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

Large-scale semantic image annotation is a significant challenge forlearning-based perception systems in robotics. Current approaches often rely onhuman labelers, which can be expensive, or simulation data, which can visuallyor physically differ from real data. This paper proposes Labels fromUltraViolet (LUV), a novel framework that enables rapid, labeled datacollection in real manipulation environments without human labeling. LUV usestransparent, ultraviolet-fluorescent paint with programmable ultraviolet LEDsto collect paired images of a scene in standard lighting and UV lighting toautonomously extract segmentation masks and keypoints via color segmentation.We apply LUV to a suite of diverse robot perception tasks to evaluate itslabeling quality, flexibility, and data collection rate. Results suggest thatLUV is 180-2500 times faster than a human labeler across the tasks. We showthat LUV provides labels consistent with human annotations on unpainted testimages. The networks trained on these labels are used to smooth and foldcrumpled towels with 83% success rate and achieve 1.7mm position error withrespect to human labels on a surgical needle pose estimation task. The low costof LUV makes it ideal as a lightweight replacement for human labeling systems,with the one-time setup costs at $300 equivalent to the cost of collectingaround 200 semantic segmentation labels on Amazon Mechanical Turk. Code,datasets, visualizations, and supplementary material can be found athttps://sites.google.com/berkeley.edu/luv

All You Need is LUV: Unsupervised Collection of Labeled Images using Invisible UV Fluorescent Indicators