No Bells, Just Whistles: Sports Field Registration by Leveraging Geometric Properties
- URL: http://arxiv.org/abs/2404.08401v1
- Date: Fri, 12 Apr 2024 11:15:15 GMT
- Title: No Bells, Just Whistles: Sports Field Registration by Leveraging Geometric Properties
- Authors: Marc Gutiérrez-Pérez, Antonio Agudo,
- Abstract summary: We propose a novel calibration pipeline enabling camera calibration using a 3D soccer field model and extending the process to assess the multiple-view nature of broadcast videos.
Our method demonstrates superior performance in both multiple- and single-view 3D camera calibration while maintaining competitive results in homography estimation.
- Score: 16.278222277579655
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Broadcast sports field registration is traditionally addressed as a homography estimation task, mapping the visible image area to a planar field model, predominantly focusing on the main camera shot. Addressing the shortcomings of previous approaches, we propose a novel calibration pipeline enabling camera calibration using a 3D soccer field model and extending the process to assess the multiple-view nature of broadcast videos. Our approach begins with a keypoint generation pipeline derived from SoccerNet dataset annotations, leveraging the geometric properties of the court. Subsequently, we execute classical camera calibration through DLT algorithm in a minimalist fashion, without further refinement. Through extensive experimentation on real-world soccer broadcast datasets such as SoccerNet-Calibration, WorldCup 2014 and TS- WorldCup, our method demonstrates superior performance in both multiple- and single-view 3D camera calibration while maintaining competitive results in homography estimation compared to state-of-the-art techniques.
Related papers
- ESC: Evolutionary Stitched Camera Calibration in the Wild [0.15346678870160887]
We identify the source of significant calibration errors in multi-camera environments.
We propose the Evolutionary Stitched Camera calibration algorithm to bridge this gap.
We demonstrate the superior performance of our approach compared to state-of-the-art methods across diverse real-life football fields.
arXiv Detail & Related papers (2024-04-19T07:50:13Z) - A Universal Protocol to Benchmark Camera Calibration for Sports [6.011159943695013]
We present a new benchmarking protocol for camera calibration in sports analytics.
We show that our protocol provides fairer evaluations of camera calibration methods.
We hope to pave the way for a new stage in camera calibration for sports applications with high accuracy standards.
arXiv Detail & Related papers (2024-04-15T14:03:31Z) - Dual-Camera Smooth Zoom on Mobile Phones [55.4114152554769]
We introduce a new task, ie, dual-camera smooth zoom (DCSZ) to achieve a smooth zoom preview.
The frame models (FI) technique is a potential solution but struggles with ground-truth collection.
We suggest a data factory solution where continuous virtual cameras are assembled to generate DCSZ data by rendering reconstructed 3D models of the scene.
arXiv Detail & Related papers (2024-04-07T10:28:01Z) - Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial
Sports Field Registration [0.0]
We combine advances in 2D human pose estimation and camera calibration via partial sports field registration to demonstrate an avenue for collecting valid large-scale kinematic datasets.
We generate a synthetic dataset of more than 10k images in Unreal Engine 5 with different viewpoints, running styles, and body types.
arXiv Detail & Related papers (2023-04-10T07:41:44Z) - Deep Learning for Camera Calibration and Beyond: A Survey [100.75060862015945]
Camera calibration involves estimating camera parameters to infer geometric features from captured sequences.
Recent efforts show that learning-based solutions have the potential to be used in place of the repeatability works of manual calibrations.
arXiv Detail & Related papers (2023-03-19T04:00:05Z) - Keypoint-less Camera Calibration for Sports Field Registration in Soccer [11.374200381593267]
We introduce a differentiable objective function that is able to learn the camera pose and focal length from segment correspondences.
We propose a novel approach for 3D sports field registration from broadcast soccer images.
arXiv Detail & Related papers (2022-07-24T10:31:25Z) - Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images [82.32776379815712]
We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses.
We adopt to further improve the shape quality by leveraging cross-view information with a graph convolution network.
Our model is robust to the quality of the initial mesh and the error of camera pose, and can be combined with a differentiable function for test-time optimization.
arXiv Detail & Related papers (2022-04-21T03:42:31Z) - Self-Supervised Camera Self-Calibration from Video [34.35533943247917]
We propose a learning algorithm to regress per-sequence calibration parameters using an efficient family of general camera models.
Our procedure achieves self-calibration results with sub-pixel reprojection error, outperforming other learning-based methods.
arXiv Detail & Related papers (2021-12-06T19:42:05Z) - Camera Calibration and Player Localization in SoccerNet-v2 and
Investigation of their Representations for Action Spotting [61.92132798351982]
We distill a powerful commercial calibration tool in a recent neural network architecture on the large-scale SoccerNet dataset.
We leverage it to provide 3 ways of representing the calibration results along with player localization.
We exploit those representations within the current best architecture for the action spotting task of SoccerNet-v2.
arXiv Detail & Related papers (2021-04-19T14:21:05Z) - Wide-angle Image Rectification: A Survey [86.36118799330802]
wide-angle images contain distortions that violate the assumptions underlying pinhole camera models.
Image rectification, which aims to correct these distortions, can solve these problems.
We present a detailed description and discussion of the camera models used in different approaches.
Next, we review both traditional geometry-based image rectification methods and deep learning-based methods.
arXiv Detail & Related papers (2020-10-30T17:28:40Z) - Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled
Representation [57.11299763566534]
We present a solution to recover 3D pose from multi-view images captured with spatially calibrated cameras.
We exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentangled from camera view-points.
Our architecture then conditions the learned representation on camera projection operators to produce accurate per-view 2d detections.
arXiv Detail & Related papers (2020-04-05T12:52:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.