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

Visual reconstruction of tomato plants by a robot is extremely challengingdue to the high levels of variation and occlusion in greenhouse environments.The paradigm of active-vision helps overcome these challenges by reasoningabout previously acquired information and systematically planning cameraviewpoints to gather novel information about the plant. However, existingactive-vision algorithms cannot perform well on targeted perception objectives,such as the 3D reconstruction of leaf nodes, because they do not distinguishbetween the plant-parts that need to be reconstructed and the rest of theplant. In this paper, we propose an attention-driven active-vision algorithmthat considers only the relevant plant-parts according to the task-at-hand. Theproposed approach was evaluated in a simulated environment on the task of 3Dreconstruction of tomato plants at varying levels of attention, namely thewhole plant, the main stem and the leaf nodes. Compared to pre-defined andrandom approaches, our approach improves the accuracy of 3D reconstruction by9.7% and 5.3% for the whole plant, 14.2% and 7.9% for the main stem, and 25.9%and 17.3% for the leaf nodes respectively within the first 3 viewpoints. Also,compared to pre-defined and random approaches, our approach reconstructs 80% ofthe whole plant and the main stem in 1 less viewpoint and 80% of the leaf nodesin 3 less viewpoints. We also demonstrated that the attention-driven NBVplanner works effectively despite changes to the plant models, the amount ofocclusion, the number of candidate viewpoints and the resolutions ofreconstruction. By adding an attention mechanism to active-vision, it ispossible to efficiently reconstruct the whole plant and targeted plant parts.We conclude that an attention mechanism for active-vision is necessary tosignificantly improve the quality of perception in complex agro-foodenvironments.

Attention-driven Active Vision for Efficient Reconstruction of Plants and Targeted Plant Parts