Obstacle Detection for Intelligent Transportation Systems Using Deep Stacked Autoencoder and k -Nearest Neighbor Scheme

Obstacle detection is an essential element for the development of intelligent transportation systems so that accidents can be avoided. In this paper, we propose a stereovision-based method for detecting obstacles in urban environment. The proposed method uses a deep stacked auto-encoders (DSA) model...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE sensors journal Vol. 18; no. 12; pp. 5122 - 5132
Main Authors:	Dairi, Abdelkader, Harrou, Fouzi, Ying Sun, Senouci, Mohamed
Format:	Journal Article
Language:	English
Published:	IEEE 15.06.2018
Subjects:	autonomous vehicles Clustering algorithms deep learning intelligent transportation systems Kernel Machine learning Machine learning algorithms Obstacle detection Partitioning algorithms Roads Sensors
ISSN:	1530-437X, 1558-1748
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Obstacle detection is an essential element for the development of intelligent transportation systems so that accidents can be avoided. In this paper, we propose a stereovision-based method for detecting obstacles in urban environment. The proposed method uses a deep stacked auto-encoders (DSA) model that combines the greedy learning features with the dimensionality reduction capacity and employs an unsupervised k -nearest neighbors (KNN) algorithm to accurately and reliably detect the presence of obstacles. We consider obstacle detection as an anomaly detection problem. We evaluated the proposed method by using practical data from three publicly available data sets, the Malaga stereovision urban data set, the Daimler urban segmentation data set, and the Bahnhof data set. Also, we compared the efficiency of DSA-KNN approach to the deep belief network-based clustering schemes. Results show that the DSA-KNN is suitable to visually monitor urban scenes.
AbstractList	Obstacle detection is an essential element for the development of intelligent transportation systems so that accidents can be avoided. In this paper, we propose a stereovision-based method for detecting obstacles in urban environment. The proposed method uses a deep stacked auto-encoders (DSA) model that combines the greedy learning features with the dimensionality reduction capacity and employs an unsupervised k -nearest neighbors (KNN) algorithm to accurately and reliably detect the presence of obstacles. We consider obstacle detection as an anomaly detection problem. We evaluated the proposed method by using practical data from three publicly available data sets, the Malaga stereovision urban data set, the Daimler urban segmentation data set, and the Bahnhof data set. Also, we compared the efficiency of DSA-KNN approach to the deep belief network-based clustering schemes. Results show that the DSA-KNN is suitable to visually monitor urban scenes.
Author	Ying Sun Dairi, Abdelkader Senouci, Mohamed Harrou, Fouzi
Author_xml	– sequence: 1 givenname: Abdelkader surname: Dairi fullname: Dairi, Abdelkader email: dairi.aek@gmail.com organization: Comput. Sci. Dept., Univ. of Oran 1 Ahmed Ben Bella, Oran, Algeria – sequence: 2 givenname: Fouzi surname: Harrou fullname: Harrou, Fouzi email: fouzi.harrou@kaust.edu.sa organization: Electr. & Math. Sci. & Eng. Div., King Abdullah Univ. of Sci. & Technol., Thuwal, Saudi Arabia – sequence: 3 surname: Ying Sun fullname: Ying Sun organization: Electr. & Math. Sci. & Eng. Div., King Abdullah Univ. of Sci. & Technol., Thuwal, Saudi Arabia – sequence: 4 givenname: Mohamed surname: Senouci fullname: Senouci, Mohamed organization: Comput. Sci. Dept., Univ. of Oran 1 Ahmed Ben Bella, Oran, Algeria
BookMark	eNp9kNFOwjAUhhuDiYA-gPGmLzBs13UtlwRRMQQuBol3S9edQWV0pK0xvL2bEC-88Or8ycn3n5xvgHq2sYDQPSUjSsn48S2bLUcxoXIUS0aJjK9Qn3IuIyoS2esyI1HCxPsNGnj_QQgdCy766GtV-KB0DfgJAuhgGourxuG5DVDXZgs24LVT1h8bF9TPOjv5AAePN97YbYvBEWdtxR5KPPkMDVjdlOCwsiXe42gJyoEPeAlmuyva5kzv4AC36LpStYe7yxyizfNsPX2NFquX-XSyiHSc8hAppnkFZUVYmYCiXKZac17ohKg0FYpTXspYjTWNgVMiGCNlpVMYJ1IIXWjJhoiee7VrvHdQ5UdnDsqdckryzlzemcs7c_nFXMuIP4w259-DU6b-l3w4kwYAfi9JxmNJKPsGd-WAAw
CODEN	ISJEAZ
CitedBy_id	crossref_primary_10_1109_TITS_2021_3090338 crossref_primary_10_1016_j_knosys_2024_112679 crossref_primary_10_1007_s10479_023_05418_y crossref_primary_10_1109_ACCESS_2024_3424488 crossref_primary_10_1109_JSEN_2021_3118365 crossref_primary_10_1109_TGRS_2020_2984951 crossref_primary_10_1080_1206212X_2020_1758877 crossref_primary_10_3390_app10238400 crossref_primary_10_1016_j_jestch_2023_101455 crossref_primary_10_1016_j_jksuci_2021_07_020 crossref_primary_10_1080_01969722_2025_2520823 crossref_primary_10_1109_JSEN_2024_3418618 crossref_primary_10_1109_JSTARS_2020_3042760 crossref_primary_10_1016_j_engappai_2021_104199 crossref_primary_10_1109_JSEN_2020_3025613 crossref_primary_10_1016_j_jbi_2021_103791 crossref_primary_10_1016_j_engappai_2024_108856 crossref_primary_10_1016_j_compeleceng_2024_109984 crossref_primary_10_1109_JSEN_2018_2865306 crossref_primary_10_1109_JSEN_2024_3375913 crossref_primary_10_1109_JSEN_2019_2936520 crossref_primary_10_1016_j_measurement_2020_107534 crossref_primary_10_1016_j_measurement_2021_109337 crossref_primary_10_1109_JSEN_2018_2879187 crossref_primary_10_1007_s10586_021_03426_w crossref_primary_10_1007_s42979_024_02603_z crossref_primary_10_1007_s12083_020_00993_4 crossref_primary_10_1016_j_ifacol_2023_10_799 crossref_primary_10_1109_ACCESS_2020_2989870 crossref_primary_10_4018_IJCVIP_301605 crossref_primary_10_1049_itr2_12085 crossref_primary_10_1016_j_rineng_2025_106132 crossref_primary_10_1016_j_ssci_2021_105479 crossref_primary_10_3390_s23062938 crossref_primary_10_1109_JSEN_2021_3114214 crossref_primary_10_1016_j_vehcom_2023_100586 crossref_primary_10_1109_MIM_2024_10423660 crossref_primary_10_1088_2632_2153_abd51d crossref_primary_10_1109_JIOT_2020_2992349 crossref_primary_10_1109_JSEN_2018_2875954 crossref_primary_10_1109_JSEN_2022_3227012 crossref_primary_10_3390_app10082749 crossref_primary_10_1016_j_knosys_2021_107391 crossref_primary_10_1109_TASE_2025_3596630 crossref_primary_10_1109_JSEN_2020_3030030 crossref_primary_10_1016_j_cose_2024_104188 crossref_primary_10_1088_1361_6501_abfdde crossref_primary_10_1109_TITS_2020_2980864 crossref_primary_10_1016_j_applthermaleng_2025_127138 crossref_primary_10_1016_j_scs_2018_12_039 crossref_primary_10_1109_JSEN_2018_2886368
Cites_doi	10.1016/j.robot.2006.05.011 10.1109/IVS.2005.1505076 10.1016/j.micpro.2007.10.002 10.1109/IVS.2006.1689643 10.1109/CVPR.2012.6248017 10.1109/IVS.2010.5548114 10.1109/ICRA.2014.6907325 10.1109/34.1000236 10.1016/j.rcim.2015.09.006 10.1007/s10115-007-0114-2 10.1561/2200000006 10.1109/TITS.2016.2614818 10.1145/1390156.1390294 10.1016/j.tics.2007.09.004 10.1007/978-3-319-27702-8_15 10.1109/TSM.2007.907607 10.1016/j.robot.2017.04.001 10.1109/JSEN.2006.888583 10.1109/TPAMI.2012.277 10.1016/j.robot.2016.06.007 10.1007/978-3-642-40602-7_46 10.1109/JSEN.2014.2354987 10.1126/science.1136800 10.1007/s11222-007-9033-z 10.1145/235968.233324 10.1109/IVS.2013.6629641 10.1111/j.2517-6161.1977.tb01600.x 10.1109/ICARCV.2014.7064455 10.1016/j.trc.2007.06.005 10.5772/56603 10.1109/JSEN.2015.2490247 10.1109/JSEN.2016.2531122 10.1177/0278364913507326 10.1109/JSEN.2011.2169782 10.3390/s16081182 10.1007/978-3-319-10602-1_35 10.1109/ROBOT.2009.5152884 10.1007/978-3-319-49409-8_6
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION
DOI	10.1109/JSEN.2018.2831082
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography Engineering
EISSN	1558-1748
EndPage	5132
ExternalDocumentID	10_1109_JSEN_2018_2831082 8352801
Genre	orig-research
GrantInformation_xml	– fundername: King Abdullah University of Science and Technology Office of Sponsored Research grantid: OSR-2015-CRG4-2582 funderid: 10.13039/501100004052
GroupedDBID	-~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AGQYO AHBIQ AJQPL AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TWZ AAYXX CITATION
ID	FETCH-LOGICAL-c265t-a3c5fedf03d4ea1586cc55bc40a667a515d82a9c12e5107330dfc6e94877cbc83
IEDL.DBID	RIE
ISICitedReferencesCount	60
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000433384300039&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1530-437X
IngestDate	Tue Nov 18 21:14:42 EST 2025 Sat Nov 29 07:48:03 EST 2025 Wed Aug 27 03:06:20 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	12
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c265t-a3c5fedf03d4ea1586cc55bc40a667a515d82a9c12e5107330dfc6e94877cbc83
ORCID	0000-0001-6703-4270 0000-0003-4712-6949 0000-0002-2138-319X
PageCount	11
ParticipantIDs	crossref_primary_10_1109_JSEN_2018_2831082 crossref_citationtrail_10_1109_JSEN_2018_2831082 ieee_primary_8352801
PublicationCentury	2000
PublicationDate	2018-June15,-15 2018-6-15
PublicationDateYYYYMMDD	2018-06-15
PublicationDate_xml	– month: 06 year: 2018 text: 2018-June15,-15 day: 15
PublicationDecade	2010
PublicationTitle	IEEE sensors journal
PublicationTitleAbbrev	JSEN
PublicationYear	2018
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref12 ap (ref44) 2014 ref15 labayrade (ref28) 2003 ref14 ref52 ref11 ref54 ref10 vincent (ref41) 2010; 11 ref17 ref16 ref19 ref18 appiah (ref5) 2015 krizhevsky (ref53) 2012 omohundro (ref32) 1989 jain (ref39) 1988 ref51 montgomery (ref48) 2009 ref50 ref46 ref45 ref47 duguleana (ref22) 2012; 28 ramos (ref25) 2016 dempster (ref35) 1977; 39 ref49 ref7 ref9 ref4 ref3 ref6 hu (ref29) 2005 ref40 krizhevsky (ref42) 2011 ref34 bengio (ref23) 2007; 34 ref37 ref36 ref31 ref30 ref2 lu (ref43) 2013 arthur (ref33) 2007 ref38 del (ref8) 2006; 54 ref24 ref26 ref20 ref21 ref27 labayrade (ref1) 2002; 2
References_xml	– volume: 54 start-page: 967 year: 2006 ident: ref8 article-title: A sonar approach to obstacle detection for a vision-based autonomous wheelchair publication-title: Robot Auto Syst doi: 10.1016/j.robot.2006.05.011 – ident: ref47 doi: 10.1109/IVS.2005.1505076 – year: 1988 ident: ref39 publication-title: Algorithms for clustering data – ident: ref46 doi: 10.1016/j.micpro.2007.10.002 – ident: ref16 doi: 10.1109/IVS.2006.1689643 – start-page: 1097 year: 2012 ident: ref53 article-title: Imagenet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref17 doi: 10.1109/CVPR.2012.6248017 – year: 1989 ident: ref32 publication-title: Five balltree construction algorithms – ident: ref18 doi: 10.1109/IVS.2010.5548114 – start-page: 1853 year: 2014 ident: ref44 article-title: An autoencoder approach to learning bilingual word representations publication-title: Proc Adv Neural Inf Process Syst – ident: ref6 doi: 10.1109/ICRA.2014.6907325 – ident: ref34 doi: 10.1109/34.1000236 – ident: ref21 doi: 10.1016/j.rcim.2015.09.006 – volume: 11 start-page: 3371 year: 2010 ident: ref41 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J Mach Learn Res – ident: ref31 doi: 10.1007/s10115-007-0114-2 – ident: ref27 doi: 10.1561/2200000006 – ident: ref24 doi: 10.1109/TITS.2016.2614818 – ident: ref40 doi: 10.1145/1390156.1390294 – start-page: 48 year: 2005 ident: ref29 article-title: UV-disparity: An efficient algorithm for stereovision based scene analysis publication-title: Proc Intell Vehicles Symp – year: 2009 ident: ref48 publication-title: Introduction to Statistical Quality Control – ident: ref26 doi: 10.1016/j.tics.2007.09.004 – volume: 2 start-page: 646 year: 2002 ident: ref1 article-title: Real time obstacle detection in stereovision on non flat road geometry through 'v-disparity' representation publication-title: Proc IEEE Intell Vehicle Symp – ident: ref9 doi: 10.1007/978-3-319-27702-8_15 – start-page: 1 year: 2011 ident: ref42 article-title: Using very deep autoencoders for content-based image retrieval publication-title: Proc ESANN – ident: ref30 doi: 10.1109/TSM.2007.907607 – ident: ref7 doi: 10.1016/j.robot.2017.04.001 – ident: ref14 doi: 10.1109/JSEN.2006.888583 – ident: ref45 doi: 10.1109/TPAMI.2012.277 – year: 2016 ident: ref25 publication-title: Detecting unexpected obstacles for self-driving cars Fusing deep learning and geometric modeling – ident: ref10 doi: 10.1016/j.robot.2016.06.007 – ident: ref50 doi: 10.1007/978-3-642-40602-7_46 – ident: ref13 doi: 10.1109/JSEN.2014.2354987 – ident: ref38 doi: 10.1126/science.1136800 – volume: 28 start-page: 132 year: 2012 ident: ref22 article-title: Obstacle avoidance of redundant manipulators using neural networks based reinforcement learning publication-title: Robot Comput -Integr Manuf – year: 2015 ident: ref5 article-title: Obstacle detection using stereo vision for self-driving cars – ident: ref37 doi: 10.1007/s11222-007-9033-z – start-page: 1 year: 2003 ident: ref28 article-title: In-vehicle obstacles detection and characterization by stereovision publication-title: Proc 1st Int Workshop In-Vehicle Cognit Comput Vis Syst – ident: ref36 doi: 10.1145/235968.233324 – ident: ref3 doi: 10.1109/IVS.2013.6629641 – volume: 39 start-page: 1 year: 1977 ident: ref35 article-title: Maximum likelihood from incomplete data via the EM algorithm publication-title: J Roy Statist Soc Series B (Methodol ) doi: 10.1111/j.2517-6161.1977.tb01600.x – ident: ref20 doi: 10.1109/ICARCV.2014.7064455 – ident: ref54 doi: 10.1016/j.trc.2007.06.005 – ident: ref4 doi: 10.5772/56603 – ident: ref12 doi: 10.1109/JSEN.2015.2490247 – start-page: 1027 year: 2007 ident: ref33 article-title: k-means++: The advantages of careful seeding publication-title: Proc 18th Annu ACM-SIAM Symp Discrete Algorithms – ident: ref15 doi: 10.1109/JSEN.2016.2531122 – ident: ref49 doi: 10.1177/0278364913507326 – ident: ref11 doi: 10.1109/JSEN.2011.2169782 – ident: ref19 doi: 10.3390/s16081182 – ident: ref51 doi: 10.1007/978-3-319-10602-1_35 – volume: 34 start-page: 1 year: 2007 ident: ref23 article-title: Scaling learning algorithms towards AI publication-title: Large Scale Kernel Machines – ident: ref52 doi: 10.1109/ROBOT.2009.5152884 – start-page: 436 year: 2013 ident: ref43 article-title: Speech enhancement based on deep denoising autoencoder publication-title: Proc INTERSPEECH – ident: ref2 doi: 10.1007/978-3-319-49409-8_6
SSID	ssj0019757
Score	2.4737406
Snippet	Obstacle detection is an essential element for the development of intelligent transportation systems so that accidents can be avoided. In this paper, we...
SourceID	crossref ieee
SourceType	Enrichment Source Index Database Publisher
StartPage	5122
SubjectTerms	autonomous vehicles Clustering algorithms deep learning intelligent transportation systems Kernel Machine learning Machine learning algorithms Obstacle detection Partitioning algorithms Roads Sensors
Title	Obstacle Detection for Intelligent Transportation Systems Using Deep Stacked Autoencoder and k -Nearest Neighbor Scheme
URI	https://ieeexplore.ieee.org/document/8352801
Volume	18
WOSCitedRecordID	wos000433384300039&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 Electronic Library (IEL) customDbUrl: eissn: 1558-1748 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0019757 issn: 1530-437X databaseCode: RIE dateStart: 20010101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9swEBZpGLR72Namo9kv9LCnUSeKFUvWY9hStjG8QduRN2OfznRsdULibOy_353imgzGoOAHYSQw_k7oO93dd0K8Nol3jg7aSFXAYcYkjQqlyoicEdTOuKoMdWtfP9ksSxcL96UnzrtaGEQMyWc44mGI5fslbPmqbMxsIeVirQNrza5Wq4sYOBtUPWkDq2iq7aKNYE6UG3-8nGecxJWOYm6rlcZ_nUF7TVXCmXLx-H5f80Q8armjnO3APhY9rE_Ewz1FwRNx2DY1v_k9EL8-l0T9aKZ8h03IuKolUVT5oVPhbGSnbR4Akq1-uQyJBLQMV5LYKG10L2fbZsmilx7Xsqi9_C6jjPVvN43M-HqVbElekgXc4qm4vphfvX0ftX0WIohN0kSF5pQzXyntp1gQXAYgSUqYqsIYWxDj8WlcOJjESDvYaq18BQYd-ToWSkj1U9GvlzWeCVkoIG8b6UHy-5QuIUFiEQaqCYDVOBTq7s_n0IqQcy-MH3lwRpTLGaycwcpbsIbiTbdktVPg-N_kAQPVTWwxevbv18_FES_mzK9J8kL0m_UWX4oH8LP5tlm_Cvb1B_eMziU
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9RAEB5KK7Q-VL22eK3VffBJTLuXza99LP1BT88oXJV7C8nsBEWbK9ec4n_vzF4MJ4gg5CGE2RDy7bLf7Mx8A_AyiZ21vNEGukYJM8ZZUGpdBeyMkLGJrStft_ZpkuZ5NpvZDxvwuq-FISKffEYncutj-W6OSzkqOxW2kEmx1lYcRaFeVWv1MQObel1PXsI6iEw662KYI21P30wvc0njyk5CaayVhX_sQmttVfyucvXo_77nMex27FGdreB-AhvUDODhmqbgALa7tuaff-7Bj_cVkz-2VBfU-pyrRjFJVeNeh7NVvbq5h0h1CubKpxLwMLpTzEd5qTt1tmznInvpaKHKxqmvKshFAfe-VbkcsPJsUlOeA7e0Dx-vLm_Or4Ou00KAYRK3QWkk6czV2riISgYsQYzjCiNdJklaMudxWVhaHIXEazg1RrsaE7Ls7aRYYWYOYLOZN_QUVKmR_W3ii9jz06bCmJhHJFiPEFNDQ9C__3yBnQy5dMP4Vnh3RNtCwCoErKIDawiv-iF3Kw2OfxnvCVC9YYfR4d8fv4Dt65t3k2Iyzt8ewY68SPLARvEz2GwXSzqGB_i9_XK_eO7n2i_XIdFs
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=Obstacle+Detection+for+Intelligent+Transportation+Systems+Using+Deep+Stacked+Autoencoder+and+%24k%24+-Nearest+Neighbor+Scheme&rft.jtitle=IEEE+sensors+journal&rft.au=Dairi%2C+Abdelkader&rft.au=Harrou%2C+Fouzi&rft.au=Sun%2C+Ying&rft.au=Senouci%2C+Mohamed&rft.date=2018-06-15&rft.issn=1530-437X&rft.eissn=1558-1748&rft.volume=18&rft.issue=12&rft.spage=5122&rft.epage=5132&rft_id=info:doi/10.1109%2FJSEN.2018.2831082&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSEN_2018_2831082
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon