Low-cost framework for 3D reconstruction and track detection of the railway network using video data
3D reconstruction from video data is proposed for mapping the Egyptian railway network. A generic framework is proposed and applied based on video data. This framework mainly passes through three main stages. The pre-processing stage contains system implementation, data acquisition, the keyframes ex...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Egyptian Journal of Remote Sensing and Space Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110982322000928 |
| _version_ | 1811293068300648448 |
|---|---|
| author | Adham Mahmoud Mohamed Gomaa Mohamed Adel El Shazly |
| author_facet | Adham Mahmoud Mohamed Gomaa Mohamed Adel El Shazly |
| author_sort | Adham Mahmoud |
| collection | DOAJ |
| description | 3D reconstruction from video data is proposed for mapping the Egyptian railway network. A generic framework is proposed and applied based on video data. This framework mainly passes through three main stages. The pre-processing stage contains system implementation, data acquisition, the keyframes extraction, and camera calibration. The second stage is the generation of the 3D reconstruction models from a set of two-dimensional images. This stage is mainly based on the feature correspondence process and Structure from Motion (SfM) techniques. The 3D coordinates of the feature points and relative camera motion parameters are refined using the bundle adjustment algorithms to generate an accurate 3D reconstruction model. Many models are reconstructed based on different parameters/scenarios to evaluate the most accurate model. The best 3D model was selected and used to generate an orthogonal photo. Finally, the third stage is the track detection framework which uses the generated orthogonal image for automatic detection of railway tracks. The framework is tested on a dataset of a railway network with an approximate length of 20 km. The accuracy of the results is compared with field survey data conducted in the same area using conventional surveying instruments. From the results, the recommended train speed for reasonable video data collection is 10 kph with an overlap percentage of 95 %. The RMSE of the extracted track width is 0.03 m, and it contributes to the efficiency of our approach in the reconstruction of 3D surfaces compared to the recommended procedures in traditional techniques. |
| first_indexed | 2024-04-13T04:55:54Z |
| format | Article |
| id | doaj.art-2b5480ed22e64b6b95ecef77d2a5ce5d |
| institution | Directory Open Access Journal |
| issn | 1110-9823 |
| language | English |
| last_indexed | 2024-04-13T04:55:54Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Egyptian Journal of Remote Sensing and Space Sciences |
| spelling | doaj.art-2b5480ed22e64b6b95ecef77d2a5ce5d2022-12-22T03:01:29ZengElsevierEgyptian Journal of Remote Sensing and Space Sciences1110-98232022-12-0125410011012Low-cost framework for 3D reconstruction and track detection of the railway network using video dataAdham Mahmoud0Mohamed Gomaa Mohamed1Adel El Shazly2Civil Engineering, Faculty of Engineering, Cairo University, Giza Governorate, 12613, EgyptCorresponding author.; Civil Engineering, Faculty of Engineering, Cairo University, Giza Governorate, 12613, EgyptCivil Engineering, Faculty of Engineering, Cairo University, Giza Governorate, 12613, Egypt3D reconstruction from video data is proposed for mapping the Egyptian railway network. A generic framework is proposed and applied based on video data. This framework mainly passes through three main stages. The pre-processing stage contains system implementation, data acquisition, the keyframes extraction, and camera calibration. The second stage is the generation of the 3D reconstruction models from a set of two-dimensional images. This stage is mainly based on the feature correspondence process and Structure from Motion (SfM) techniques. The 3D coordinates of the feature points and relative camera motion parameters are refined using the bundle adjustment algorithms to generate an accurate 3D reconstruction model. Many models are reconstructed based on different parameters/scenarios to evaluate the most accurate model. The best 3D model was selected and used to generate an orthogonal photo. Finally, the third stage is the track detection framework which uses the generated orthogonal image for automatic detection of railway tracks. The framework is tested on a dataset of a railway network with an approximate length of 20 km. The accuracy of the results is compared with field survey data conducted in the same area using conventional surveying instruments. From the results, the recommended train speed for reasonable video data collection is 10 kph with an overlap percentage of 95 %. The RMSE of the extracted track width is 0.03 m, and it contributes to the efficiency of our approach in the reconstruction of 3D surfaces compared to the recommended procedures in traditional techniques.http://www.sciencedirect.com/science/article/pii/S1110982322000928Railway track detection3D reconstructionVideo data acquisitionComputer vision and photogrammetry |
| spellingShingle | Adham Mahmoud Mohamed Gomaa Mohamed Adel El Shazly Low-cost framework for 3D reconstruction and track detection of the railway network using video data Egyptian Journal of Remote Sensing and Space Sciences Railway track detection 3D reconstruction Video data acquisition Computer vision and photogrammetry |
| title | Low-cost framework for 3D reconstruction and track detection of the railway network using video data |
| title_full | Low-cost framework for 3D reconstruction and track detection of the railway network using video data |
| title_fullStr | Low-cost framework for 3D reconstruction and track detection of the railway network using video data |
| title_full_unstemmed | Low-cost framework for 3D reconstruction and track detection of the railway network using video data |
| title_short | Low-cost framework for 3D reconstruction and track detection of the railway network using video data |
| title_sort | low cost framework for 3d reconstruction and track detection of the railway network using video data |
| topic | Railway track detection 3D reconstruction Video data acquisition Computer vision and photogrammetry |
| url | http://www.sciencedirect.com/science/article/pii/S1110982322000928 |
| work_keys_str_mv | AT adhammahmoud lowcostframeworkfor3dreconstructionandtrackdetectionoftherailwaynetworkusingvideodata AT mohamedgomaamohamed lowcostframeworkfor3dreconstructionandtrackdetectionoftherailwaynetworkusingvideodata AT adelelshazly lowcostframeworkfor3dreconstructionandtrackdetectionoftherailwaynetworkusingvideodata |