<h2 toutiao-origin="h2" > the content of this article is from the Journal of Surveying and Mapping, No. 8, 2021</h2>
Research on the extraction of urban road network change information and its impact on land use
Wang Shuai
Wuhan Institute of Surveying and Mapping, Wuhan 430022, Hubei
Received:2020-08-27
Fund Project: Hubei Province Postdoctoral Funding Project
Citation format: Wang Shuai. Research on Information Extraction of Urban Road Network Change and Its Impact on Land Use[J]. Journal of Geomatics,2021,50(8):1136-1136.] DOI: 10.11947/j.AGCS.2021.20200412
WANG Shuai. Research on the change information extraction of urban road network and its impact on land use[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8): 1136-1136. DOI: 10.11947/j.AGCS.2021.20200412
Read more: http://xb.sinomaps.com/article/2021/1001-1595/2021-8-1136.htm
Abstract of doctoral dissertation
Urban road networks interact with land use as a special type of land cover. Road changes in modern urban systems are becoming more and more frequent, how to quickly and accurately extract the change information of urban road network can not only support the update needs of the basic mapping data of the road network, but also provide auxiliary support for urban land use. Based on remote sensing and vector data, the paper extracts the change information of road network, and analyzes the correlation between urban road network structure and change and land use. The main research contents are as follows:
(1) Deep learning technology is used to extract and interpret the change information of remote sensing image road network. In deep fully convolutional neural networks, the real feeling is much smaller than the theoretical field of feeling. This makes it impossible for the network to fully integrate important global contextual information, reduces the model's perception of the scene, and weakens the consistency of the classification of objects in the scene. In addition, the deep learning network model uses the pooling layer for downsampling, allowing the network to see larger contextual information, but this results in the loss of a large amount of high-frequency detail information. In view of this problem, a network model is proposed, called CDG (coord-dense-global) network model. The model is divided into three parts: the Coordinate Convolutional Information Fusion Module, the Improved SenseNet Network, and the Global Attention Information Enhancement Module. Experimental results show that the coordinate convolution information fusion module can obtain more accurate spatial feature information in road extraction, and enhance road boundary information and detail information. The global attention information enhancement module can obtain more contextual information by expanding the sensory field, strengthen the global context information of highly discriminant features, improve the consistency of pixel classification, and maintain the continuity of the road. The improved SenseNet network adopts a dense connection structure to extract and accumulate the multi-level features of the original image, and introduces the feature information recorded in the upsampling process into the downsampling process through the jump connection to enhance feature generation, strengthen the sensitivity of the network to the detailed road, and improve the accuracy of road network extraction.
(2) The target matching technology is used to identify and extract the vector road network change information. The traditional "node-arc" road network data organization method is difficult to analyze and operate the geometric characteristics of linear elements as a whole, which separates the understanding of the overall road object and lacks the measurement of the overall road geometric characteristics. This way of organizing data is inconsistent with the human understanding of road entity objects. Faced with such a problem, the proposed target matching algorithm takes stroke as the matching unit, and uses the length, angle and spatial distance indicators in the overall matching of the stroke to calculate the geometric similarity by assigning different weights and thresholds, combines the geometric features with the spatial topological relationship of the neighborhood space, and calculates the structural similarity of the spatial scene after improving the evaluation method. After performing the stroke overall matching step, a stroke partial matching algorithm is designed for the existing mismatch. The stroke partial matching algorithm based on arc segment decomposition (SPMA-S) is designed, which preserves the original two sets of road network data to the greatest extent. Design a stroke partial matching algorithm based on vertex decomposition (SPMA-V) can solve problems in local matching between independent line segments (such as growth, shortening, topology changes, etc.). The experimental results show that the matching accuracy, recall rate and operation efficiency of the algorithm are better.
(3) Analysis of the relationship between urban road network structure and change and land use. Urban road networks interact with land use, and urban land use can be distinguished according to its physical attributes or social functions. The centrality index of road network can reflect the structural characteristics of road network very well, and the previous research on the relationship between road network centrality and land use intensity relies on land cover data, ignoring the social function of urban land use. Using point-of-interest (POI) classification data can determine not only urban land use type, but also urban land use intensity. Analyzing the correlation between road network centrality and land use is conducive to the implementation of urban land use planning and transportation planning. The incremental changes of road network and the incremental changes of urban construction land in the grid of administrative units in 61 blocks of Shenzhen are counted, and the correlation between road network changes and land use is analyzed, and the results show that the road network changes have a significant impact on urban land use expansion.
About the Author
About author:Shuai Wang (1987-), male, graduated from Wuhan University in June 2020 with a doctorate degree in engineering (supervisor: Professor Guo Qingsheng), whose research direction is intelligent processing and visualization of geographic information.
E-mail: [email protected]
Recommended in previous periods
information
○ Vote | "Southern Digital" Cup "Surveying and Mapping Bulletin" 2021 Excellent Paper Invites You to Vote!
○ UAV Industry Innovation and Application Conference (2021) - and the 3rd Pegasus Robot Industry Application Conference Notice
○ Zhejiang Provincial Water Conservancy and Hydropower Survey and Design Institute 2022 Campus Recruitment Announcement (including surveying and mapping, geoscience related majors)
○ Application Guide for 2021 Open Projects of the Key Laboratory of the Ministry of Education of the Lyra Project
meeting
○ Notice No. 2 of the 8th National Conference on Virtual Geographic Environment (CVGE 2021).
○ The 4th International Symposium on Earth Sciences and Surveying (IFGG 2021)
○ Notice of the 8th "Frontier Technology Forum on Surveying and Mapping Science" (No. 3)
¡ Meeting Notice | Notice of the 2021 Annual Conference on Theories and Methods of Geographic Information Science in China (No. 2)
c
Journal of Surveying and Mapping
○ Intelligent Surveying and Mapping Special Issue | Zhang Yongjun: Framework and preliminary practice of photogrammetry remote sensing intelligent processing technology for multi-source satellite imagery
○ Intelligent Surveying and Mapping Special Issue | Yang Bisheng: A deep learning network suitable for large-scale point cloud semantic identification in urban scenarios
○ Intelligent Surveying and Mapping Special Issue | Wu Lixin: The model and direction of collaborative intelligent monitoring of the pregnant disaster environment and disasters in the glacier basin
○ Intelligent Surveying and Mapping Special Issue | Yang Yuanxi: PNT intelligent service
Bulletin of Surveying and Mapping
○ How to identify the Internet "problem map"?
○ A new type of mapping for the digital transformation of Shanghai city
○ Development and prospect of image total station and image measurement
○ Catalogue of surveying and mapping bulletin, No. 7, 2021
Beijing Surveying and Mapping
○ Beijing Surveying and Mapping, No. 7, 2021 Abstract Recommendation (Part 2)
○ Beijing Surveying and Mapping, No. 7, 2021 Abstract Recommendation (Part 1)
○ Beijing Surveying and Mapping, No. 6, 2021 Abstract Recommendation (Part 2)
○ Beijing Surveying and Mapping, No. 6, 2021 Abstract Recommendation (Part 1)
Journal of Surveying and Mapping Science and Technology
○ Recommended by the Journal of Surveying and Mapping Science and Technology, No. 1, 2021
○ Abstract | abstract recommendation of Journal of Surveying and Mapping Science and Technology, No. 3, 2021
○ Abstract | Abstract recommendation of Journal of Surveying and Mapping Science and Technology, No. 2, 2021
○ Abstract | abstract recommendation of Journal of Surveying and Mapping Science and Technology, No. 1, 2021
Journal of Geo-Information Science
○ Journal of Geo-Information Science, No. 8, 2021
○ Special Issue Call for Papers: Social Perception and Geographic Big Data Mining (in the call for papers)
Surveying and Mapping Engineering
○ Abstract | abstract recommendation of Surveying and Mapping Engineering, Issue 4, 2021
○ Abstract | abstract recommendation of Surveying and Mapping Engineering, No. 3, 2021
○ Abstract | abstract recommendation of Surveying and Mapping Engineering, No. 2, 2021
○ Abstract | abstract recommendation of Surveying and Mapping Engineering, Issue 1, 2021
China Space Science and Technology
○ Abstract | abstract recommendation of China Space Science and Technology, No. 4, 2021
○ Abstract | recommended by China Space Science and Technology, No. 3, 2021
○ Abstract | abstract recommendation of China Space Science and Technology, No. 2, 2021
○ Abstract | abstract recommendation of China Space Science and Technology, No. 1, 2021
Satellite Applications
<h1 toutiao-origin="h1" >○ Abstract Recommended | Satellite Applications, No. 7, 2021</h1>
○ Abstract | abstract recommendation of Satellite Applications, No. 6, 2021
○ Abstract | Abstract recommendation of Satellite Applications, No. 5, 2021
○ "Satellite Application" entered the "Smart Painting Science Service" integrated media platform!
《Journal of Geodesy and Geoinformation Science》
○ Special issue call for papers | Call for Papers: Spatial Human and Social Geographic Computing (SHGSS)
○ Selected Papers | journal of "GNSS and LBS" in the Journal of Surveying and Mapping (English Edition).
《Satellite Navigation》
○ "Satellite Navigation (English)" scientific editor recruitment notice
○ Multi-source navigation (1) | Satellite Navigation key paper recommendation
○ Navigation positioning app | Featured Satellite Navigation articles
<h1 toutiao-origin="h1" >○ SatNav Essay: Looking forward to excellent papers in the field of PPP/PPP-RTK</h1>