Exploiting Motion Prior for Accurate Pose Estimation of Dashboard Cameras
This work addresses a domain-specific challenge for applications like driving map production using dashcam data, representing an incremental improvement over existing methods.
The paper tackles the problem of accurately estimating camera poses from low-quality dashboard camera images, which suffer from motion blur and dynamic objects, by leveraging inherent camera motion prior, resulting in a 22% improvement in pose estimation accuracy and enabling pose estimation for 19% more images with less reprojection error.
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).