Calibration and object correspondence in camera networks with widely separated overlapping views
This study contributes in two ways to the research of multi‐camera object tracking in the context of visual surveillance. Firstly, a semi‐automatic scene calibration method is proposed to deal with mapping a network of cameras with overlapped fields of view onto a single ground plane view, even when...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2015-06-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2013.0301 |
| _version_ | 1797684809851469824 |
|---|---|
| author | Fei Yin Dimitrios Makris Sergio A. Velastin Tim Ellis |
| author_facet | Fei Yin Dimitrios Makris Sergio A. Velastin Tim Ellis |
| author_sort | Fei Yin |
| collection | DOAJ |
| description | This study contributes in two ways to the research of multi‐camera object tracking in the context of visual surveillance. Firstly, a semi‐automatic scene calibration method is proposed to deal with mapping a network of cameras with overlapped fields of view onto a single ground plane view, even when the overlap is not substantial. The proposed method uses a semi‐supervised approach that combines tracked blobs with user‐selected line scene features to recover the homographies between camera views that are both simple and accurate. Then, based on the scene calibration information, the intersection points of the projected vertical axis of single camera blobs are used to make object correspondences across multiple views. The method works in mixed environments of both pedestrians and vehicles, and is shown to be accurate and robust against segmentation noise and occlusions. Finally, the advantage of the proposed method is demonstrated by quantitative tracking performance evaluation and comparison against previous methods. |
| first_indexed | 2024-03-12T00:35:10Z |
| format | Article |
| id | doaj.art-6fb5a060322e4a049d093e02c0e7d1ad |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:35:10Z |
| publishDate | 2015-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-6fb5a060322e4a049d093e02c0e7d1ad2023-09-15T09:37:49ZengWileyIET Computer Vision1751-96321751-96402015-06-019335436710.1049/iet-cvi.2013.0301Calibration and object correspondence in camera networks with widely separated overlapping viewsFei Yin0Dimitrios Makris1Sergio A. Velastin2Tim Ellis3Department of Computer Science, College of Information and Management ScienceHenan Agriculture UniversityZhengzhou450002People's Republic of ChinaFaculty of Science, Engineering and ComputingDigital Imaging Research CentreSchool of Computing and Information SystemsKingston UniversityPenrhyn RoadKingston upon ThamesSurreyKT1 2EEUKDepartment of Informatic EngineeringUniversidad de Santiago de ChileSantiagoChileFaculty of Science, Engineering and ComputingDigital Imaging Research CentreSchool of Computing and Information SystemsKingston UniversityPenrhyn RoadKingston upon ThamesSurreyKT1 2EEUKThis study contributes in two ways to the research of multi‐camera object tracking in the context of visual surveillance. Firstly, a semi‐automatic scene calibration method is proposed to deal with mapping a network of cameras with overlapped fields of view onto a single ground plane view, even when the overlap is not substantial. The proposed method uses a semi‐supervised approach that combines tracked blobs with user‐selected line scene features to recover the homographies between camera views that are both simple and accurate. Then, based on the scene calibration information, the intersection points of the projected vertical axis of single camera blobs are used to make object correspondences across multiple views. The method works in mixed environments of both pedestrians and vehicles, and is shown to be accurate and robust against segmentation noise and occlusions. Finally, the advantage of the proposed method is demonstrated by quantitative tracking performance evaluation and comparison against previous methods.https://doi.org/10.1049/iet-cvi.2013.0301object correspondencewidely separated overlapping viewsmulticamera object trackingvisual surveillancesemiautomatic scene calibration methodcamera network mapping |
| spellingShingle | Fei Yin Dimitrios Makris Sergio A. Velastin Tim Ellis Calibration and object correspondence in camera networks with widely separated overlapping views IET Computer Vision object correspondence widely separated overlapping views multicamera object tracking visual surveillance semiautomatic scene calibration method camera network mapping |
| title | Calibration and object correspondence in camera networks with widely separated overlapping views |
| title_full | Calibration and object correspondence in camera networks with widely separated overlapping views |
| title_fullStr | Calibration and object correspondence in camera networks with widely separated overlapping views |
| title_full_unstemmed | Calibration and object correspondence in camera networks with widely separated overlapping views |
| title_short | Calibration and object correspondence in camera networks with widely separated overlapping views |
| title_sort | calibration and object correspondence in camera networks with widely separated overlapping views |
| topic | object correspondence widely separated overlapping views multicamera object tracking visual surveillance semiautomatic scene calibration method camera network mapping |
| url | https://doi.org/10.1049/iet-cvi.2013.0301 |
| work_keys_str_mv | AT feiyin calibrationandobjectcorrespondenceincameranetworkswithwidelyseparatedoverlappingviews AT dimitriosmakris calibrationandobjectcorrespondenceincameranetworkswithwidelyseparatedoverlappingviews AT sergioavelastin calibrationandobjectcorrespondenceincameranetworkswithwidelyseparatedoverlappingviews AT timellis calibrationandobjectcorrespondenceincameranetworkswithwidelyseparatedoverlappingviews |