English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate registration of 2D imagery with point clouds is a key technology forimage-LiDAR point cloud fusion, camera to laser scanner calibration and cameralocalization. Despite continuous improvements, automatic registration of 2D and3D data without using additional textured information still faces greatchallenges. In this paper, we propose a new 2D-3D registration method toestimate 2D-3D line feature correspondences and the camera pose in untexturedpoint clouds of structured environments. Specifically, we first use geometricconstraints between vanishing points and 3D parallel lines to compute allfeasible camera rotations. Then, we utilize a hypothesis testing strategy toestimate the 2D-3D line correspondences and the translation vector. By checkingthe consistency with computed correspondences, the best rotation matrix can befound. Finally, the camera pose is further refined using non-linearoptimization with all the 2D-3D line correspondences. The experimental resultsdemonstrate the effectiveness of the proposed method on the synthetic and realdataset (outdoors and indoors) with repeated structures and rapid depthchanges.

Line-based Camera Pose Estimation in Point Cloud of Structured Environments