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

Scale ambiguity is a fundamental problem in monocular visual odometry.Typical solutions include loop closure detection and environment informationmining. For applications like self-driving cars, loop closure is not alwaysavailable, hence mining prior knowledge from the environment becomes a morepromising approach. In this paper, with the assumption of a constant height ofthe camera above the ground, we develop a light-weight scale recovery frameworkleveraging an accurate and robust estimation of the ground plane. The frameworkincludes a ground point extraction algorithm for selecting high-quality pointson the ground plane, and a ground point aggregation algorithm for joining theextracted ground points in a local sliding window. Based on the aggregateddata, the scale is finally recovered by solving a least-squares problem using aRANSAC-based optimizer. Sufficient data and robust optimizer enable a highlyaccurate scale recovery. Experiments on the KITTI dataset show that theproposed framework can achieve state-of-the-art accuracy in terms oftranslation errors, while maintaining competitive performance on the rotationerror. Due to the light-weight design, our framework also demonstrates a highfrequency of 20Hz on the dataset.

Accurate and Robust Scale Recovery for Monocular Visual Odometry Based on Plane Geometry