A 3D WebGIS-Enhanced Representation Method Fusing Surveillance Video Information
In Internet applications, there are more and more demands for geographic information expression technology that integrates video surveillance information, but there are generally problems such as camera position, direction, field of view and other parameters that are difficult to calculate accuratel...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10239365/ |
| _version_ | 1797685376068878336 |
|---|---|
| author | Qisong Jiao Guangwei Sun Zheng Chen Liusheng Han Junfu Fan |
| author_facet | Qisong Jiao Guangwei Sun Zheng Chen Liusheng Han Junfu Fan |
| author_sort | Qisong Jiao |
| collection | DOAJ |
| description | In Internet applications, there are more and more demands for geographic information expression technology that integrates video surveillance information, but there are generally problems such as camera position, direction, field of view and other parameters that are difficult to calculate accurately, texture occlusion, etc., which seriously affect the fusion expression of 3D scenes and video information Effect. To address the above problems, in this study, movable objects and trees are removed from the model surface, and an enhanced representation framework is designed for the fusion of video and 3D WebGIS under weak constraints. At the same time, the proposed method is verified and analyzed from three aspects: feature point matching, line coincidence degree and occlusion effect. The experimental results show the following. 1) In terms of the feature point matching ability, the feature point matching ability of the proposed method is 22.22% higher than that under strong constraints. 2) In terms of the occlusion effect, the proposed method achieves a 74.12% reduction in the area of the occlusion area, which is 1.63% higher than the occlusion area reduction rate after video projection under strong constraints. 3) In terms of the straight line coincidence, the experimental results of the proposed method are significantly better than those obtained using the strong constraints method. Both the length difference of the straight line with the same name and the relative offset angle are smaller than the result of the method using the strong constraint conditions. Also, the FPS is stabilized at about 30f/s during system operation with high rendering efficiency, which further proves the feasibility and stability of this system. Experiments show that using the proposed method can reflect real geospatial information, better enhance geographic information expression and be easy to implement, providing a valuable reference for the construction of applications such as real-world 3D models and smart cities. |
| first_indexed | 2024-03-12T00:44:15Z |
| format | Article |
| id | doaj.art-8198eb1623094712859629f326d988fe |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-12T00:44:15Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8198eb1623094712859629f326d988fe2023-09-14T23:00:29ZengIEEEIEEE Access2169-35362023-01-0111970249703610.1109/ACCESS.2023.331215610239365A 3D WebGIS-Enhanced Representation Method Fusing Surveillance Video InformationQisong Jiao0Guangwei Sun1https://orcid.org/0009-0009-7433-4058Zheng Chen2Liusheng Han3Junfu Fan4https://orcid.org/0000-0001-8987-7930National Institute of Natural Hazards, Ministry of Emergency Management of China, Beijing, ChinaSchool of Architectural Engineering and Geomatics, Shandong University of Technology, Zibo, ChinaHigh-Resolution Earth Observation System Data and Application Center of Zibo, Zibo, ChinaSchool of Architectural Engineering and Geomatics, Shandong University of Technology, Zibo, ChinaSchool of Architectural Engineering and Geomatics, Shandong University of Technology, Zibo, ChinaIn Internet applications, there are more and more demands for geographic information expression technology that integrates video surveillance information, but there are generally problems such as camera position, direction, field of view and other parameters that are difficult to calculate accurately, texture occlusion, etc., which seriously affect the fusion expression of 3D scenes and video information Effect. To address the above problems, in this study, movable objects and trees are removed from the model surface, and an enhanced representation framework is designed for the fusion of video and 3D WebGIS under weak constraints. At the same time, the proposed method is verified and analyzed from three aspects: feature point matching, line coincidence degree and occlusion effect. The experimental results show the following. 1) In terms of the feature point matching ability, the feature point matching ability of the proposed method is 22.22% higher than that under strong constraints. 2) In terms of the occlusion effect, the proposed method achieves a 74.12% reduction in the area of the occlusion area, which is 1.63% higher than the occlusion area reduction rate after video projection under strong constraints. 3) In terms of the straight line coincidence, the experimental results of the proposed method are significantly better than those obtained using the strong constraints method. Both the length difference of the straight line with the same name and the relative offset angle are smaller than the result of the method using the strong constraint conditions. Also, the FPS is stabilized at about 30f/s during system operation with high rendering efficiency, which further proves the feasibility and stability of this system. Experiments show that using the proposed method can reflect real geospatial information, better enhance geographic information expression and be easy to implement, providing a valuable reference for the construction of applications such as real-world 3D models and smart cities.https://ieeexplore.ieee.org/document/10239365/Video fusionenhanced representationfeature point matchingocclusion effectslinear overlap |
| spellingShingle | Qisong Jiao Guangwei Sun Zheng Chen Liusheng Han Junfu Fan A 3D WebGIS-Enhanced Representation Method Fusing Surveillance Video Information IEEE Access Video fusion enhanced representation feature point matching occlusion effects linear overlap |
| title | A 3D WebGIS-Enhanced Representation Method Fusing Surveillance Video Information |
| title_full | A 3D WebGIS-Enhanced Representation Method Fusing Surveillance Video Information |
| title_fullStr | A 3D WebGIS-Enhanced Representation Method Fusing Surveillance Video Information |
| title_full_unstemmed | A 3D WebGIS-Enhanced Representation Method Fusing Surveillance Video Information |
| title_short | A 3D WebGIS-Enhanced Representation Method Fusing Surveillance Video Information |
| title_sort | 3d webgis enhanced representation method fusing surveillance video information |
| topic | Video fusion enhanced representation feature point matching occlusion effects linear overlap |
| url | https://ieeexplore.ieee.org/document/10239365/ |
| work_keys_str_mv | AT qisongjiao a3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation AT guangweisun a3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation AT zhengchen a3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation AT liushenghan a3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation AT junfufan a3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation AT qisongjiao 3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation AT guangweisun 3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation AT zhengchen 3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation AT liushenghan 3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation AT junfufan 3dwebgisenhancedrepresentationmethodfusingsurveillancevideoinformation |