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

Monitoring plants and fruits at high resolution play a key role in the futureof agriculture. Accurate 3D information can pave the way to a diverse number ofrobotic applications in agriculture ranging from autonomous harvesting toprecise yield estimation. Obtaining such 3D information is non-trivial asagricultural environments are often repetitive and cluttered, and one has toaccount for the partial observability of fruit and plants. In this paper, weaddress the problem of jointly estimating complete 3D shapes of fruit and theirpose in a 3D multi-resolution map built by a mobile robot. To this end, wepropose an online multi-resolution panoptic mapping system where regions ofinterest are represented with a higher resolution. We exploit data to learn ageneral fruit shape representation that we use at inference time together withan occlusion-aware differentiable rendering pipeline to complete partial fruitobservations and estimate the 7 DoF pose of each fruit in the map. Theexperiments presented in this paper evaluated both in the controlledenvironment and in a commercial greenhouse, show that our novel algorithmyields higher completion and pose estimation accuracy than existing methods,with an improvement of 41% in completion accuracy and 52% in pose estimationaccuracy while keeping a low inference time of 0.6s in average. Codes areavailable at: https://github.com/PRBonn/HortiMapping.

Panoptic Mapping with Fruit Completion and Pose Estimation for Horticultural Robots