proposed an adaptive mapping method for disaster emergency services. First, based on the comprehensive analysis of the mapping requirements, map content and operation experience of the disaster emergency scene, we proposed a user-oriented adaptive mapping strategies, and described its specific mapping content in detail, including regional scale, mapping template, dynamic symbol and real-time data. Then, according to the characteristics of the disaster scene and adaptive mapping, the overall technical process was designed. The key technologies such as cartographic knowledge expression, construction of mapping templates, production engine of symbols, situational symbol plotting, order-based mapping mode and personal mapping space were also analyzed in depth to form a complete adaptive mapping solution for disaster emergency.   Results   We used six types of disasters such as earthquake, fire, flood, building collapse, geological disaster and traffic accident as application examples.   Conclusions   By analyzing previous excellent disaster maps and summering the mapping variables and the relationship between the variables, we used the proposed adaptive mapping technologies to extract 300 kinds of disaster mapping knowledge rules, 200 sets of disaster mapping templates and 100 kinds of dynamic mapping symbols, and build a disaster emergency adaptive rapid mapping platform to provide technical reference for disaster emergency services from the theoretical and practical levels.

WANG Taoyang

Space Remote Sensing Dynamic Monitoring for Urban Complex

Urban complex is the basic unit of urban politics, economy and social life, and space remote sensing dynamic monitoring for urban complex is an efficient and accurate technical method. A space remote sensing dynamic monitoring system for urban complex is proposed and constructed from the aspects of application demand, technical method, remote sensing products, management release, etc. Using the system, the construction progress and surrounding water environment monitoring of the urban complex of Huoshenshan Hospital and Leishenshan Hospital are carried out. The construction progress of Huoshenshan Hospital and Leishenshan Hospital is monitored by high-resolution optical satellites such as Gaofen-2, Jilin-1 and Pleiades, which is identical with the construction progress in the news report and the officially published hospital area. The construction intensity of Huoshenshan Hospital is monitored by the high-resolution night light satellite Jilin-1, most areas of the construction plant are under high-intensity construction at night. The water environment around Huoshenshan Hospital and Leishenshan Hospital is monitored by the hyperspectral satellite Zhuhai-1, the construction process has no significant impact on the surrounding water environment. The surface stability of Huoshenshan Hospital and Leishenshan Hospital before construction is analyzed by the high-resolution radar satellite Sentinel-1A, there is no obvious surface subsidence in the construction area of Huoshenshan Hospital, and there are different degrees of surface subsidence signals in the surrounding areas of Leishenshan Hospital. In the critical period of fighting against the coronavirus disease 2019(COVID-19), it has met the public's attention needs and plays a certain role in stabilizing social mood. A retrospective monitoring of the collapse of Xinjia hotel in Quanzhou is carried out to provide data reference for accident liability analysis. The deformation of Xinjia hotel is mainly caused by the south wall, and the foundation settlement is not obvious. This result is consistent with the fact that the hotel collapses to the south, and the main reason for the collapse is the instability of the internal structure of the building, rather than the uneven ground settlement. The effectiveness of the system is verified.

  • All visit:
  • Today's visit: