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

Developing robot perception systems for recognizing objects in the real-worldrequires computer vision algorithms to be carefully scrutinized with respect tothe expected operating domain. This demands large quantities of ground truthdata to rigorously evaluate the performance of algorithms. This paper presentsthe EasyLabel tool for easily acquiring high quality ground truth annotation ofobjects at the pixel-level in densely cluttered scenes. In a semi-automaticprocess, complex scenes are incrementally built and EasyLabel exploits depthchange to extract precise object masks at each step. We use this tool togenerate the Object Cluttered Indoor Dataset (OCID) that captures diversesettings of objects, background, context, sensor to scene distance, viewpointangle and lighting conditions. OCID is used to perform a systematic comparisonof existing object segmentation methods. The baseline comparison supports theneed for pixel- and object-wise annotation to progress robot vision towardsrealistic applications. This insight reveals the usefulness of EasyLabel andOCID to better understand the challenges that robots face in the real-world.  Copyright 20XX IEEE. Personal use of this material is permitted. Permissionfrom IEEE must be obtained for all other uses, in any current or future media,including reprinting/republishing this material for advertising or promotionalpurposes, creating new collective works, for resale or redistribution toservers or lists, or reuse of any copyrighted component of this work in otherworks.

EasyLabel: A Semi-Automatic Pixel-wise Object Annotation Tool for Creating Robotic RGB-D Datasets