Robust Vehicle Detection in Aerial Images Based on Cascaded Convolutional Neural Networks

Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of con...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Sensors (Basel, Switzerland) Jg. 17; H. 12; S. 2720
Hauptverfasser:	Zhong, Jiandan, Lei, Tao, Yao, Guangle
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Switzerland MDPI AG 24.11.2017 MDPI
Schlagworte:	aerial image Computer vision convolutional neural network deep learning Neural networks vehicle detection vehicle detection deep learning aerial image convolutional neural network
ISSN:	1424-8220, 1424-8220
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of convolutional neural networks (CNNs) in computer vision, many state-of-the-art detectors have been designed based on deep CNNs. However, these CNN-based detectors are inefficient when applied in aerial image data due to the fact that the existing CNN-based models struggle with small-size object detection and precise localization. To improve the detection accuracy without decreasing speed, we propose a CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales. Because the multi-feature maps combine the advantage of the deep and shallow convolutional layer, the first network performs well on locating the small targets in aerial image data. Then, the generated candidate regions are fed into the second network for feature extraction and decision making. Comprehensive experiments are conducted on the Vehicle Detection in Aerial Imagery (VEDAI) dataset and Munich vehicle dataset. The proposed cascaded detection model yields high performance, not only in detection accuracy but also in detection speed.
AbstractList	Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of convolutional neural networks (CNNs) in computer vision, many state-of-the-art detectors have been designed based on deep CNNs. However, these CNN-based detectors are inefficient when applied in aerial image data due to the fact that the existing CNN-based models struggle with small-size object detection and precise localization. To improve the detection accuracy without decreasing speed, we propose a CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales. Because the multi-feature maps combine the advantage of the deep and shallow convolutional layer, the first network performs well on locating the small targets in aerial image data. Then, the generated candidate regions are fed into the second network for feature extraction and decision making. Comprehensive experiments are conducted on the Vehicle Detection in Aerial Imagery (VEDAI) dataset and Munich vehicle dataset. The proposed cascaded detection model yields high performance, not only in detection accuracy but also in detection speed. Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of convolutional neural networks (CNNs) in computer vision, many state-of-the-art detectors have been designed based on deep CNNs. However, these CNN-based detectors are inefficient when applied in aerial image data due to the fact that the existing CNN-based models struggle with small-size object detection and precise localization. To improve the detection accuracy without decreasing speed, we propose a CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales. Because the multi-feature maps combine the advantage of the deep and shallow convolutional layer, the first network performs well on locating the small targets in aerial image data. Then, the generated candidate regions are fed into the second network for feature extraction and decision making. Comprehensive experiments are conducted on the Vehicle Detection in Aerial Imagery (VEDAI) dataset and Munich vehicle dataset. The proposed cascaded detection model yields high performance, not only in detection accuracy but also in detection speed.Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were developed and achieved acceptable performance, but these models are time-consuming in the detection phase. Recently, with the great success of convolutional neural networks (CNNs) in computer vision, many state-of-the-art detectors have been designed based on deep CNNs. However, these CNN-based detectors are inefficient when applied in aerial image data due to the fact that the existing CNN-based models struggle with small-size object detection and precise localization. To improve the detection accuracy without decreasing speed, we propose a CNN-based detection model combining two independent convolutional neural networks, where the first network is applied to generate a set of vehicle-like regions from multi-feature maps of different hierarchies and scales. Because the multi-feature maps combine the advantage of the deep and shallow convolutional layer, the first network performs well on locating the small targets in aerial image data. Then, the generated candidate regions are fed into the second network for feature extraction and decision making. Comprehensive experiments are conducted on the Vehicle Detection in Aerial Imagery (VEDAI) dataset and Munich vehicle dataset. The proposed cascaded detection model yields high performance, not only in detection accuracy but also in detection speed.
Author	Yao, Guangle Lei, Tao Zhong, Jiandan
AuthorAffiliation	1 Institute of Optics and Electronics, Chinese Academy of Sciences, No. 1, Guangdian Avenue, Chengdu 610209, China; taoleiyan@ioe.ac.cn (T.L.); guangle.yao@std.uestc.edu.cn (G.Y.) 2 School of Optoelectronic Information, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, China 3 University of Chinese Academy of Sciences, 19 A Yuquan Rd, Shijingshan District, Beijing 100039, China
AuthorAffiliation_xml	– name: 2 School of Optoelectronic Information, University of Electronic Science and Technology of China, No. 4, Section 2, North Jianshe Road, Chengdu 610054, China – name: 3 University of Chinese Academy of Sciences, 19 A Yuquan Rd, Shijingshan District, Beijing 100039, China – name: 1 Institute of Optics and Electronics, Chinese Academy of Sciences, No. 1, Guangdian Avenue, Chengdu 610209, China; taoleiyan@ioe.ac.cn (T.L.); guangle.yao@std.uestc.edu.cn (G.Y.)
Author_xml	– sequence: 1 givenname: Jiandan orcidid: 0000-0001-5686-7955 surname: Zhong fullname: Zhong, Jiandan – sequence: 2 givenname: Tao orcidid: 0000-0002-0900-1582 surname: Lei fullname: Lei, Tao – sequence: 3 givenname: Guangle surname: Yao fullname: Yao, Guangle
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/29186756$$D View this record in MEDLINE/PubMed
BookMark	eNplkktrFEEQxxuJmIce_AIy4EUPa_r9uAhxfS0EBVHBU9PTXbPpdXY66Z6J-O3tySYhiacqqn71p16HaG9IAyD0nOA3jBl8XIgilCqKH6EDwilfaErx3h1_Hx2WssGYMsb0E7RPDdFSCXmAfn1L7VTG5iecRd9D8x5G8GNMQxOH5gRydH2z2ro1lOadKxCamlm64l2o_jINl6mfZrxiX2DKV2b8k_Lv8hQ97lxf4Nm1PUI_Pn74vvy8OP36abU8OV14Ls248KYDQXUrghY8BEIlo5oR6oXDqoaJ6bSSQWiq2pZJKTqNTSCSSpCCm5YdodVONyS3sec5bl3-a5OL9iqQ8tq6PM7DWQEGY0YU7qTjDhvDeMcNptAaronmVevtTut8arcQPAxjHeme6P3MEM_sOl1aoQQR1FSBV9cCOV1MUEa7jcVD37sB0lQsMQpLqo0iFX35AN2kKddFzpTWglGjZaVe3O3otpWbC1bgeAf4nErJ0FkfRzefpDYYe0uwnX_E3v5IrXj9oOJG9H_2H8hMuI0
CitedBy_id	crossref_primary_10_3390_electronics13020319 crossref_primary_10_3390_s19194062 crossref_primary_10_1155_2022_3247229 crossref_primary_10_3390_s18030774 crossref_primary_10_1002_dac_4928 crossref_primary_10_1109_LGRS_2019_2912582 crossref_primary_10_3390_rs11141708 crossref_primary_10_1016_j_sysarc_2021_102152 crossref_primary_10_1080_13682199_2023_2174651 crossref_primary_10_1109_JSEN_2020_3007883 crossref_primary_10_3390_rs12030417 crossref_primary_10_1155_2022_1828848 crossref_primary_10_3390_s22186837 crossref_primary_10_1109_ACCESS_2020_3040290 crossref_primary_10_3390_rs13193908 crossref_primary_10_3233_JIFS_169907 crossref_primary_10_1109_ACCESS_2023_3234281 crossref_primary_10_1007_s11760_019_01592_4 crossref_primary_10_3390_data7040047 crossref_primary_10_3390_rs11182176 crossref_primary_10_4018_IJSWIS_331083 crossref_primary_10_3390_computers12080151 crossref_primary_10_1109_ACCESS_2021_3049741 crossref_primary_10_1016_j_isprsjprs_2019_11_023 crossref_primary_10_1016_j_trc_2018_12_004 crossref_primary_10_1109_TITS_2021_3072872 crossref_primary_10_1109_JSTARS_2022_3179026 crossref_primary_10_3390_electronics13112140 crossref_primary_10_1080_23249935_2025_2511818 crossref_primary_10_1109_LGRS_2019_2930308 crossref_primary_10_1109_ACCESS_2020_2990870 crossref_primary_10_1109_JSTARS_2019_2933501 crossref_primary_10_1016_j_infrared_2019_04_008 crossref_primary_10_3390_rs13050862 crossref_primary_10_1007_s00371_024_03689_5 crossref_primary_10_1109_TGRS_2021_3051383 crossref_primary_10_1007_s11554_024_01457_1 crossref_primary_10_1109_JSTARS_2022_3169128 crossref_primary_10_3390_ijgi10080549 crossref_primary_10_3390_rs14246270 crossref_primary_10_3390_s24175661 crossref_primary_10_1109_LGRS_2019_2909541 crossref_primary_10_3390_electronics12061312 crossref_primary_10_3390_rs12172734 crossref_primary_10_3390_rs13214196 crossref_primary_10_1155_2019_9282141 crossref_primary_10_3390_agriculture10030057 crossref_primary_10_1016_j_isprsjprs_2019_07_009 crossref_primary_10_1109_ACCESS_2019_2947143 crossref_primary_10_3390_s23041865 crossref_primary_10_1109_JSTARS_2022_3181594 crossref_primary_10_1109_ACCESS_2020_2994379 crossref_primary_10_1007_s11760_022_02328_7 crossref_primary_10_1049_ipr2_12038 crossref_primary_10_3390_s18072386 crossref_primary_10_1007_s11042_020_08807_8
Cites_doi	10.1109/CVPR.2016.91 10.1007/978-3-540-88693-8_52 10.1162/neco.1989.1.4.541 10.1023/B:VISI.0000029664.99615.94 10.1109/ICCV.2015.296 10.1109/CVPR.2016.97 10.3390/s17020336 10.1007/s10043-015-0067-8 10.1109/TPAMI.2012.28 10.1109/CVPR.2015.7298621 10.3390/s16081325 10.1109/TPAMI.2015.2465908 10.1007/978-3-319-10602-1_48 10.1109/CVPR.2014.49 10.1109/ICCV.2015.169 10.1109/TPAMI.2012.120 10.1007/978-3-319-10590-1_53 10.1109/JSTARS.2017.2694890 10.1109/TPAMI.2015.2389824 10.1109/CVPR.2014.414 10.1007/978-3-319-10602-1_26 10.3390/rs61111315 10.1007/s11042-015-2520-x 10.1145/1961189.1961199 10.1109/ICCV.2015.285 10.3390/rs9040312 10.1109/CVPR.2015.7298965 10.1007/s11263-013-0620-5 10.1109/TCSVT.2014.2358031 10.1109/TPAMI.2011.231 10.1109/LGRS.2015.2439517 10.1109/TPAMI.2016.2577031 10.1145/2647868.2654889 10.1007/978-3-662-44851-9_15 10.1109/CVPR.2016.98 10.1109/CVPR.2014.81 10.1109/CVPR.2014.276 10.1007/s11263-009-0275-4 10.1016/j.jvcir.2015.11.002 10.1007/978-3-642-15555-0_16 10.1109/TPAMI.2009.167 10.1007/s11042-016-4043-5
ContentType	Journal Article
Copyright	Copyright MDPI AG 2017 2017 by the authors. 2017
Copyright_xml	– notice: Copyright MDPI AG 2017 – notice: 2017 by the authors. 2017
DBID	AAYXX CITATION NPM 3V. 7X7 7XB 88E 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA
DOI	10.3390/s17122720
DatabaseName	CrossRef PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) ProQuest Hospital Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) ProQuest Health & Medical Collection Medical Database ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef PubMed Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic
DatabaseTitleList	Publicly Available Content Database CrossRef MEDLINE - Academic PubMed
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1424-8220
ExternalDocumentID	oai_doaj_org_article_5e9003170f6a4a09934f4902eb948184 PMC5751529 29186756 10_3390_s17122720
Genre	Journal Article
GroupedDBID	--- 123 2WC 53G 5VS 7X7 88E 8FE 8FG 8FI 8FJ AADQD AAHBH AAYXX ABDBF ABUWG ACUHS ADBBV ADMLS ADRAZ AENEX AFFHD AFKRA AFZYC ALMA_UNASSIGNED_HOLDINGS BENPR BPHCQ BVXVI CCPQU CITATION CS3 D1I DU5 E3Z EBD ESX F5P FYUFA GROUPED_DOAJ GX1 HH5 HMCUK HYE IPNFZ KQ8 L6V M1P M48 MODMG M~E OK1 OVT P2P P62 PHGZM PHGZT PIMPY PJZUB PPXIY PQQKQ PROAC PSQYO RIG RNS RPM TUS UKHRP XSB ~8M 3V. ABJCF ALIPV ARAPS HCIFZ KB. M7S NPM PDBOC 7XB 8FK AZQEC DWQXO K9. PKEHL PQEST PQUKI PRINS 7X8 PUEGO 5PM
ID	FETCH-LOGICAL-c469t-c9fe528b5d854dd126328312c5a078b519f876d5827bb3665f809d1626e6549b3
IEDL.DBID	DOA
ISICitedReferencesCount	57
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000423285800020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1424-8220
IngestDate	Fri Oct 03 12:50:41 EDT 2025 Tue Nov 04 01:50:59 EST 2025 Thu Sep 04 19:23:08 EDT 2025 Sat Nov 29 14:55:21 EST 2025 Tue Feb 25 01:06:50 EST 2025 Tue Nov 18 21:47:11 EST 2025 Sat Nov 29 07:10:15 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	12
Keywords	vehicle detection deep learning aerial image convolutional neural network
Language	English
License	Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c469t-c9fe528b5d854dd126328312c5a078b519f876d5827bb3665f809d1626e6549b3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-5686-7955 0000-0002-0900-1582
OpenAccessLink	https://doaj.org/article/5e9003170f6a4a09934f4902eb948184
PMID	29186756
PQID	1988532986
PQPubID	2032333
ParticipantIDs	doaj_primary_oai_doaj_org_article_5e9003170f6a4a09934f4902eb948184 pubmedcentral_primary_oai_pubmedcentral_nih_gov_5751529 proquest_miscellaneous_1970628971 proquest_journals_1988532986 pubmed_primary_29186756 crossref_citationtrail_10_3390_s17122720 crossref_primary_10_3390_s17122720
PublicationCentury	2000
PublicationDate	20171124
PublicationDateYYYYMMDD	2017-11-24
PublicationDate_xml	– month: 11 year: 2017 text: 20171124 day: 24
PublicationDecade	2010
PublicationPlace	Switzerland
PublicationPlace_xml	– name: Switzerland – name: Basel
PublicationTitle	Sensors (Basel, Switzerland)
PublicationTitleAlternate	Sensors (Basel)
PublicationYear	2017
Publisher	MDPI AG MDPI
Publisher_xml	– name: MDPI AG – name: MDPI
References	Chang (ref_7) 2011; 2 Alexe (ref_12) 2012; 54 Ren (ref_19) 2017; 39 ref_14 ref_13 ref_11 Razakarivony (ref_42) 2016; 34 Tang (ref_1) 2017; 76 Felzenszwalb (ref_9) 2010; 32 ref_18 ref_16 ref_15 Bergh (ref_32) 2013; 7578 Gu (ref_4) 2015; 22 ref_24 ref_22 LeCun (ref_45) 1989; 4 ref_21 ref_20 Everingham (ref_47) 2010; 88 ref_28 ref_27 ref_26 Liu (ref_43) 2015; 12 Lowe (ref_6) 2004; 60 Hosang (ref_25) 2016; 38 ref_36 ref_35 ref_34 ref_33 ref_31 ref_30 ref_38 ref_37 He (ref_17) 2015; 37 Leitloff (ref_50) 2014; 6 ref_46 Qu (ref_39) 2016; 76 Uijlings (ref_10) 2013; 104 ref_44 ref_40 Carreira (ref_23) 2012; 34 Achanta (ref_29) 2012; 34 ref_3 Wen (ref_2) 2015; 25 ref_49 ref_48 Deng (ref_41) 2017; 10 ref_8 ref_5
References_xml	– ident: ref_5 – ident: ref_36 doi: 10.1109/CVPR.2016.91 – ident: ref_30 doi: 10.1007/978-3-540-88693-8_52 – volume: 4 start-page: 541 year: 1989 ident: ref_45 article-title: Backpropagation applied to handwritten zip code recognition publication-title: Neural Comput. doi: 10.1162/neco.1989.1.4.541 – ident: ref_16 – volume: 60 start-page: 91 year: 2004 ident: ref_6 article-title: Distinctive image features from scale-invariant keypoints publication-title: Int. J. Comput. Vis. doi: 10.1023/B:VISI.0000029664.99615.94 – ident: ref_22 doi: 10.1109/ICCV.2015.296 – ident: ref_26 doi: 10.1109/CVPR.2016.97 – ident: ref_40 doi: 10.3390/s17020336 – volume: 22 start-page: 197 year: 2015 ident: ref_4 article-title: Vision-based multi-scaled vehicle detection and distance relevant mix tracking for driver assistance system publication-title: Opt. Rev. doi: 10.1007/s10043-015-0067-8 – volume: 54 start-page: 2189 year: 2012 ident: ref_12 article-title: Measuring the objectness of image windows publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2012.28 – ident: ref_8 – ident: ref_33 doi: 10.1109/CVPR.2015.7298621 – ident: ref_37 doi: 10.3390/s16081325 – volume: 38 start-page: 814 year: 2016 ident: ref_25 article-title: What makes for effective detection proposals? publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2465908 – ident: ref_13 – ident: ref_20 doi: 10.1007/978-3-319-10602-1_48 – ident: ref_27 doi: 10.1109/CVPR.2014.49 – ident: ref_18 doi: 10.1109/ICCV.2015.169 – volume: 34 start-page: 2274 year: 2012 ident: ref_29 article-title: SLIC superpixels compared to state-of-the-art superpixel methods publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2012.120 – ident: ref_49 doi: 10.1007/978-3-319-10590-1_53 – volume: 10 start-page: 3652 year: 2017 ident: ref_41 article-title: Toward Fast and Accurate Vehicle Detection in Aerial Images Using Coupled Region-Based Convolutional Neural Networks publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2017.2694890 – volume: 7578 start-page: 1 year: 2013 ident: ref_32 article-title: SEEDS: Superpixels Extracted via Energy-Driven Sampling publication-title: Int. J. Comput. Vis. – volume: 37 start-page: 1904 year: 2015 ident: ref_17 article-title: Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2389824 – ident: ref_3 – ident: ref_11 doi: 10.1109/CVPR.2014.414 – ident: ref_24 doi: 10.1007/978-3-319-10602-1_26 – volume: 6 start-page: 11315 year: 2014 ident: ref_50 article-title: An operational system for estimating road traffic information from aerial images publication-title: Remote Sens. doi: 10.3390/rs61111315 – volume: 76 start-page: 5817 year: 2017 ident: ref_1 article-title: Vehicle detection and recognition for intelligent traffic surveillance system publication-title: Multimedia Tools Appl. doi: 10.1007/s11042-015-2520-x – volume: 2 start-page: 389 year: 2011 ident: ref_7 article-title: LIBSVM: A library for support vector machines publication-title: ACM Trans. Intell. Syst. Technol. doi: 10.1145/1961189.1961199 – ident: ref_28 doi: 10.1109/ICCV.2015.285 – ident: ref_38 doi: 10.3390/rs9040312 – ident: ref_14 – ident: ref_34 doi: 10.1109/CVPR.2015.7298965 – ident: ref_21 – volume: 104 start-page: 154 year: 2013 ident: ref_10 article-title: Selective search for object recognition publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-013-0620-5 – volume: 25 start-page: 508 year: 2015 ident: ref_2 article-title: Efficient Feature Selection and Classification for Vehicle Detection publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2014.2358031 – volume: 34 start-page: 1312 year: 2012 ident: ref_23 article-title: CPMC: Automatic object segmentation using constrained parametric min-cuts publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2011.231 – volume: 12 start-page: 1938 year: 2015 ident: ref_43 article-title: Fast Multiclass Vehicle Detection on Aerial Images publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2015.2439517 – volume: 39 start-page: 1137 year: 2017 ident: ref_19 article-title: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2577031 – ident: ref_46 doi: 10.1145/2647868.2654889 – ident: ref_48 doi: 10.1007/978-3-662-44851-9_15 – ident: ref_44 doi: 10.1109/CVPR.2016.98 – ident: ref_15 doi: 10.1109/CVPR.2014.81 – ident: ref_35 doi: 10.1109/CVPR.2014.276 – volume: 88 start-page: 303 year: 2010 ident: ref_47 article-title: The Pascal Visual Object Classes (VOC) Challenge publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-009-0275-4 – volume: 34 start-page: 187 year: 2016 ident: ref_42 article-title: Vehicle detection in aerial imagery: A small target detection benchmark publication-title: J. Vis. Commun. Image Represent. doi: 10.1016/j.jvcir.2015.11.002 – ident: ref_31 doi: 10.1007/978-3-642-15555-0_16 – volume: 32 start-page: 1627 year: 2010 ident: ref_9 article-title: Object detection with discriminatively trained part based models publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2009.167 – volume: 76 start-page: 21651 year: 2016 ident: ref_39 article-title: Vehicle detection from high-resolution aerial images using spatial pyramid pooling-based deep convolutional neural networks publication-title: Multimedia Tools Appl. doi: 10.1007/s11042-016-4043-5
SSID	ssj0023338
Score	2.4756489
Snippet	Vehicle detection in aerial images is an important and challenging task. Traditionally, many target detection models based on sliding-window fashion were...
SourceID	doaj pubmedcentral proquest pubmed crossref
SourceType	Open Website Open Access Repository Aggregation Database Index Database Enrichment Source
StartPage	2720
SubjectTerms	aerial image Computer vision convolutional neural network deep learning Neural networks vehicle detection
SummonAdditionalLinks	– databaseName: Publicly Available Content Database dbid: PIMPY link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELZgy4EeeD8CBRnEgUu0sR3H9gm1CxU9UK0QoPYUObHdrgRJu8n29zOT9YYuqjhxihRPJEfz9oy_IeQdCI3NgzKpMCKkuQoitUxnqRfgbqvAjZX1MGxCHR_rkxMzj9eju9hWubGJg6Feoz1j3zYY4alrazwxn0KqDH6GG118uLhMcYYU1lrjQI3bZAeBt_SE7MyPvsxPxwRMQD62RhcSkOpPO6YYxzrklk8aoPtvijf_bpu85ocO7__fP3hA7sV4lO6vBeghueWbR2T3GkrhY3L6ta1WXU9_-HOkoR99P_RvNXTR0P1BgunRL7BLHT0An-gorMxsh433js7a5ipKN5AhFMjwGHrPuyfk--Gnb7PPaZzIkNaQRvdpbYKXXFfSaZk7xxDsXQvGa2kh1KggGgxgXZ3UXFWVKAoZdGYcg6TJF5CIVuIpmTRt458Tmqlgg-RF5YPMgxPWZK5G2PPgIKgyKiHvNzwp6whXjlMzfpaQtiD7ypF9CXk7kl6sMTpuIjpAxo4ECKs9vGiXZ2XU0lJ6PNhlKguFzS0EzyIPucm4rxDURucJ2duwtoy63pV_OJmQN-MyaCmWXmzj2xXSKLysahRLyLO1FI074QZBBSV8rbbka2ur2yvN4nxAAseimeTmxb-39ZLc5RiMMJbyfI9M-uXKvyJ36qt-0S1fRyX5DR_nIuU priority: 102 providerName: ProQuest
Title	Robust Vehicle Detection in Aerial Images Based on Cascaded Convolutional Neural Networks
URI	https://www.ncbi.nlm.nih.gov/pubmed/29186756 https://www.proquest.com/docview/1988532986 https://www.proquest.com/docview/1970628971 https://pubmed.ncbi.nlm.nih.gov/PMC5751529 https://doaj.org/article/5e9003170f6a4a09934f4902eb948184
Volume	17
WOSCitedRecordID	wos000423285800020&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: DOA dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: M~E dateStart: 20010101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: 7X7 dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: BENPR dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: PIMPY dateStart: 20010101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3Pb9MwFH6CwQEOaPwOjMogDlyixXYc28e168QOq6oJUHeKnNjWKo0ULe2O_O08O2nUoklcuCSS_SI5z89-34tfvgfwGY3G5F7qlGvu01x6nhqqstRxdLeVZ9qIOhabkLOZWiz0fKfUV8gJ6-iBO8UdCxe-tVGZ-cLkBvEMz32uM-aqwDOiIhMoop5tMNWHWhwjr45HiGNQf9xSSVk4cdzzPpGk_z5k-XeC5I7HOTuEZz1UJCfdEJ_DA9e8gKc7BIIv4epyVW3aNfnhroMMOXXrmFrVkGVDTqJxkfOfuGW0ZIzuyhLsmZg25MRbMlk1d73hoVhg6Yi3mBbevoLvZ9Nvk69pXywhrTHCXae19k4wVQmrRG4tDTzsilNWC4MooEKg5nHjs0IxWVW8KIRXmbYU4xlXYIxY8ddw0Kwa9xZIJr3xghWV8yL3lhud2TowknuLeEfLBL5slVjWPZN4KGhxU2JEEfRdDvpO4NMg-qujz7hPaBxmYhAIjNexAe2g7O2g_JcdJHC0nceyX4ZtSbVCOMK0KhL4OHTjAgqnIqZxq02QkeE_Ui1pAm-6aR9GwnTg-xP4tNwziL2h7vc0y-tI0h3OswTT7_7Hu72HJyygCUpTlh_Bwfp24z7A4_puvWxvR_BQLmS8qhE8Gk9n88tRXA14vfg9xbb5-cX86g9lnQw0
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VgkQ58H4sFDAIJC5REzuO4wNC7Zaqq5YVQgVtTyGJ7XYlSMpmt4g_xW9kJq92UcWtB06R4knkxJ_nYY-_AXiFoElDp7QntHBeqJzw0iD2PSvQ3GaO61TmdbEJNR7Hk4n-uAK_u7MwlFbZ6cRaUZsypzXyDQyO0bJwHUfvTn54VDWKdle7EhoNLPbsr58YslVvR9s4vq8533l_MNz12qoCXo6h4NzLtbOSx5k0sQyNCYiwPBYBz2WK5jJDj8ahhjAy5irLRBRJF_vaBOj42wiDqUzge6_AVdTjilLI1OQswBMY7zXsRUJof6MKVMBpn3PJ5tWlAS7yZ_9Oyzxn53Zu_W9_6DbcbD1qttlMgTuwYou7cOMcz-I9OPxUZotqzr7YY5Jh23ZeZ6AVbFqwzXoOstF31KwV20Krbhi2DNOKjg4YNiyL03Z-ohiRmdSXOnu-ug-fL-XbHsBqURb2ETBfudRJHmXWydAZkWrf5ETc7gy6hVoN4E036kneEq5T3Y9vCQZeBJCkB8gAXvaiJw3LyEVCWwSdXoCIwesb5ewoafVMIi0tTQfKd1Eapuj-i9CF2uc2I1qeOBzAegeepNVWVXKGnAG86JtRz9DmUVrYckEyio7bahUM4GGD074nXBMtosSn1RKCl7q63FJMj2suc9r2k1w__ne3nsP13YMP-8n-aLz3BNY4uVZB4PFwHVbns4V9Ctfy0_m0mj2rJySDr5eN7z83a2-W
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nj9MwEB0tC0Jw4PsjsIBBIHGJmthxHB8Q2m2pqBZVKwSonEIS22wlSJYmXcRf49cxkybdLVpx2wOnSvGkctrnmXnx-A3AcwRNFjmlfaGF8yPlhJ-FSeBbgeE2d1xnsmibTajpNJnN9MEW_O7PwlBZZe8TW0dtqoLekQ-QHGNk4TqJB64rizgYjV8f_fCpgxTttPbtNFYQ2be_fiJ9q19NRvhfv-B8_ObD8K3fdRjwC6SFjV9oZyVPcmkSGRkTknh5IkJeyAxDZ47ZjUNvYWTCVZ6LOJYuCbQJkQTYGIlVLvB7L8BFJYSithFqdkL2BHK_lZKREDoY1KEKOe15bsS_tk3AWbnt3yWap2Le-Pr__GvdgGtdps12V0vjJmzZ8hZcPaW_eBs-v6_yZd2wT_aQbNjINm1lWsnmJdtt1yabfEePW7M9jPaG4cgwq-lIgWHDqjzu1i2akchJ-9FW1dd34OO5PNtd2C6r0t4HFiiXOcnj3DoZOSMyHZiCBN2dwXRRKw9e9ghIi06InfqBfEuRkBFY0jVYPHi2Nj1aqY-cZbRHMFobkGB4e6FafE07_5NKS6-sQxW4OIsypAUicpEOuM1JrieJPNjpgZR2XqxOT1DkwdP1MPof2lTKSlstyUbRMVytQg_urTC7ngnXJJco8W61geaNqW6OlPPDVuOctgMl1w_-Pa0ncBlhnb6bTPcfwhVOGVcY-jzage1msbSP4FJx3MzrxeN2bTL4ct7w_gNLJnhK
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=Robust+Vehicle+Detection+in+Aerial+Images+Based+on+Cascaded+Convolutional+Neural+Networks&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.date=2017-11-24&rft.eissn=1424-8220&rft.volume=17&rft.issue=12&rft_id=info:doi/10.3390%2Fs17122720&rft_id=info%3Apmid%2F29186756&rft.externalDocID=29186756
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon