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

Point cloud registration sits at the core of many important and challenging3D perception problems including autonomous navigation, SLAM, object/scenerecognition, and augmented reality. In this paper, we present a newregistration algorithm that is able to achieve state-of-the-art speed andaccuracy through its use of a hierarchical Gaussian Mixture Model (GMM)representation. Our method constructs a top-down multi-scale representation ofpoint cloud data by recursively running many small-scale data likelihoodsegmentations in parallel on a GPU. We leverage the resulting representationusing a novel PCA-based optimization criterion that adaptively finds the bestscale to perform data association between spatial subsets of point cloud data.Compared to previous Iterative Closest Point and GMM-based techniques, ourtree-based point association algorithm performs data association inlogarithmic-time while dynamically adjusting the level of detail to best matchthe complexity and spatial distribution characteristics of local scenegeometry. In addition, unlike other GMM methods that restrict covariances to beisotropic, our new PCA-based optimization criterion well-approximates the trueMLE solution even when fully anisotropic Gaussian covariances are used.Efficient data association, multi-scale adaptability, and a robust MLEapproximation produce an algorithm that is up to an order of magnitude bothfaster and more accurate than current state-of-the-art on a wide variety of 3Ddatasets captured from LiDAR to structured light.

Fast and Accurate Point Cloud Registration using Trees of Gaussian Mixtures