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

The estimation of the relative pose of two camera views is a fundamentalproblem in computer vision. Kneip et al. proposed to solve this problem byintroducing the normal epipolar constraint (NEC). However, their approach doesnot take into account uncertainties, so that the accuracy of the estimatedrelative pose is highly dependent on accurate feature positions in the targetframe. In this work, we introduce the probabilistic normal epipolar constraint(PNEC) that overcomes this limitation by accounting for anisotropic andinhomogeneous uncertainties in the feature positions. To this end, we propose anovel objective function, along with an efficient optimization scheme thateffectively minimizes our objective while maintaining real-time performance. Inexperiments on synthetic data, we demonstrate that the novel PNEC yields moreaccurate rotation estimates than the original NEC and several popular relativerotation estimation algorithms. Furthermore, we integrate the proposed methodinto a state-of-the-art monocular rotation-only odometry system and achieveconsistently improved results for the real-world KITTI dataset.

The Probabilistic Normal Epipolar Constraint for Frame-To-Frame Rotation Optimization under Uncertain Feature Positions