Visual Route Recognition in Urban Spaces: A Scalable Approach Using Open Street View Data
This article presents a novel pipeline for visual route recognition (VRR) in large-scale urban environments, leveraging open street view data. The proposed approach aims to identify the path of a video recorder by analyzing visual cues from continuous video frames and street landmarks, evaluated thr...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10819660/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582413590462464 |
|---|---|
| author | Menglin Wu Qingren Jia Anran Yang Zhinong Zhong Mengyu Ma Luo Chen Ning Jing |
| author_facet | Menglin Wu Qingren Jia Anran Yang Zhinong Zhong Mengyu Ma Luo Chen Ning Jing |
| author_sort | Menglin Wu |
| collection | DOAJ |
| description | This article presents a novel pipeline for visual route recognition (VRR) in large-scale urban environments, leveraging open street view data. The proposed approach aims to identify the path of a video recorder by analyzing visual cues from continuous video frames and street landmarks, evaluated through datasets from New York and Taipei City. The pipeline begins with semantic visual geo-localization (SemVG), a semantic fused feature extraction network that filters out nonlandmark noise, generating robust visual representations. We construct a feature database from multiperspective street view images to enable efficient feature retrieval for query video frames. In addition, we introduce a spatio-temporal trajectory reconstruction method that corrects mismatches in the camera's motion path, ensuring consistency. Our contributions include the development of SemVG, a method for maintaining spatio-temporal consistency in trajectory reconstruction, and a large-scale Taipei dataset designed for VRR. This work has implications for urban surveillance, law enforcement, and smart city applications, supporting urban planning, resource management, search and rescue, and augmented reality navigation by improving localization without specialized hardware. |
| format | Article |
| id | doaj-art-e9e1b538f9664535a22d2649ea1a09e3 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-e9e1b538f9664535a22d2649ea1a09e32025-01-30T00:00:17ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184004401910.1109/JSTARS.2024.352429610819660Visual Route Recognition in Urban Spaces: A Scalable Approach Using Open Street View DataMenglin Wu0https://orcid.org/0009-0002-9476-8258Qingren Jia1https://orcid.org/0000-0002-3741-5897Anran Yang2Zhinong Zhong3Mengyu Ma4Luo Chen5https://orcid.org/0000-0003-2665-6086Ning Jing6College of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaThis article presents a novel pipeline for visual route recognition (VRR) in large-scale urban environments, leveraging open street view data. The proposed approach aims to identify the path of a video recorder by analyzing visual cues from continuous video frames and street landmarks, evaluated through datasets from New York and Taipei City. The pipeline begins with semantic visual geo-localization (SemVG), a semantic fused feature extraction network that filters out nonlandmark noise, generating robust visual representations. We construct a feature database from multiperspective street view images to enable efficient feature retrieval for query video frames. In addition, we introduce a spatio-temporal trajectory reconstruction method that corrects mismatches in the camera's motion path, ensuring consistency. Our contributions include the development of SemVG, a method for maintaining spatio-temporal consistency in trajectory reconstruction, and a large-scale Taipei dataset designed for VRR. This work has implications for urban surveillance, law enforcement, and smart city applications, supporting urban planning, resource management, search and rescue, and augmented reality navigation by improving localization without specialized hardware.https://ieeexplore.ieee.org/document/10819660/Metric learningstreet view imagerytrajectory reconstructionvisual geo-localization (VG)visual route recognition (visual route recognition) |
| spellingShingle | Menglin Wu Qingren Jia Anran Yang Zhinong Zhong Mengyu Ma Luo Chen Ning Jing Visual Route Recognition in Urban Spaces: A Scalable Approach Using Open Street View Data IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Metric learning street view imagery trajectory reconstruction visual geo-localization (VG) visual route recognition (visual route recognition) |
| title | Visual Route Recognition in Urban Spaces: A Scalable Approach Using Open Street View Data |
| title_full | Visual Route Recognition in Urban Spaces: A Scalable Approach Using Open Street View Data |
| title_fullStr | Visual Route Recognition in Urban Spaces: A Scalable Approach Using Open Street View Data |
| title_full_unstemmed | Visual Route Recognition in Urban Spaces: A Scalable Approach Using Open Street View Data |
| title_short | Visual Route Recognition in Urban Spaces: A Scalable Approach Using Open Street View Data |
| title_sort | visual route recognition in urban spaces a scalable approach using open street view data |
| topic | Metric learning street view imagery trajectory reconstruction visual geo-localization (VG) visual route recognition (visual route recognition) |
| url | https://ieeexplore.ieee.org/document/10819660/ |
| work_keys_str_mv | AT menglinwu visualrouterecognitioninurbanspacesascalableapproachusingopenstreetviewdata AT qingrenjia visualrouterecognitioninurbanspacesascalableapproachusingopenstreetviewdata AT anranyang visualrouterecognitioninurbanspacesascalableapproachusingopenstreetviewdata AT zhinongzhong visualrouterecognitioninurbanspacesascalableapproachusingopenstreetviewdata AT mengyuma visualrouterecognitioninurbanspacesascalableapproachusingopenstreetviewdata AT luochen visualrouterecognitioninurbanspacesascalableapproachusingopenstreetviewdata AT ningjing visualrouterecognitioninurbanspacesascalableapproachusingopenstreetviewdata |