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

Keypoint annotation in point clouds is an important task for 3Dreconstruction, object tracking and alignment, in particular in deformable ormoving scenes. In the context of agriculture robotics, it is a critical taskfor livestock automation to work toward condition assessment or behaviourrecognition. In this work, we propose a novel approach for semantic keypointannotation in point clouds, by reformulating the keypoint extraction as aregression problem of the distance between the keypoints and the rest of thepoint cloud. We use the distance on the point cloud manifold mapped into aradial basis function (RBF), which is then learned using an encoder-decoderarchitecture. Special consideration is given to the data augmentation specificto multi-depth-camera systems by considering noise over the extrinsiccalibration and camera frame dropout. Additionally, we investigatecomputationally efficient non-rigid deformation methods that can be applied toanimal point clouds. Our method is tested on data collected in the field, onmoving beef cattle, with a calibrated system of multiple hardware-synchronisedRGB-D cameras.

Semantic keypoint extraction for scanned animals using multi-depth-camera systems