Real-time Instance-Aware Segmentation and Semantic Mapping on Edge Devices

Perceiving the environment semantically in real-time is challenging for unmanned aerial vehicles (UAVs) with limited computational resources. In this paper, a real-time instance-aware segmentation and semantic mapping method on small edge devices is proposed. Taking RGB-D image as input, the present...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on instrumentation and measurement Ročník 72; s. 1
Hlavní autori: Lu, Junjie, Tian, Bailing, Shen, Hongming, Zhang, Xuewei
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.01.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:0018-9456, 1557-9662
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Perceiving the environment semantically in real-time is challenging for unmanned aerial vehicles (UAVs) with limited computational resources. In this paper, a real-time instance-aware segmentation and semantic mapping method on small edge devices is proposed. Taking RGB-D image as input, the presented instance segmentation pipeline is able to run at the speed of 38 FPS on AGX Xavier. To achieve this, we take a lightweight object detection model as backbone and reformulate the mask generation problem as threshold regression in depth by a novel designed truncation network. After that, a probability grid map is constructed to integrate the categories of voxels and object-level entities. Objects parameterized by pose, extent, category, and point cloud are tracked and fused across frames by data association. Finally, autonomous exploration experiments of UAV are conducted to demonstrate the effectiveness of the proposed method in both simulation and real-world.
AbstractList Perceiving the environment semantically in real-time is challenging for unmanned aerial vehicles (UAVs) with limited computational resources. In this paper, a real-time instance-aware segmentation and semantic mapping method on small edge devices is proposed. Taking RGB-D image as input, the presented instance segmentation pipeline is able to run at the speed of 38 FPS on AGX Xavier. To achieve this, we take a lightweight object detection model as backbone and reformulate the mask generation problem as threshold regression in depth by a novel designed truncation network. After that, a probability grid map is constructed to integrate the categories of voxels and object-level entities. Objects parameterized by pose, extent, category, and point cloud are tracked and fused across frames by data association. Finally, autonomous exploration experiments of UAV are conducted to demonstrate the effectiveness of the proposed method in both simulation and real-world.
Perceiving the environment semantically in real-time is challenging for unmanned aerial vehicles (UAVs) with limited computational resources. In this article, a real-time instance-aware segmentation and semantic mapping method on small edge devices is proposed. Taking red, green, blue, and the depth (RGB-D) image as input, the presented instance segmentation pipeline is able to run at the speed of 38 frames/s on AGX Xavier. To achieve this, we take a lightweight object detection model as the backbone and reformulate the mask generation problem as threshold regression in depth by a novel designed truncation network. After that, a probability grid map is constructed to integrate the categories of voxels and object-level entities. Objects parameterized by pose, extent, category, and point cloud are tracked and fused across frames by data association. Finally, autonomous exploration experiments of UAVs are conducted to demonstrate the effectiveness of the proposed method in both simulation and real-world.
Author Shen, Hongming
Lu, Junjie
Zhang, Xuewei
Tian, Bailing
Author_xml – sequence: 1
  givenname: Junjie
  orcidid: 0000-0002-0993-9765
  surname: Lu
  fullname: Lu, Junjie
  organization: School of Electrical and Information Egineering, Tianjin University, Tianjin, China
– sequence: 2
  givenname: Bailing
  orcidid: 0000-0003-1004-8350
  surname: Tian
  fullname: Tian, Bailing
  organization: School of Electrical and Information Egineering, Tianjin University, Tianjin, China
– sequence: 3
  givenname: Hongming
  orcidid: 0000-0003-0141-1904
  surname: Shen
  fullname: Shen, Hongming
  organization: School of Electrical and Information Egineering, Tianjin University, Tianjin, China
– sequence: 4
  givenname: Xuewei
  orcidid: 0000-0003-4512-1335
  surname: Zhang
  fullname: Zhang, Xuewei
  organization: School of Electrical and Information Egineering, Tianjin University, Tianjin, China
BookMark eNp9kE1LAzEQhoNUsK3eBS8Lnrcm2Xw0x1KrVloEreeQTWdLSjdbk1Tx37tliwcPngZe5pmXeQao5xsPCF0TPCIEq7vVfDmimNJRQSnjhJ6hPuFc5koI2kN9jMk4V4yLCzSIcYsxloLJPnp-BbPLk6shm_uYjLeQT75MgOwNNjX4ZJJrfGb8ug1q45Oz2dLs985vsjafrTeQ3cOnsxAv0XlldhGuTnOI3h9mq-lTvnh5nE8ni9xSSlJuAJdcCEt5aSvMpKCVwrYNlGBMMiO5LCyUtlSsYGNcGm6YLFlluQVi1rgYotvu7j40HweISW-bQ_BtpaZSCEG4lON2C3dbNjQxBqj0PrjahG9NsD4a060xfTSmT8ZaRPxBrOv-T8G43X_gTQc6APjtUUoUApPiB6dBeVU
CODEN IEIMAO
CitedBy_id crossref_primary_10_1109_TRO_2023_3273180
Cites_doi 10.1109/TIM.2019.2930158
10.1109/CVPR.2019.00086
10.15607/RSS.2014.X.007
10.1109/TRO.2017.2705103
10.1109/LRA.2019.2923960
10.1109/IROS40897.2019.8968199
10.1109/ICRA.2017.7989538
10.1109/IROS.2017.8206392
10.1109/TII.2020.2981367
10.1109/IROS.2018.8593993
10.1109/ICCV.2019.00925
10.1109/TIE.2019.2892698
10.1109/IROS45743.2020.9341176
10.1109/LRA.2021.3097242
10.1109/CVPR.2019.00455
10.1109/3DV.2018.00015
10.1109/ICRA.2017.7989518
10.1109/CVPR.2013.178
10.1109/CVPR.2018.00472
10.1109/LRA.2021.3051563
10.1109/CVPR.2017.50
10.1145/504729.504754
10.1109/TSMC.1979.4310076
10.1109/ISMAR.2018.00024
10.1109/ICCV.2017.322
10.1109/ICCV.2015.259
10.1109/ICCV48922.2021.00369
10.1109/ICRA40945.2020.9196885
10.1109/TIM.2018.2834085
10.1109/TRO.2018.2853729
10.1109/TIM.2021.3102739
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
7U5
8FD
L7M
DOI 10.1109/TIM.2022.3224512
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE/IET Electronic Library
CrossRef
Electronics & Communications Abstracts
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList
Solid State and Superconductivity Abstracts
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
EISSN 1557-9662
EndPage 1
ExternalDocumentID 10_1109_TIM_2022_3224512
9963601
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62273249; 62022060; 61903349; 62073234; 62003236
  funderid: 10.13039/501100001809
– fundername: Integration of Industry, Education and Research Innovation Fund of China University
  grantid: 2021ZYA08009
GroupedDBID -~X
0R~
29I
4.4
5GY
6IK
85S
97E
AAJGR
AASAJ
AAWTH
ABQJQ
ABVLG
ACGFO
ACIWK
ACNCT
AENEX
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TN5
TWZ
5VS
8WZ
A6W
AAYXX
AETIX
AGSQL
AI.
AIBXA
ALLEH
CITATION
EJD
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFJZH
VH1
VJK
7SP
7U5
8FD
AARMG
ABAZT
L7M
ID FETCH-LOGICAL-c221t-ae0b566c25bcf04762f90c66c964474a7573cebcb943480ba5a47b4fc5ce1ad03
IEDL.DBID RIE
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000922147200044&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-9456
IngestDate Mon Jun 30 10:14:06 EDT 2025
Sat Nov 29 04:38:29 EST 2025
Tue Nov 18 22:21:56 EST 2025
Tue Nov 25 14:44:28 EST 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c221t-ae0b566c25bcf04762f90c66c964474a7573cebcb943480ba5a47b4fc5ce1ad03
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-0993-9765
0000-0003-4512-1335
0000-0003-0141-1904
0000-0003-1004-8350
PQID 2766615778
PQPubID 85462
PageCount 1
ParticipantIDs crossref_primary_10_1109_TIM_2022_3224512
crossref_citationtrail_10_1109_TIM_2022_3224512
ieee_primary_9963601
proquest_journals_2766615778
PublicationCentury 2000
PublicationDate 2023-01-01
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – month: 01
  year: 2023
  text: 2023-01-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on instrumentation and measurement
PublicationTitleAbbrev TIM
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref34
ref14
Redmon (ref15) 2018
ref31
Qi (ref27); 30
ref30
ref11
ref33
ref10
ref32
ref2
ref1
ref17
ref16
ref19
ref18
ref24
ref23
ref26
ref25
ref20
ref21
ref28
ref29
ref8
ref7
ref9
ref4
ref3
ref6
ref5
Wang (ref22); 33
References_xml – ident: ref21
  doi: 10.1109/TIM.2019.2930158
– ident: ref25
  doi: 10.1109/CVPR.2019.00086
– ident: ref1
  doi: 10.15607/RSS.2014.X.007
– ident: ref4
  doi: 10.1109/TRO.2017.2705103
– year: 2018
  ident: ref15
  article-title: YOLOv3: An incremental improvement
  publication-title: arXiv:1804.02767
– ident: ref10
  doi: 10.1109/LRA.2019.2923960
– ident: ref5
  doi: 10.1109/IROS40897.2019.8968199
– ident: ref7
  doi: 10.1109/ICRA.2017.7989538
– ident: ref11
  doi: 10.1109/IROS.2017.8206392
– ident: ref30
  doi: 10.1109/TII.2020.2981367
– ident: ref8
  doi: 10.1109/IROS.2018.8593993
– ident: ref23
  doi: 10.1109/ICCV.2019.00925
– ident: ref29
  doi: 10.1109/TIE.2019.2892698
– ident: ref2
  doi: 10.1109/IROS45743.2020.9341176
– ident: ref34
  doi: 10.1109/LRA.2021.3097242
– ident: ref17
  doi: 10.1109/CVPR.2019.00455
– ident: ref33
  doi: 10.1109/3DV.2018.00015
– ident: ref12
  doi: 10.1109/ICRA.2017.7989518
– volume: 33
  start-page: 17721
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref22
  article-title: SOLOv2: Dynamic and fast instance segmentation
– ident: ref20
  doi: 10.1109/CVPR.2013.178
– ident: ref24
  doi: 10.1109/CVPR.2018.00472
– ident: ref6
  doi: 10.1109/LRA.2021.3051563
– ident: ref26
  doi: 10.1109/CVPR.2017.50
– ident: ref32
  doi: 10.1145/504729.504754
– ident: ref31
  doi: 10.1109/TSMC.1979.4310076
– ident: ref13
  doi: 10.1109/ISMAR.2018.00024
– ident: ref14
  doi: 10.1109/ICCV.2017.322
– ident: ref16
  doi: 10.1109/ICCV.2015.259
– ident: ref18
  doi: 10.1109/ICCV48922.2021.00369
– ident: ref9
  doi: 10.1109/ICRA40945.2020.9196885
– ident: ref19
  doi: 10.1109/TIM.2018.2834085
– volume: 30
  start-page: 1
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref27
  article-title: PointNet: Deep hierarchical feature learning on point sets in a metric space
– ident: ref3
  doi: 10.1109/TRO.2018.2853729
– ident: ref28
  doi: 10.1109/TIM.2021.3102739
SSID ssj0007647
Score 2.3874478
Snippet Perceiving the environment semantically in real-time is challenging for unmanned aerial vehicles (UAVs) with limited computational resources. In this paper, a...
Perceiving the environment semantically in real-time is challenging for unmanned aerial vehicles (UAVs) with limited computational resources. In this article,...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms autonomous exploration
Feature extraction
Image edge detection
Image segmentation
instance segmentation
Mapping
Object recognition
Real time
Real-time systems
Semantic mapping
Semantics
Simultaneous localization and mapping
Statistical analysis
Three-dimensional displays
Unmanned aerial vehicles
Title Real-time Instance-Aware Segmentation and Semantic Mapping on Edge Devices
URI https://ieeexplore.ieee.org/document/9963601
https://www.proquest.com/docview/2766615778
Volume 72
WOSCitedRecordID wos000922147200044&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE/IET Electronic Library (IEL) (UW System Shared)
  customDbUrl:
  eissn: 1557-9662
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0007647
  issn: 0018-9456
  databaseCode: RIE
  dateStart: 19630101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dbxMxDLe2CaTtgUG7aYWB7mEvSKS9pMnl8jhBK4rWCUGZ9nZKcm5Vab2ifsC_j5O7VqAhJN5OVqKc7MT-OY5tgCvu8lIbnjNLA5h0qmQGM8Ukt6l12igRs_jvbvTtbX5_bz4fwLt9Lgwixsdn2A2fMZZfLv02XJX1CJv3s5Csdah1Vudq7bWuzmRdH5PWNYQKdiHJ1PQmozE5gkJ0afNKxcUfJij2VHmkiKN1GZ7-3389h2cNikyua7G_gAOsWnDyW23BFjyNbzv9ug2fvhAYZKGJfDKKYNAju_5pV5h8xdmiyT2qEluVRFgQp-c-GdtQt2GWEH1QzjD5gFGjnMG34WDy_iNrWigwLwTfMIupI8DmhXJ-mkrSfFOTeiIYwkFaWq1036PzLpSJy1NnlZXayalXHrkt0_45HFXLCi8gEaXmSB4bISwuNYYAKi1RkhWcosr6ogO9HVcL39QXD20uHoroZ6SmIDkUQQ5FI4cOvN3P-F7X1vjH2Hbg-35cw_IOXO4EVzSHb10ITT4ZV1rnL_8-6xUch67x9U3KJRxtVlt8DU_8j818vXoT99Uvu3nH8w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dTxsxDLcQ2wQ87IMPUT62e9jLJEKTNGkuj2gD0a2tpq0g3k5Jzq2Q4EBt2f79OblrtWkIibeTlSgnO7F_jmMb4KPweWmsyJmjAUx5XTKLXc2UcNx5Y7VMWfyXfTMc5ldX9vsKHC1zYRAxPT7D4_iZYvnlXXiIV2VtwuadbkzWeqGVkrzO1lrqXdNVdYVMWtkSLlgEJbltj3oDcgWlPKbtq7SQ_xih1FXlP1Wc7MvZm-f92Vt43eDI7KQW_DtYwWoTNv6qLrgJr9LrzjDbgq8_CA6y2EY-6yU4GJCd_HZTzH7i5LbJPqoyV5VEuCVeX4ds4GLlhklG9NNygtkXTDplGy7OTkefz1nTRIEFKcWcOeSeIFuQ2ocxV6T7xpYHIlhCQkY5o00noA8-ForLuXfaKePVOOiAwpW8swOr1V2Fu5DJ0ggkn40wllAGYwiVlijJDo5RdzuyBe0FV4vQVBiPjS5uiuRpcFuQHIooh6KRQws-LWfc19U1nhi7Ffm-HNewvAUHC8EVzfGbFdKQVya0Mfne47M-wNr5aNAv-r3ht31Yjz3k63uVA1idTx_wEF6GX_Pr2fR92mN_AE_4yzo
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Real-Time+Instance-Aware+Segmentation+and+Semantic+Mapping+on+Edge+Devices&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Lu%2C+Junjie&rft.au=Tian%2C+Bailing&rft.au=Shen%2C+Hongming&rft.au=Zhang%2C+Xuewei&rft.date=2023-01-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9456&rft.eissn=1557-9662&rft.volume=72&rft.spage=1&rft_id=info:doi/10.1109%2FTIM.2022.3224512&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9456&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9456&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9456&client=summon