Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction

We present an unsupervised deep neural network approach to the fusion of RGB-D imagery with inertial measurements for absolute trajectory estimation. Our network, dubbed the Visual-Inertial-Odometry Learner (VIOLearner), learns to perform visual-inertial odometry (VIO) without inertial measurement u...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-03
Main Authors: Shamwell, E Jared, Leung, Sarah, Nothwang, William D
Format: Article
Language:English
Subjects:
Accelerometers
Error correction
Imagery
Inertial platforms
Jacobians
Neural networks
Odometers
Simultaneous localization and mapping
Trajectory analysis
Trajectory measurement
White noise
Online Access:Get 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 arXiv.org
container_volume
creator Shamwell, E Jared
Leung, Sarah
Nothwang, William D
description We present an unsupervised deep neural network approach to the fusion of RGB-D imagery with inertial measurements for absolute trajectory estimation. Our network, dubbed the Visual-Inertial-Odometry Learner (VIOLearner), learns to perform visual-inertial odometry (VIO) without inertial measurement unit (IMU) intrinsic parameters (corresponding to gyroscope and accelerometer bias or white noise) or the extrinsic calibration between an IMU and camera. The network learns to integrate IMU measurements and generate hypothesis trajectories which are then corrected online according to the Jacobians of scaled image projection errors with respect to a spatial grid of pixel coordinates. We evaluate our network against state-of-the-art (SOA) visual-inertial odometry, visual odometry, and visual simultaneous localization and mapping (VSLAM) approaches on the KITTI Odometry dataset and demonstrate competitive odometry performance.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2071782860</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2071782860</sourcerecordid><originalsourceid>FETCH-proquest_journals_20717828603</originalsourceid><addsrcrecordid>eNqNjMEKwjAQRIMgWLT_sOC5kKba9ipa8aQX9Vqqrpq2JnU3Vfx7c_ADPM3AvDcDEagkiaN8ptRIhMy1lFKlmZrPk0A0R83ammihL3iBxYlt2zuEPVU1np2lDxTs9KNyHoIDa3ODyhfDfYf00uylFWIHW3RvSw28tbvDzrTaIBRElmBpifyV9ydieK1axvCXYzFdF_vlJurIPntkV9a2J-OnUsksznKVpzL5j_oCcSxJTg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2071782860</pqid></control><display><type>article</type><title>Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction</title><source>Publicly Available Content Database</source><creator>Shamwell, E Jared ; Leung, Sarah ; Nothwang, William D</creator><creatorcontrib>Shamwell, E Jared ; Leung, Sarah ; Nothwang, William D</creatorcontrib><description>We present an unsupervised deep neural network approach to the fusion of RGB-D imagery with inertial measurements for absolute trajectory estimation. Our network, dubbed the Visual-Inertial-Odometry Learner (VIOLearner), learns to perform visual-inertial odometry (VIO) without inertial measurement unit (IMU) intrinsic parameters (corresponding to gyroscope and accelerometer bias or white noise) or the extrinsic calibration between an IMU and camera. The network learns to integrate IMU measurements and generate hypothesis trajectories which are then corrected online according to the Jacobians of scaled image projection errors with respect to a spatial grid of pixel coordinates. We evaluate our network against state-of-the-art (SOA) visual-inertial odometry, visual odometry, and visual simultaneous localization and mapping (VSLAM) approaches on the KITTI Odometry dataset and demonstrate competitive odometry performance.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Accelerometers ; Error correction ; Imagery ; Inertial platforms ; Jacobians ; Neural networks ; Odometers ; Simultaneous localization and mapping ; Trajectory analysis ; Trajectory measurement ; White noise</subject><ispartof>arXiv.org, 2018-03</ispartof><rights>2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2071782860?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>777,781,25734,36993,44571</link.rule.ids></links><search><creatorcontrib>Shamwell, E Jared</creatorcontrib><creatorcontrib>Leung, Sarah</creatorcontrib><creatorcontrib>Nothwang, William D</creatorcontrib><title>Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction</title><title>arXiv.org</title><description>We present an unsupervised deep neural network approach to the fusion of RGB-D imagery with inertial measurements for absolute trajectory estimation. Our network, dubbed the Visual-Inertial-Odometry Learner (VIOLearner), learns to perform visual-inertial odometry (VIO) without inertial measurement unit (IMU) intrinsic parameters (corresponding to gyroscope and accelerometer bias or white noise) or the extrinsic calibration between an IMU and camera. The network learns to integrate IMU measurements and generate hypothesis trajectories which are then corrected online according to the Jacobians of scaled image projection errors with respect to a spatial grid of pixel coordinates. We evaluate our network against state-of-the-art (SOA) visual-inertial odometry, visual odometry, and visual simultaneous localization and mapping (VSLAM) approaches on the KITTI Odometry dataset and demonstrate competitive odometry performance.</description><subject>Accelerometers</subject><subject>Error correction</subject><subject>Imagery</subject><subject>Inertial platforms</subject><subject>Jacobians</subject><subject>Neural networks</subject><subject>Odometers</subject><subject>Simultaneous localization and mapping</subject><subject>Trajectory analysis</subject><subject>Trajectory measurement</subject><subject>White noise</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjMEKwjAQRIMgWLT_sOC5kKba9ipa8aQX9Vqqrpq2JnU3Vfx7c_ADPM3AvDcDEagkiaN8ptRIhMy1lFKlmZrPk0A0R83ammihL3iBxYlt2zuEPVU1np2lDxTs9KNyHoIDa3ODyhfDfYf00uylFWIHW3RvSw28tbvDzrTaIBRElmBpifyV9ydieK1axvCXYzFdF_vlJurIPntkV9a2J-OnUsksznKVpzL5j_oCcSxJTg</recordid><startdate>20180308</startdate><enddate>20180308</enddate><creator>Shamwell, E Jared</creator><creator>Leung, Sarah</creator><creator>Nothwang, William D</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20180308</creationdate><title>Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction</title><author>Shamwell, E Jared ; Leung, Sarah ; Nothwang, William D</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20717828603</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Accelerometers</topic><topic>Error correction</topic><topic>Imagery</topic><topic>Inertial platforms</topic><topic>Jacobians</topic><topic>Neural networks</topic><topic>Odometers</topic><topic>Simultaneous localization and mapping</topic><topic>Trajectory analysis</topic><topic>Trajectory measurement</topic><topic>White noise</topic><toplevel>online_resources</toplevel><creatorcontrib>Shamwell, E Jared</creatorcontrib><creatorcontrib>Leung, Sarah</creatorcontrib><creatorcontrib>Nothwang, William D</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shamwell, E Jared</au><au>Leung, Sarah</au><au>Nothwang, William D</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction</atitle><jtitle>arXiv.org</jtitle><date>2018-03-08</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>We present an unsupervised deep neural network approach to the fusion of RGB-D imagery with inertial measurements for absolute trajectory estimation. Our network, dubbed the Visual-Inertial-Odometry Learner (VIOLearner), learns to perform visual-inertial odometry (VIO) without inertial measurement unit (IMU) intrinsic parameters (corresponding to gyroscope and accelerometer bias or white noise) or the extrinsic calibration between an IMU and camera. The network learns to integrate IMU measurements and generate hypothesis trajectories which are then corrected online according to the Jacobians of scaled image projection errors with respect to a spatial grid of pixel coordinates. We evaluate our network against state-of-the-art (SOA) visual-inertial odometry, visual odometry, and visual simultaneous localization and mapping (VSLAM) approaches on the KITTI Odometry dataset and demonstrate competitive odometry performance.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2018-03
issn 2331-8422
language eng
recordid cdi_proquest_journals_2071782860
source Publicly Available Content Database
subjects Accelerometers
Error correction
Imagery
Inertial platforms
Jacobians
Neural networks
Odometers
Simultaneous localization and mapping
Trajectory analysis
Trajectory measurement
White noise
title Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T14%3A06%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Vision-Aided%20Absolute%20Trajectory%20Estimation%20Using%20an%20Unsupervised%20Deep%20Network%20with%20Online%20Error%20Correction&rft.jtitle=arXiv.org&rft.au=Shamwell,%20E%20Jared&rft.date=2018-03-08&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2071782860%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20717828603%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2071782860&rft_id=info:pmid/&rfr_iscdi=true