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

Active perception for fruit mapping and harvesting is a difficult task sinceocclusions occur frequently and the location as well as size of fruits changeover time. State-of-the-art viewpoint planning approaches utilizecomputationally expensive ray casting operations to find good viewpoints aimingat maximizing information gain and covering the fruits in the scene. In thispaper, we present a novel viewpoint planning approach that explicitly usesinformation about the predicted fruit shapes to compute targeted viewpointsthat observe as yet unobserved parts of the fruits. Furthermore, we formulatethe concept of viewpoint dissimilarity to reduce the sampling space for moreefficient selection of useful, dissimilar viewpoints. Our simulationexperiments with a UR5e arm equipped with an RGB-D sensor provide aquantitative demonstration of the efficacy of our iterative next best viewplanning method based on shape completion. In comparative experiments with astate-of-the-art viewpoint planner, we demonstrate improvement not only in theestimation of the fruit sizes, but also in their reconstruction, whilesignificantly reducing the planning time. Finally, we show the viability of ourapproach for mapping sweet peppers plants with a real robotic system in acommercial glasshouse.

NBV-SC: Next Best View Planning based on Shape Completion for Fruit Mapping and Reconstruction