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

Estimating the pose of a pallet and other logistics objects is crucial forvarious use cases, such as automatized material handling or tracking.Innovations in computer vision, computing power, and machine learning open upnew opportunities for device-free localization based on cameras and neuralnetworks. Large image datasets with annotated poses are required for trainingthe network. Manual annotation, especially of 6D poses, is an extremelylabor-intensive process. Hence, newer approaches often leverage synthetictraining data to automatize the process of generating annotated image datasets.In this work, the generation of synthetic training data for 6D pose estimationof pallets is presented. The data is then used to train the Deep Object PoseEstimation (DOPE) algorithm. The experimental validation of the algorithmproves that the 6D pose estimation of a standardized Euro pallet with aRed-Green-Blue (RGB) camera is feasible. The comparison of the results fromthree varying datasets under different lighting conditions shows the relevanceof an appropriate dataset design to achieve an accurate and robustlocalization. The quantitative evaluation shows an average position error ofless than 20 cm for the preferred dataset. The validated training dataset and aphotorealistic model of a Euro pallet are publicly provided.

Estimating the Pose of a Euro Pallet with an RGB Camera based on Synthetic Training Data