From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909183246336000 |
|---|---|
| author | Qian, Zekun Han, Ruize Feng, Wei Wang, Feifan Wang, Song |
| author_facet | Qian, Zekun Han, Ruize Feng, Wei Wang, Feifan Wang, Song |
| contents | We tackle a new problem of multi-view camera and subject registration in the bird's eye view (BEV) without pre-given camera calibration. This is a very challenging problem since its only input is several RGB images from different first-person views (FPVs) for a multi-person scene, without the BEV image and the calibration of the FPVs, while the output is a unified plane with the localization and orientation of both the subjects and cameras in a BEV. We propose an end-to-end framework solving this problem, whose main idea can be divided into following parts: i) creating a view-transform subject detection module to transform the FPV to a virtual BEV including localization and orientation of each pedestrian, ii) deriving a geometric transformation based method to estimate camera localization and view direction, i.e., the camera registration in a unified BEV, iii) making use of spatial and appearance information to aggregate the subjects into the unified BEV. We collect a new large-scale synthetic dataset with rich annotations for evaluation. The experimental results show the remarkable effectiveness of our proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_09298 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration Qian, Zekun Han, Ruize Feng, Wei Wang, Feifan Wang, Song Computer Vision and Pattern Recognition We tackle a new problem of multi-view camera and subject registration in the bird's eye view (BEV) without pre-given camera calibration. This is a very challenging problem since its only input is several RGB images from different first-person views (FPVs) for a multi-person scene, without the BEV image and the calibration of the FPVs, while the output is a unified plane with the localization and orientation of both the subjects and cameras in a BEV. We propose an end-to-end framework solving this problem, whose main idea can be divided into following parts: i) creating a view-transform subject detection module to transform the FPV to a virtual BEV including localization and orientation of each pedestrian, ii) deriving a geometric transformation based method to estimate camera localization and view direction, i.e., the camera registration in a unified BEV, iii) making use of spatial and appearance information to aggregate the subjects into the unified BEV. We collect a new large-scale synthetic dataset with rich annotations for evaluation. The experimental results show the remarkable effectiveness of our proposed method. |
| title | From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2212.09298 |