Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2023 IEEE Winter Conference on Applications of Computer Vision |
| Untertitel | WACV 2023 |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 1166-1175 |
| Seitenumfang | 10 |
| ISBN (elektronisch) | 9781665493468 |
| ISBN (Print) | 978-1-6654-9347-5 |
| Publikationsstatus | Veröffentlicht - 2023 |
| Veranstaltung | 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023 - Waikoloa, USA / Vereinigte Staaten Dauer: 3 Jan. 2023 → 7 Jan. 2023 |
Publikationsreihe
| Name | IEEE Winter Conference on Applications of Computer Vision |
|---|---|
| ISSN (Print) | 2472-6737 |
| ISSN (elektronisch) | 2642-9381 |
Abstract
Sports field registration in broadcast videos is typically interpreted as the task of homography estimation, which provides a mapping between a planar field and the corresponding visible area of the image. In contrast to previous approaches, we consider the task as a camera calibration problem. First, we introduce a differentiable objective function that is able to learn the camera pose and focal length from segment correspondences (e.g., lines, point clouds), based on pixel-level annotations for segments of a known calibration object. The calibration module iteratively minimizes the segment reprojection error induced by the estimated camera parameters. Second, we propose a novel approach for 3D sports field registration from broadcast soccer images. Compared to the typical solution, which subsequently refines an initial estimation, our solution does it in one step. The proposed method is evaluated for sports field registration on two datasets and achieves superior results compared to two state-of-the-art approaches.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Artificial intelligence
- Informatik (insg.)
- Angewandte Informatik
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2023 IEEE Winter Conference on Applications of Computer Vision: WACV 2023. Institute of Electrical and Electronics Engineers Inc., 2023. S. 1166-1175 (IEEE Winter Conference on Applications of Computer Vision).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - TVCalib
T2 - 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
AU - Theiner, Jonas
AU - Ewerth, Ralph
N1 - Funding Information: Thanks to Wolfgang Gritz and Eric Müller-Budack for reviewing this paper, Jim Rhotert for the segmentation module and Markos Stamatakis for enriching the WC14 dataset. This project has received funding from the German Federal Ministry of Education and Research (BMBF – Bundesmin-isterium für Bildung und Forschung) under 01IS20021B.
PY - 2023
Y1 - 2023
N2 - Sports field registration in broadcast videos is typically interpreted as the task of homography estimation, which provides a mapping between a planar field and the corresponding visible area of the image. In contrast to previous approaches, we consider the task as a camera calibration problem. First, we introduce a differentiable objective function that is able to learn the camera pose and focal length from segment correspondences (e.g., lines, point clouds), based on pixel-level annotations for segments of a known calibration object. The calibration module iteratively minimizes the segment reprojection error induced by the estimated camera parameters. Second, we propose a novel approach for 3D sports field registration from broadcast soccer images. Compared to the typical solution, which subsequently refines an initial estimation, our solution does it in one step. The proposed method is evaluated for sports field registration on two datasets and achieves superior results compared to two state-of-the-art approaches.
AB - Sports field registration in broadcast videos is typically interpreted as the task of homography estimation, which provides a mapping between a planar field and the corresponding visible area of the image. In contrast to previous approaches, we consider the task as a camera calibration problem. First, we introduce a differentiable objective function that is able to learn the camera pose and focal length from segment correspondences (e.g., lines, point clouds), based on pixel-level annotations for segments of a known calibration object. The calibration module iteratively minimizes the segment reprojection error induced by the estimated camera parameters. Second, we propose a novel approach for 3D sports field registration from broadcast soccer images. Compared to the typical solution, which subsequently refines an initial estimation, our solution does it in one step. The proposed method is evaluated for sports field registration on two datasets and achieves superior results compared to two state-of-the-art approaches.
KW - Algorithms: 3D computer vision
KW - Arts/games/social media
KW - Image recognition and understanding (object detection, categorization, segmentation, scene modeling, visual reasoning)
UR - http://www.scopus.com/inward/record.url?scp=85149032173&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2207.11709
DO - 10.48550/arXiv.2207.11709
M3 - Conference contribution
SN - 978-1-6654-9347-5
T3 - IEEE Winter Conference on Applications of Computer Vision
SP - 1166
EP - 1175
BT - 2023 IEEE Winter Conference on Applications of Computer Vision
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 3 January 2023 through 7 January 2023
ER -