Recognition of surrounding environment from electric wheelchair videos based on modified YOLOv2

Currently, the aging population is growing in Japan, and the needs for the utilization of welfare equipment are consequently increasing. The electric wheelchair, which is a convenient transportation tool, has rapidly become popular. However, many accidents have occurred when using electric wheelchai...

Full description

Saved in:
Bibliographic Details
Published in:Future generation computer systems Vol. 92; pp. 157 - 161
Main Authors: Sakai, Yuki, Lu, Huimin, Tan, Joo-Kooi, Kim, Hyoungseop
Format: Journal Article
Language:English
Published: Elsevier B.V 01.03.2019
Subjects:
ISSN:0167-739X, 1872-7115
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Currently, the aging population is growing in Japan, and the needs for the utilization of welfare equipment are consequently increasing. The electric wheelchair, which is a convenient transportation tool, has rapidly become popular. However, many accidents have occurred when using electric wheelchairs, and the dangers of driving have been noted. Therefore, there is a need to improve accident factors, reduce accidents and improve the convenience of electric wheelchairs by using automation. Environmental recognition is the key technology for developing autonomous electric wheelchairs. Environmental recognition includes self-position estimation, the recognition of sidewalks, crosswalks and traffic lights, and moving object predictions. To solve these problems, this paper develops a system for detecting sidewalks, crosswalks and traffic lights. We develop the object recognition methods using a modified YOLOv2, which is an object detection algorithm that applies convolutional neural networks (CNNs). We detect the object through YOLOv2 and perform processing steps, such as unnecessary bounding box deletion and interpolation. The experimental results demonstrate that the average AUC of the detection rate is 0.587. •We develop a system for detecting sidewalks, crosswalks and traffic lights.•We develop the object recognition methods using a modified YOLOv2.•We detect the object use bounding box deletion and interpolation.
AbstractList Currently, the aging population is growing in Japan, and the needs for the utilization of welfare equipment are consequently increasing. The electric wheelchair, which is a convenient transportation tool, has rapidly become popular. However, many accidents have occurred when using electric wheelchairs, and the dangers of driving have been noted. Therefore, there is a need to improve accident factors, reduce accidents and improve the convenience of electric wheelchairs by using automation. Environmental recognition is the key technology for developing autonomous electric wheelchairs. Environmental recognition includes self-position estimation, the recognition of sidewalks, crosswalks and traffic lights, and moving object predictions. To solve these problems, this paper develops a system for detecting sidewalks, crosswalks and traffic lights. We develop the object recognition methods using a modified YOLOv2, which is an object detection algorithm that applies convolutional neural networks (CNNs). We detect the object through YOLOv2 and perform processing steps, such as unnecessary bounding box deletion and interpolation. The experimental results demonstrate that the average AUC of the detection rate is 0.587. •We develop a system for detecting sidewalks, crosswalks and traffic lights.•We develop the object recognition methods using a modified YOLOv2.•We detect the object use bounding box deletion and interpolation.
Author Tan, Joo-Kooi
Kim, Hyoungseop
Sakai, Yuki
Lu, Huimin
Author_xml – sequence: 1
  givenname: Yuki
  surname: Sakai
  fullname: Sakai, Yuki
– sequence: 2
  givenname: Huimin
  orcidid: 0000-0001-9794-3221
  surname: Lu
  fullname: Lu, Huimin
  email: dr.huimin.lu@ieee.org
– sequence: 3
  givenname: Joo-Kooi
  surname: Tan
  fullname: Tan, Joo-Kooi
– sequence: 4
  givenname: Hyoungseop
  surname: Kim
  fullname: Kim, Hyoungseop
  email: kimhs@cntl.kyutech.ac.jp
BookMark eNqFkM1KAzEUhYNUsK2-gYu8wIzJZKbJuBCk-AeFgijoKmSSmzZlJpFkOuLbO6WuXOjqnsX9DpxvhiY-eEDokpKcErq42uV23-8j5AWhIid1ThbiBE2p4EXGKa0maDq-8Yyz-u0MzVLaEUIoZ3SK5DPosPGud8HjYHHaxxj23ji_weAHF4PvwPfYxtBhaEH30Wn8uQVo9Va5iAdnICTcqAQGjx1dMM66Mb-vV-uhOEenVrUJLn7uHL3e370sH7PV-uFpebvKNONFn9WmpIyUQtXCKGYKW6lKWVJQxsAWJTRC6IpX1biP1Q1XJa9qY4QmVWOFFpbN0fWxV8eQUgQrtevVYVUflWslJfKgSu7kUZU8qJKklqOqES5_wR_RdSp-_YfdHDEYhw0OokzagddgXBxFSRPc3wXf_0SKAw
CitedBy_id crossref_primary_10_1002_cpe_5430
crossref_primary_10_1007_s11760_023_02553_8
crossref_primary_10_1109_ACCESS_2019_2901008
crossref_primary_10_1016_j_compeleceng_2020_106765
crossref_primary_10_1109_TVT_2019_2936792
crossref_primary_10_1007_s11042_023_16736_5
crossref_primary_10_1016_j_asoc_2020_106528
crossref_primary_10_1109_ACCESS_2018_2889030
crossref_primary_10_1109_ACCESS_2020_2994947
crossref_primary_10_3390_wevj13020023
crossref_primary_10_1016_j_compeleceng_2021_106983
crossref_primary_10_1016_j_aei_2023_101988
crossref_primary_10_3390_mti8120108
crossref_primary_10_1007_s00521_019_04086_z
crossref_primary_10_1007_s10489_020_02116_1
crossref_primary_10_1007_s11042_021_11016_6
crossref_primary_10_1007_s12652_020_02066_z
crossref_primary_10_1007_s11042_019_7216_1
crossref_primary_10_1155_2020_8891393
crossref_primary_10_7467_KSAE_2024_32_2_167
crossref_primary_10_1155_2020_8848553
crossref_primary_10_3390_app122110871
crossref_primary_10_1007_s12652_020_02170_0
crossref_primary_10_1007_s11276_019_02199_w
Cites_doi 10.1109/ICMLA.2016.0144
10.1007/978-3-319-46448-0_2
10.1016/j.patcog.2017.11.007
10.1109/CVPR.2014.81
10.1109/TIP.2015.2427518
10.1007/978-3-662-45286-8_43
10.1109/CVPR.2017.690
ContentType Journal Article
Copyright 2018 Elsevier B.V.
Copyright_xml – notice: 2018 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.future.2018.09.068
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-7115
EndPage 161
ExternalDocumentID 10_1016_j_future_2018_09_068
S0167739X18315887
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
29H
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABFNM
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
AEBSH
AEKER
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
IHE
J1W
KOM
LG9
M41
MO0
MS~
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
PC.
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SES
SEW
SPC
SPCBC
SSV
SSZ
T5K
UHS
WUQ
XPP
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ADNMO
AEIPS
AFJKZ
AGQPQ
AIIUN
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c372t-9d413048a98da3d2f5a5af02133ef24eb88c575501839b7a4759dd8c05bf8c8f3
ISICitedReferencesCount 30
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000454370600014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-739X
IngestDate Tue Nov 18 22:35:04 EST 2025
Sat Nov 29 07:24:37 EST 2025
Fri Feb 23 02:43:56 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords YOLOv2
Autonomous wheelchair
Convolutional neural network
Object detection
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c372t-9d413048a98da3d2f5a5af02133ef24eb88c575501839b7a4759dd8c05bf8c8f3
ORCID 0000-0001-9794-3221
PageCount 5
ParticipantIDs crossref_citationtrail_10_1016_j_future_2018_09_068
crossref_primary_10_1016_j_future_2018_09_068
elsevier_sciencedirect_doi_10_1016_j_future_2018_09_068
PublicationCentury 2000
PublicationDate March 2019
2019-03-00
PublicationDateYYYYMMDD 2019-03-01
PublicationDate_xml – month: 03
  year: 2019
  text: March 2019
PublicationDecade 2010
PublicationTitle Future generation computer systems
PublicationYear 2019
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References (2018/2/2access) (in Japanese).
F. Ran, et al. Vision-based lane detection algorithm in urban traffic scenes, in: International Conference on Life System Modeling and Simulation and International Conference on Intelligent Computing for Sustainable Energy and Environment, 2014, pp. 409-419.
(2018/1/9 access) (in Japanese).
Y. Alkhorsid, et al. Road detection through supervised classification, in: IEEE International Conference on Machine Learning and Applications, 2016, pp. 806–809.
Wang, Lu, Xiao (b4) 2015; 24
W. Liu, et al. SSD: single shot multibox detector, in: European Conference on Computer Vision, 2015, pp. 21–37.
Bharat Singh, et al. R-FCN-3000 at 30fps: Decoupling detection and classification, arXiv preprint
Li, Wang, Wang (b3) 2018; 76
Ministry of Internal Affairs and Communications, Toukei Kara Mita Wagakunino Koreisha (The elderly in our country viewed from statistics)
Electric wheelchair safety dissemination association, Shukka Disu No Suii (Trends in shipments)
J. Redmon, et al. YOLO9000: Better, Faster, Stronger, in: IEEE Conference on Computer Vision and Patern Recognition, 2017, pp. 7263–7271.
R. Girshick, et al. Rich feature hierarchies for accurate object detection and semantic segmentation, in: IEEE Conference on Computer Vision and Patern Recognition, 2014, pp. 580–587.
2016.
10.1016/j.future.2018.09.068_b8
10.1016/j.future.2018.09.068_b9
10.1016/j.future.2018.09.068_b6
10.1016/j.future.2018.09.068_b7
Li (10.1016/j.future.2018.09.068_b3) 2018; 76
10.1016/j.future.2018.09.068_b1
Wang (10.1016/j.future.2018.09.068_b4) 2015; 24
10.1016/j.future.2018.09.068_b10
10.1016/j.future.2018.09.068_b5
10.1016/j.future.2018.09.068_b2
References_xml – reference: (2018/2/2access) (in Japanese).
– reference: (2018/1/9 access) (in Japanese).
– reference: Ministry of Internal Affairs and Communications, Toukei Kara Mita Wagakunino Koreisha (The elderly in our country viewed from statistics),
– volume: 76
  start-page: 323
  year: 2018
  end-page: 338
  ident: b3
  article-title: Deep visual tracking: Review and experimental comparison
  publication-title: Pattern Recognit.
– reference: Y. Alkhorsid, et al. Road detection through supervised classification, in: IEEE International Conference on Machine Learning and Applications, 2016, pp. 806–809.
– reference: W. Liu, et al. SSD: single shot multibox detector, in: European Conference on Computer Vision, 2015, pp. 21–37.
– reference: Bharat Singh, et al. R-FCN-3000 at 30fps: Decoupling detection and classification, arXiv preprint
– reference: Electric wheelchair safety dissemination association, Shukka Disu No Suii (Trends in shipments),
– reference: J. Redmon, et al. YOLO9000: Better, Faster, Stronger, in: IEEE Conference on Computer Vision and Patern Recognition, 2017, pp. 7263–7271.
– volume: 24
  start-page: 2646
  year: 2015
  end-page: 2657
  ident: b4
  article-title: Inverse sparse tracker with a locally weighted distance metric
  publication-title: IEEE Trans. Image Process.
– reference: , 2016.
– reference: F. Ran, et al. Vision-based lane detection algorithm in urban traffic scenes, in: International Conference on Life System Modeling and Simulation and International Conference on Intelligent Computing for Sustainable Energy and Environment, 2014, pp. 409-419.
– reference: R. Girshick, et al. Rich feature hierarchies for accurate object detection and semantic segmentation, in: IEEE Conference on Computer Vision and Patern Recognition, 2014, pp. 580–587.
– ident: 10.1016/j.future.2018.09.068_b5
  doi: 10.1109/ICMLA.2016.0144
– ident: 10.1016/j.future.2018.09.068_b10
– ident: 10.1016/j.future.2018.09.068_b2
– ident: 10.1016/j.future.2018.09.068_b9
  doi: 10.1007/978-3-319-46448-0_2
– ident: 10.1016/j.future.2018.09.068_b1
– volume: 76
  start-page: 323
  year: 2018
  ident: 10.1016/j.future.2018.09.068_b3
  article-title: Deep visual tracking: Review and experimental comparison
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2017.11.007
– ident: 10.1016/j.future.2018.09.068_b8
  doi: 10.1109/CVPR.2014.81
– volume: 24
  start-page: 2646
  issue: 9
  year: 2015
  ident: 10.1016/j.future.2018.09.068_b4
  article-title: Inverse sparse tracker with a locally weighted distance metric
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2015.2427518
– ident: 10.1016/j.future.2018.09.068_b6
  doi: 10.1007/978-3-662-45286-8_43
– ident: 10.1016/j.future.2018.09.068_b7
  doi: 10.1109/CVPR.2017.690
SSID ssj0001731
Score 2.3950777
Snippet Currently, the aging population is growing in Japan, and the needs for the utilization of welfare equipment are consequently increasing. The electric...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 157
SubjectTerms Autonomous wheelchair
Convolutional neural network
Object detection
YOLOv2
Title Recognition of surrounding environment from electric wheelchair videos based on modified YOLOv2
URI https://dx.doi.org/10.1016/j.future.2018.09.068
Volume 92
WOSCitedRecordID wos000454370600014&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-7115
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001731
  issn: 0167-739X
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JbtswECVcp4deuhdNN_DQm6FCEimTOgZFgnRBUjQp4JwEiguixJUM2XKSL-nvliNSslAX3YBeBEOQZILzNDMccd5D6DUznHKaJIExmtgFiqaBACZMPuVTIkxoF0WqFZtgR0d8Nks_jUbful6Y9ZyVJb--Thf_1dT2nDU2tM7-hbn7h9oT9rc1uj1as9vjHxn-c7clyGWCy6auQToJSgKDrjbXV-JEcAo5uTrXei7PRVFPoDGvWk4gvCn4lPC1UoWBRPXs-OPxOh5mswctIQmoMGsPJOlFIjxDdJ-wn4hLp3t91lwW_Sagpg18DQiLbSoIrlmkqoIPVdVf6kWfD2_AOS11tRhWK6BBigyrFdttNK6qab01I62mrg1KzhNzZlP_yPV6dq7ayeZ5Xxs5ZmsftiPH6b4VEVxx4uKNo2iBvXy8JbZ1Yj4_cG2fwEhgINbRRYn1v7fQTsySlI_Rzt67_dn7PshHzEtd-pF3XZnt1sHt__p51jPIZE7vo7t-CYL3HHQeoJEuH6J7nbwH9t7-EcoGSMKVwQMk4QGSMCAJd0jCGyRhhyTcIgnbZ3RIwg5Jj9GXg_3Tt4eB1-MIJGHxKkgVZDyUi5QrQVRsEpHY1zmOCNEmpjrnXNrsHygiSZozAVSSSnEZJrnhkhvyBI3LqtRPEY6VyVWeKx5qSZUS8LE4oSI0hlKqo-kuIt18ZdKT1YNmyjzrdiVeZG6WM5jlLEwzO8u7KOjvWjiylt9czzpTZD7hdIlkZtHzyzuf_fOdz9GdzXvxAo1XdaNfottyvSqW9SsPs-_hcKxP
linkProvider Elsevier
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=Recognition+of+surrounding+environment+from+electric+wheelchair+videos+based+on+modified+YOLOv2&rft.jtitle=Future+generation+computer+systems&rft.au=Sakai%2C+Yuki&rft.au=Lu%2C+Huimin&rft.au=Tan%2C+Joo-Kooi&rft.au=Kim%2C+Hyoungseop&rft.date=2019-03-01&rft.pub=Elsevier+B.V&rft.issn=0167-739X&rft.eissn=1872-7115&rft.volume=92&rft.spage=157&rft.epage=161&rft_id=info:doi/10.1016%2Fj.future.2018.09.068&rft.externalDocID=S0167739X18315887
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-739X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-739X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-739X&client=summon