Loading…

A Motion based Real-time Foveation Control Loop for Rapid and Relevant 3D Laser Scanning

We present an implementation of a novel foveating 3D sensor concept, inspired by the human eye, which intends to allow future robots to better interact with their surroundings. The sensor is based on a time-of-flight laser scanning technology, where each range distance measurement is performed indiv...

Full description

Saved in:
Bibliographic Details
Main Authors: Breivik, Gøril Margrethe, Thielemann, Jens T, Berge, Asbjørn, Skotheim, Øystein, Kirkhus, Trine
Format: Book
Language:English
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Breivik, Gøril Margrethe
Thielemann, Jens T
Berge, Asbjørn
Skotheim, Øystein
Kirkhus, Trine
description We present an implementation of a novel foveating 3D sensor concept, inspired by the human eye, which intends to allow future robots to better interact with their surroundings. The sensor is based on a time-of-flight laser scanning technology, where each range distance measurement is performed individually for increased quality. Micro-mirrors enable detailed control on where and when each sample point is acquired in the scene. By finding regions-of-interest (ROIs) and mainly concentrating the data acquisition here, the spatial resolution or frame rate of these ROIs can be significantly increased compared to a non-foveating system. Foveation is enabled through a real-time implementation of a feed-back control loop for the sensor hardware, based on vision algorithms for 3D scene analysis. In this paper, we describe and apply an algorithm for detecting ROIs based on motion detection in range data using background modeling. Heuristics are incorporated to cope with camera motion. We report first results applying this algorithm to scenes with moving objects, and show that the foveation capability allows the frame rate to be increased by up to 8.2 compared to a non-foveating sensor, utilizing up to 99% of the potential frame rate increase. The incorporated heuristics significantly improves the foveation’s performance for moving camera scenes.
format book
fullrecord <record><control><sourceid>cristin_3HK</sourceid><recordid>TN_cdi_cristin_nora_11250_2431527</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>11250_2431527</sourcerecordid><originalsourceid>FETCH-cristin_nora_11250_24315273</originalsourceid><addsrcrecordid>eNqNjDkOwjAQAN1QIOAPywMiYZuIGgUiitAECjprSRy0ktmNbCvv5xAPoJpiRjNXtz2cJZMw3DH5HlqPocj09FDL5PFrKuEcJUAjMsIgEVocqQfkTx78hJzBHqB5DyJcOmQmfizVbMCQ_OrHhVrXx2t1KrpIKRM7lohOa1NunNlaXZqd_ad5AZmLOAE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>book</recordtype></control><display><type>book</type><title>A Motion based Real-time Foveation Control Loop for Rapid and Relevant 3D Laser Scanning</title><source>NORA - Norwegian Open Research Archives</source><creator>Breivik, Gøril Margrethe ; Thielemann, Jens T ; Berge, Asbjørn ; Skotheim, Øystein ; Kirkhus, Trine</creator><creatorcontrib>Breivik, Gøril Margrethe ; Thielemann, Jens T ; Berge, Asbjørn ; Skotheim, Øystein ; Kirkhus, Trine</creatorcontrib><description>We present an implementation of a novel foveating 3D sensor concept, inspired by the human eye, which intends to allow future robots to better interact with their surroundings. The sensor is based on a time-of-flight laser scanning technology, where each range distance measurement is performed individually for increased quality. Micro-mirrors enable detailed control on where and when each sample point is acquired in the scene. By finding regions-of-interest (ROIs) and mainly concentrating the data acquisition here, the spatial resolution or frame rate of these ROIs can be significantly increased compared to a non-foveating system. Foveation is enabled through a real-time implementation of a feed-back control loop for the sensor hardware, based on vision algorithms for 3D scene analysis. In this paper, we describe and apply an algorithm for detecting ROIs based on motion detection in range data using background modeling. Heuristics are incorporated to cope with camera motion. We report first results applying this algorithm to scenes with moving objects, and show that the foveation capability allows the frame rate to be increased by up to 8.2 compared to a non-foveating sensor, utilizing up to 99% of the potential frame rate increase. The incorporated heuristics significantly improves the foveation’s performance for moving camera scenes.</description><language>eng</language><ispartof>IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2011, 2011</ispartof><rights>info:eu-repo/semantics/openAccess</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,307,780,885,4048,26567</link.rule.ids><linktorsrc>$$Uhttp://hdl.handle.net/11250/2431527$$EView_record_in_NORA$$FView_record_in_$$GNORA$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Breivik, Gøril Margrethe</creatorcontrib><creatorcontrib>Thielemann, Jens T</creatorcontrib><creatorcontrib>Berge, Asbjørn</creatorcontrib><creatorcontrib>Skotheim, Øystein</creatorcontrib><creatorcontrib>Kirkhus, Trine</creatorcontrib><title>A Motion based Real-time Foveation Control Loop for Rapid and Relevant 3D Laser Scanning</title><title>IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2011</title><description>We present an implementation of a novel foveating 3D sensor concept, inspired by the human eye, which intends to allow future robots to better interact with their surroundings. The sensor is based on a time-of-flight laser scanning technology, where each range distance measurement is performed individually for increased quality. Micro-mirrors enable detailed control on where and when each sample point is acquired in the scene. By finding regions-of-interest (ROIs) and mainly concentrating the data acquisition here, the spatial resolution or frame rate of these ROIs can be significantly increased compared to a non-foveating system. Foveation is enabled through a real-time implementation of a feed-back control loop for the sensor hardware, based on vision algorithms for 3D scene analysis. In this paper, we describe and apply an algorithm for detecting ROIs based on motion detection in range data using background modeling. Heuristics are incorporated to cope with camera motion. We report first results applying this algorithm to scenes with moving objects, and show that the foveation capability allows the frame rate to be increased by up to 8.2 compared to a non-foveating sensor, utilizing up to 99% of the potential frame rate increase. The incorporated heuristics significantly improves the foveation’s performance for moving camera scenes.</description><fulltext>true</fulltext><rsrctype>book</rsrctype><creationdate>2011</creationdate><recordtype>book</recordtype><sourceid>3HK</sourceid><recordid>eNqNjDkOwjAQAN1QIOAPywMiYZuIGgUiitAECjprSRy0ktmNbCvv5xAPoJpiRjNXtz2cJZMw3DH5HlqPocj09FDL5PFrKuEcJUAjMsIgEVocqQfkTx78hJzBHqB5DyJcOmQmfizVbMCQ_OrHhVrXx2t1KrpIKRM7lohOa1NunNlaXZqd_ad5AZmLOAE</recordid><startdate>2011</startdate><enddate>2011</enddate><creator>Breivik, Gøril Margrethe</creator><creator>Thielemann, Jens T</creator><creator>Berge, Asbjørn</creator><creator>Skotheim, Øystein</creator><creator>Kirkhus, Trine</creator><scope>3HK</scope></search><sort><creationdate>2011</creationdate><title>A Motion based Real-time Foveation Control Loop for Rapid and Relevant 3D Laser Scanning</title><author>Breivik, Gøril Margrethe ; Thielemann, Jens T ; Berge, Asbjørn ; Skotheim, Øystein ; Kirkhus, Trine</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-cristin_nora_11250_24315273</frbrgroupid><rsrctype>books</rsrctype><prefilter>books</prefilter><language>eng</language><creationdate>2011</creationdate><toplevel>online_resources</toplevel><creatorcontrib>Breivik, Gøril Margrethe</creatorcontrib><creatorcontrib>Thielemann, Jens T</creatorcontrib><creatorcontrib>Berge, Asbjørn</creatorcontrib><creatorcontrib>Skotheim, Øystein</creatorcontrib><creatorcontrib>Kirkhus, Trine</creatorcontrib><collection>NORA - Norwegian Open Research Archives</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Breivik, Gøril Margrethe</au><au>Thielemann, Jens T</au><au>Berge, Asbjørn</au><au>Skotheim, Øystein</au><au>Kirkhus, Trine</au><format>book</format><genre>book</genre><ristype>BOOK</ristype><atitle>A Motion based Real-time Foveation Control Loop for Rapid and Relevant 3D Laser Scanning</atitle><btitle>IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2011</btitle><date>2011</date><risdate>2011</risdate><abstract>We present an implementation of a novel foveating 3D sensor concept, inspired by the human eye, which intends to allow future robots to better interact with their surroundings. The sensor is based on a time-of-flight laser scanning technology, where each range distance measurement is performed individually for increased quality. Micro-mirrors enable detailed control on where and when each sample point is acquired in the scene. By finding regions-of-interest (ROIs) and mainly concentrating the data acquisition here, the spatial resolution or frame rate of these ROIs can be significantly increased compared to a non-foveating system. Foveation is enabled through a real-time implementation of a feed-back control loop for the sensor hardware, based on vision algorithms for 3D scene analysis. In this paper, we describe and apply an algorithm for detecting ROIs based on motion detection in range data using background modeling. Heuristics are incorporated to cope with camera motion. We report first results applying this algorithm to scenes with moving objects, and show that the foveation capability allows the frame rate to be increased by up to 8.2 compared to a non-foveating sensor, utilizing up to 99% of the potential frame rate increase. The incorporated heuristics significantly improves the foveation’s performance for moving camera scenes.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2011, 2011
issn
language eng
recordid cdi_cristin_nora_11250_2431527
source NORA - Norwegian Open Research Archives
title A Motion based Real-time Foveation Control Loop for Rapid and Relevant 3D Laser Scanning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T15%3A21%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-cristin_3HK&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=book&rft.atitle=A%20Motion%20based%20Real-time%20Foveation%20Control%20Loop%20for%20Rapid%20and%20Relevant%203D%20Laser%20Scanning&rft.btitle=IEEE%20Computer%20Society%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshop%20(CVPRW),%202011&rft.au=Breivik,%20G%C3%B8ril%20Margrethe&rft.date=2011&rft_id=info:doi/&rft_dat=%3Ccristin_3HK%3E11250_2431527%3C/cristin_3HK%3E%3Cgrp_id%3Ecdi_FETCH-cristin_nora_11250_24315273%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true