利用行车记录仪的运动规律，提升低质视频中的相机位姿估计精度。
Exploiting Motion Prior for Accurate Pose Estimation of Dashboard Cameras
- 基于摄像头运动规律设计先验学习模块，优化特征匹配与位姿估计。
- 在真实数据集上比基线方法提升22%的位姿估计准确率（AUC5°）。
- 可处理19%更多图像，且重投影误差更低，适合自动驾驶地图更新。
行车记录仪每日记录海量驾驶视频，为道路地图构建与更新提供潜在数据源。但其拍摄图像常因运动模糊和动态物体导致质量低下，现有图像匹配方法难以准确估计相机位姿。本文提出一种基于相机运动先验的精准位姿估计方法。由于行车记录仪视频序列通常具有明显运动模式（如前向移动或横向转向），我们设计了一个姿态回归模块，用于学习此类运动先验，并将其融入对应点估计与位姿求解过程。实验表明，在真实行车记录仪数据集上，本方法在AUC5°指标上较基线提升22%，且可在SfM中成功估计19%更多图像的位姿，同时保持更低的重投影误差。
原文摘要 · Abstract (English)
Dashboard cameras (dashcams) record millions of driving videos daily, offering a valuable potential data source for various applications, including driving map production and updates. A necessary step for utilizing these dashcam data involves the estimation of camera poses. However, the low-quality images captured by dashcams, characterized by motion blurs and dynamic objects, pose challenges for existing image-matching methods in accurately estimating camera poses. In this study, we propose a precise pose estimation method for dashcam images, leveraging the inherent camera motion prior. Typically, image sequences captured by dash cameras exhibit pronounced motion prior, such as forward movement or lateral turns, which serve as essential cues for correspondence estimation. Building upon this observation, we devise a pose regression module aimed at learning camera motion prior, subsequently integrating these prior into both correspondences and pose estimation processes. The experiment shows that, in real dashcams dataset, our method is 22% better than the baseline for pose estimation in AUC5\textdegree, and it can estimate poses for 19% more images with less reprojection error in Structure from Motion (SfM).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。