Fast Pedestrian Detection Based on the Selective Window Differential Filter
Following the recent progress of the pixel-level filtering for pedestrian detection, we propose a window differential feature (WDF) based on the multiple channel maps. More specifically, WDF encodes first-order statistics between artitary two pixels in the whole detection window, thus obtaining larg...
Saved in:
| Published in | Neural processing letters Vol. 48; no. 1; pp. 403 - 417 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
New York
Springer US
01.08.2018
Springer Nature B.V |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Following the recent progress of the pixel-level filtering for pedestrian detection, we propose a window differential feature (WDF) based on the multiple channel maps. More specifically, WDF encodes first-order statistics between artitary two pixels in the whole detection window, thus obtaining larger receptive field for achor pixel than other filtering methods. Despite obtaining more discriminative information for pedestrian, WDF suffers expensive space complexity due to the high feature dimensionality. Quantitive analysis for the arbitrary pairwise elements in the WDF vector demonstrates the weak correlations existing in the proposed feature, thus motivate dimension reduction with feature selection to be the top choice. Three different dimension reduction methods for the WDF demonstrate that feature selection with mutual information achieves superior result. In addition, we find the complementary characteristics between the baseline feature and selective window differential feature, thus combining both can obtain further performance improvement. Extensive experiments on the INRIA, Caltech, ETH, and TUD-Brussel datasets consistently show superior performance of the proposed method to state-of-the-art methods with a 22 fps running speed for 640
×
480 images. |
|---|---|
| AbstractList | Following the recent progress of the pixel-level filtering for pedestrian detection, we propose a window differential feature (WDF) based on the multiple channel maps. More specifically, WDF encodes first-order statistics between artitary two pixels in the whole detection window, thus obtaining larger receptive field for achor pixel than other filtering methods. Despite obtaining more discriminative information for pedestrian, WDF suffers expensive space complexity due to the high feature dimensionality. Quantitive analysis for the arbitrary pairwise elements in the WDF vector demonstrates the weak correlations existing in the proposed feature, thus motivate dimension reduction with feature selection to be the top choice. Three different dimension reduction methods for the WDF demonstrate that feature selection with mutual information achieves superior result. In addition, we find the complementary characteristics between the baseline feature and selective window differential feature, thus combining both can obtain further performance improvement. Extensive experiments on the INRIA, Caltech, ETH, and TUD-Brussel datasets consistently show superior performance of the proposed method to state-of-the-art methods with a 22 fps running speed for 640 × 480 images. Following the recent progress of the pixel-level filtering for pedestrian detection, we propose a window differential feature (WDF) based on the multiple channel maps. More specifically, WDF encodes first-order statistics between artitary two pixels in the whole detection window, thus obtaining larger receptive field for achor pixel than other filtering methods. Despite obtaining more discriminative information for pedestrian, WDF suffers expensive space complexity due to the high feature dimensionality. Quantitive analysis for the arbitrary pairwise elements in the WDF vector demonstrates the weak correlations existing in the proposed feature, thus motivate dimension reduction with feature selection to be the top choice. Three different dimension reduction methods for the WDF demonstrate that feature selection with mutual information achieves superior result. In addition, we find the complementary characteristics between the baseline feature and selective window differential feature, thus combining both can obtain further performance improvement. Extensive experiments on the INRIA, Caltech, ETH, and TUD-Brussel datasets consistently show superior performance of the proposed method to state-of-the-art methods with a 22 fps running speed for 640 × 480 images. |
| Author | Qian, Chengshan Shen, Jifeng Yu, Hualong Zuo, Xin Shan, Yongwei Xu, Dan |
| Author_xml | – sequence: 1 givenname: Xin surname: Zuo fullname: Zuo, Xin organization: School of Computer Science and Engineering, Jiangsu University of Science and Technology – sequence: 2 givenname: Jifeng surname: Shen fullname: Shen, Jifeng email: shenjifeng1980@hotmail.com organization: School of Electronic and Informatics Engineering, Jiangsu University – sequence: 3 givenname: Hualong surname: Yu fullname: Yu, Hualong organization: School of Computer Science and Engineering, Jiangsu University of Science and Technology – sequence: 4 givenname: Dan surname: Xu fullname: Xu, Dan organization: School of Computer Science and Engineering, Jiangsu University of Science and Technology – sequence: 5 givenname: Chengshan surname: Qian fullname: Qian, Chengshan organization: School of Computer and Software, Nanjing University of Information Science and Technology – sequence: 6 givenname: Yongwei surname: Shan fullname: Shan, Yongwei organization: School of Civil and Environmental Engineering, Oklahoma State University |
| BookMark | eNp9kEFLAzEQhYNUsK3-AG8Bz9Fks7vZPWprVSwoqOgtTDeJpqzZmqSK_94sKwiCnmaYvG_m5U3QyHVOI3TI6DGjVJwExmjJCWWC1CIvSbWDxqwQnAjBn0ap54KSvMzYHpqEsKY0URkdo-sFhIhvtdIhegsOz3XUTbSdw2cQtMKpiS8a3-m2H79r_Gid6j7w3BqjvXbRQosXto3a76NdA23QB991ih4W5_ezS7K8ubianS5Jw1kZCagGmqJWKyHyShUKDGs45BXPIVcVr5gpINkVGVcrQxVVoqoLMKBXOUsvwKfoaNi78d3bNhmX627rXTops5qlPVkhqqQSg6rxXQheG9nYCP3PogfbSkZln5wckpMpOdknJ3uS_SI33r6C__yXyQYmJK171v7H09_QFyovgpA |
| CitedBy_id | crossref_primary_10_1007_s11063_019_10046_4 |
| Cites_doi | 10.1109/CVPR.2009.5206638 10.1016/j.patcog.2016.09.010 10.1214/aos/1016218223 10.1109/TPAMI.2015.2474388 10.1109/TPAMI.2009.167 10.5244/C.23.91 10.5244/C.29.176 10.1109/CVPR.2015.7298784 10.1145/2508037.2508039 10.1016/j.neucom.2017.03.007 10.1007/978-3-319-46475-6_28 10.1109/TPAMI.2014.2300479 10.1016/j.image.2016.06.002 10.1145/1961189.1961199 10.1007/s00521-012-1153-5 10.1109/TPAMI.2015.2469276 10.5244/C.29.32 10.1016/j.neucom.2015.08.107 10.1162/neco.2006.18.7.1527 10.1109/ICCV.2015.18 10.1109/TPAMI.2009.109 10.1109/TPAMI.2011.155 10.1109/CVPR.2005.177 10.1016/j.ins.2014.10.040 10.1109/TSMC.2016.2629509 10.1109/CVPR.2014.126 10.1007/s11263-016-0880-y 10.1109/ICCV.2009.5459207 10.1016/j.neucom.2011.03.032 10.1109/ICCV.2015.312 |
| ContentType | Journal Article |
| Copyright | Springer Science+Business Media, LLC, part of Springer Nature 2017 Copyright Springer Nature B.V. Aug 2018 |
| Copyright_xml | – notice: Springer Science+Business Media, LLC, part of Springer Nature 2017 – notice: Copyright Springer Nature B.V. Aug 2018 |
| DBID | AAYXX CITATION 8FE 8FG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- P5Z P62 PHGZM PHGZT PKEHL PQEST PQGLB PQQKQ PQUKI PRINS PSYQQ |
| DOI | 10.1007/s11063-017-9746-8 |
| DatabaseName | CrossRef ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central UK/Ireland Advanced Technologies & Aerospace Collection ProQuest Central Essentials Proquest Central Technology Collection ProQuest One ProQuest Central ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic (New) ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China ProQuest One Psychology |
| DatabaseTitle | CrossRef Advanced Technologies & Aerospace Collection ProQuest One Psychology Computer Science Database ProQuest Central Student Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection ProQuest One Academic Eastern Edition SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central Advanced Technologies & Aerospace Database ProQuest One Applied & Life Sciences ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic ProQuest One Academic (New) |
| DatabaseTitleList | Advanced Technologies & Aerospace Collection |
| Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1573-773X |
| EndPage | 417 |
| ExternalDocumentID | 10_1007_s11063_017_9746_8 |
| GrantInformation_xml | – fundername: Natural Science Foundation of Jiangsu Province grantid: BK20140566; BK20150470 funderid: http://dx.doi.org/10.13039/501100004608 – fundername: National Natural Science Foundation of China grantid: 61305058 funderid: http://dx.doi.org/10.13039/501100001809 – fundername: Jiangsu University grantid: 13JDG093 funderid: http://dx.doi.org/10.13039/501100002703 – fundername: Basic Research Program of Jiangsu Education Department grantid: 15KJB520008; 16KJB520009 funderid: http://dx.doi.org/10.13039/501100005144 |
| GroupedDBID | -4Z -5F -5G -BR -EM -Y2 -~C .86 .DC .VR 06D 0R~ 0VY 123 1N0 1SB 2.D 203 28- 29N 2J2 2JN 2JY 2KG 2LR 2P1 2VQ 2~H 30V 4.4 406 408 409 40D 40E 53G 5QI 5VS 67Z 6NX 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AAHNG AAIAL AAJKR AAJSJ AAKKN AANZL AAOBN AARHV AARTL AATVU AAUYE AAWCG AAYIU AAYOK AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDZT ABECU ABEEZ ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMOR ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABWNU ABXPI ACACY ACBXY ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACSNA ACULB ACZOJ ADHHG ADHIR ADIMF ADINQ ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFEXP AFGCZ AFGXO AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN B-. BA0 BBWZM BDATZ BENPR BGLVJ BGNMA C24 C6C CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 EBLON EBS EIOEI EJD ESBYG FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNWQR GQ6 GQ7 GQ8 GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I09 IHE IJ- IKXTQ ITM IWAJR IXC IXE IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ K7- KDC KOV KOW LAK LLZTM M4Y MA- N2Q NB0 NDZJH NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM OVD P19 P2P P9O PF0 PSYQQ PT5 QOK QOS R4E R89 R9I RHV RNI RNS ROL RPX RSV RZC RZE RZK S16 S1Z S26 S27 S28 S3B SAP SCJ SCLPG SDH SDM SHX SISQX SNE SNPRN SNX SOHCF SOJ SPH SPISZ SRMVM SSLCW STPWE SZN T13 T16 TEORI TSG TSK TSV TUC U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z7R Z7X Z81 Z83 Z88 Z8M Z8R Z8U Z8W Z92 ZMTXR ~EX AASML AAYXX ABDBE ABFSG ACSTC ADHKG AEZWR AFHIU AGQPQ AHPBZ AHWEU AIXLP AYFIA CITATION PHGZM PHGZT 8FE 8FG AZQEC DWQXO GNUQQ JQ2 P62 PKEHL PQEST PQGLB PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c316t-adcac59db7748d5daf1c3a4834a4d8381f5a137723dbf0d0d7895afaeb415a1a3 |
| IEDL.DBID | BENPR |
| ISSN | 1370-4621 |
| IngestDate | Wed Aug 13 10:40:14 EDT 2025 Thu Apr 24 23:08:58 EDT 2025 Tue Jul 01 01:09:30 EDT 2025 Fri Feb 21 02:36:37 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Keywords | Feature selection Windows differential feature Pedestrian detection |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c316t-adcac59db7748d5daf1c3a4834a4d8381f5a137723dbf0d0d7895afaeb415a1a3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| PQID | 2918342578 |
| PQPubID | 2043838 |
| PageCount | 15 |
| ParticipantIDs | proquest_journals_2918342578 crossref_citationtrail_10_1007_s11063_017_9746_8 crossref_primary_10_1007_s11063_017_9746_8 springer_journals_10_1007_s11063_017_9746_8 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 20180800 2018-8-00 20180801 |
| PublicationDateYYYYMMDD | 2018-08-01 |
| PublicationDate_xml | – month: 8 year: 2018 text: 20180800 |
| PublicationDecade | 2010 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York – name: Dordrecht |
| PublicationTitle | Neural processing letters |
| PublicationTitleAbbrev | Neural Process Lett |
| PublicationYear | 2018 |
| Publisher | Springer US Springer Nature B.V |
| Publisher_xml | – name: Springer US – name: Springer Nature B.V |
| References | ShengBHuQLiJYangWZhangBSunCFiltered shallow-deep feature channels for pedestrian detectionNeurocomputing2017249192710.1016/j.neucom.2017.03.007 Dollar P, Tu Z, Perona P, Belongie S (2009) Integral channel features. In: British machine vision conference, vol 91, pp 1–11 WenXShaoLXueYFangWA rapid learning algorithm for vehicle classificationInf Sci201529539540610.1016/j.ins.2014.10.040 GuBShengVSA robust regularization path algorithm for v-support vector classificationIEEE Trans Neural Netw Learn Syst20169918 ZhangBLiZCaoXYeQChenCShenLPerinaAJillROutput constraint transfer for kernelized correlation filter in trackingIEEE Trans Syst Man Cybern Syst201747469370310.1109/TSMC.2016.2629509 NamWDollarPHanJHLocal decorrelation for improved pedestrian detectionAdv Neural Inf Process Syst201427424432 ZhangBPerinaALiZMurinoVLiuJJiRBounding multiple Gaussians uncertainty with application to object trackingInt J Comput Vis20161183364379351067510.1007/s11263-016-0880-y ChangCLinCLIBSVM: a library for support vector machinesACM Trans Intell Syst Technol20112312710.1145/1961189.1961199 Yang B, Yan J, Lei Z, Li SZ (2015) Convolutional channel features. In: IEEE international conference on computer vision, pp 82–90 ShenJYangWSunCReal-time human detection based on gentle MILBoost with variable granularity HOG-CSLBPNeural Comput Appl2013237–81937194810.1007/s00521-012-1153-5 Zhang S, Bauckhage C, Cremers AB (2014) Informed haar-like features improve pedestrian detection. In: IEEE conference on computer vision and pattern recognition, pp 947–954 FelzenszwalbPGirshickRMcAllesterDRamananDObject detection with discriminatively trained part based modelsIEEE Trans Pattern Anal Mach Intell20093291627164510.1109/TPAMI.2009.167 LiXShenCDickAZhangZZhuangYOnline metric-weighted linear representations for robust visual trackingIEEE Trans Pattern Anal Mach Intell201638593195010.1109/TPAMI.2015.2469276 DollárPWojekCSchieleBPeronaPPedestrian detection: an evaluation of the state of the artIEEE Trans Pattern Anal Mach Intell201234474376110.1109/TPAMI.2011.155 Gu B, Sun X, Sheng VS (2016) Structural minimax probability machine. IEEE Trans Neural Netw Learn Syst 28(7):1646–1656 Zhu Q, Yeh MC, Cheng KT, Avidan S (2006) Fast human detection using a cascade of histograms of oriented gradients. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 1491–1498 ShenJSunCYangWWangZSunZA novel distribution-based feature for rapid object detectionNeurocomputing201174172767277910.1016/j.neucom.2011.03.032 ShenJZuoXYangWYuHLiuGLearning discriminative shape statistics distribution features for pedestrian detectionNeurocomputing2016184667710.1016/j.neucom.2015.08.107 HintonGEOsinderoSTehYA fast learning algorithm for deep belief netsNeural Comput2006182006222448510.1162/neco.2006.18.7.15271106.68094 Wang X, Han T, Yan S (2009) An HOG-LBP human detector with partial occlusion handling. In: IEEE international conference on computer vision, pp 32–39 ShenJZuoXLiJYangWLingHA novel pixel neighborhood differential statistic feature for pedestrian and face detectionPattern Recogn20176312713810.1016/j.patcog.2016.09.010 Wojek C, Walk S, Schiele B (2009) Multi-cue onboard pedestrian detection. In: IEEE conference on computer vision and pattern recognition, pp 794–801 Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceeding of IEEE conference on computer vision and pattern recognition, vol 1, pp 886–893 WangLZhangBHanJShenLQianCRobust object representation by boosting-like deep learning architectureSig Process Image Commun20164749049910.1016/j.image.2016.06.002 Yang Y, Wang Z, Wu F (2015) Exploring prior knowledge for pedestrian detection. In: Proceedings of the British machine vision conference, pp 176.1–176.12 Zhang S, Benenson R, Schiele B (2015) Filtered channel features for pedestrian detection. In: IEEE conference on computer vision and pattern recognition, pp 1751–1760 Zhang L, Lin L, Liang X, He K (2016) Is faster R-CNN doing well for pedestrian detection? In: Proceedings of 14th european conference computer vision, pp 443–457 EssALeibeBSchindlerKvan GoolLRobust multiperson tracking from a mobile platformIEEE Trans Pattern Anal Mach Intell200931101831184610.1109/TPAMI.2009.109 Chen C, Seff A, Kornhauser A, Xiao J (2015) DeepDriving: learning affordance for direct perception in autonomous driving. In: IEEE international conference on computer vision (ICCV), pp 2722–2730 BilalMKhanAKhanMUKKyungCMA low complexity pedestrian detection framework for smart video surveillance systemsIEEE Trans Circuits Syst Video Technol20169911 LiXHuWShenCZhangZDickAHengelAVDA survey of appearance models in visual object trackingACM Trans Intell Syst Technol20134414810.1145/2508037.2508039 Angelova A, Krizhevsky A, Vanhoucke V, Ogale A, Fergusonn D (2015) Real-time pedestrian detection with deep network cascades. In: British machine vision conference, vol 32, pp 1–12 PaisitkriangkraiSShenCHengelAVDPedestrian detection with spatially pooled features and structured ensemble learningIEEE Trans Pattern Anal Mach Intell20163861243125710.1109/TPAMI.2015.2474388 DollárPAppelRBelongieSPeronaPFast feature pyramids for object detectionIEEE Trans Pattern Anal Mach Intell20143681532154510.1109/TPAMI.2014.2300479 Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28(2):337–407 B Zhang (9746_CR3) 2017; 47 B Sheng (9746_CR12) 2017; 249 W Nam (9746_CR20) 2014; 27 9746_CR21 9746_CR22 9746_CR25 9746_CR26 9746_CR28 S Paisitkriangkrai (9746_CR33) 2016; 38 C Chang (9746_CR13) 2011; 2 B Zhang (9746_CR4) 2016; 118 J Shen (9746_CR35) 2011; 74 L Wang (9746_CR11) 2016; 47 J Shen (9746_CR24) 2017; 63 P Dollár (9746_CR29) 2012; 34 P Dollár (9746_CR10) 2014; 36 X Li (9746_CR6) 2013; 4 J Shen (9746_CR19) 2013; 23 9746_CR32 9746_CR31 9746_CR34 9746_CR8 9746_CR9 9746_CR16 GE Hinton (9746_CR27) 2006; 18 X Li (9746_CR5) 2016; 38 9746_CR15 X Wen (9746_CR7) 2015; 295 B Gu (9746_CR14) 2016; 99 9746_CR18 9746_CR1 A Ess (9746_CR30) 2009; 31 P Felzenszwalb (9746_CR17) 2009; 32 M Bilal (9746_CR2) 2016; 99 J Shen (9746_CR23) 2016; 184 |
| References_xml | – reference: Wang X, Han T, Yan S (2009) An HOG-LBP human detector with partial occlusion handling. In: IEEE international conference on computer vision, pp 32–39 – reference: Zhang L, Lin L, Liang X, He K (2016) Is faster R-CNN doing well for pedestrian detection? In: Proceedings of 14th european conference computer vision, pp 443–457 – reference: ShenJSunCYangWWangZSunZA novel distribution-based feature for rapid object detectionNeurocomputing201174172767277910.1016/j.neucom.2011.03.032 – reference: Zhu Q, Yeh MC, Cheng KT, Avidan S (2006) Fast human detection using a cascade of histograms of oriented gradients. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 1491–1498 – reference: Zhang S, Benenson R, Schiele B (2015) Filtered channel features for pedestrian detection. In: IEEE conference on computer vision and pattern recognition, pp 1751–1760 – reference: ShenJZuoXYangWYuHLiuGLearning discriminative shape statistics distribution features for pedestrian detectionNeurocomputing2016184667710.1016/j.neucom.2015.08.107 – reference: NamWDollarPHanJHLocal decorrelation for improved pedestrian detectionAdv Neural Inf Process Syst201427424432 – reference: EssALeibeBSchindlerKvan GoolLRobust multiperson tracking from a mobile platformIEEE Trans Pattern Anal Mach Intell200931101831184610.1109/TPAMI.2009.109 – reference: Zhang S, Bauckhage C, Cremers AB (2014) Informed haar-like features improve pedestrian detection. In: IEEE conference on computer vision and pattern recognition, pp 947–954 – reference: ShenJZuoXLiJYangWLingHA novel pixel neighborhood differential statistic feature for pedestrian and face detectionPattern Recogn20176312713810.1016/j.patcog.2016.09.010 – reference: Wojek C, Walk S, Schiele B (2009) Multi-cue onboard pedestrian detection. In: IEEE conference on computer vision and pattern recognition, pp 794–801 – reference: ZhangBPerinaALiZMurinoVLiuJJiRBounding multiple Gaussians uncertainty with application to object trackingInt J Comput Vis20161183364379351067510.1007/s11263-016-0880-y – reference: BilalMKhanAKhanMUKKyungCMA low complexity pedestrian detection framework for smart video surveillance systemsIEEE Trans Circuits Syst Video Technol20169911 – reference: HintonGEOsinderoSTehYA fast learning algorithm for deep belief netsNeural Comput2006182006222448510.1162/neco.2006.18.7.15271106.68094 – reference: Dollar P, Tu Z, Perona P, Belongie S (2009) Integral channel features. In: British machine vision conference, vol 91, pp 1–11 – reference: WangLZhangBHanJShenLQianCRobust object representation by boosting-like deep learning architectureSig Process Image Commun20164749049910.1016/j.image.2016.06.002 – reference: GuBShengVSA robust regularization path algorithm for v-support vector classificationIEEE Trans Neural Netw Learn Syst20169918 – reference: Angelova A, Krizhevsky A, Vanhoucke V, Ogale A, Fergusonn D (2015) Real-time pedestrian detection with deep network cascades. In: British machine vision conference, vol 32, pp 1–12 – reference: ShengBHuQLiJYangWZhangBSunCFiltered shallow-deep feature channels for pedestrian detectionNeurocomputing2017249192710.1016/j.neucom.2017.03.007 – reference: ShenJYangWSunCReal-time human detection based on gentle MILBoost with variable granularity HOG-CSLBPNeural Comput Appl2013237–81937194810.1007/s00521-012-1153-5 – reference: Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceeding of IEEE conference on computer vision and pattern recognition, vol 1, pp 886–893 – reference: ChangCLinCLIBSVM: a library for support vector machinesACM Trans Intell Syst Technol20112312710.1145/1961189.1961199 – reference: Chen C, Seff A, Kornhauser A, Xiao J (2015) DeepDriving: learning affordance for direct perception in autonomous driving. In: IEEE international conference on computer vision (ICCV), pp 2722–2730 – reference: WenXShaoLXueYFangWA rapid learning algorithm for vehicle classificationInf Sci201529539540610.1016/j.ins.2014.10.040 – reference: DollárPAppelRBelongieSPeronaPFast feature pyramids for object detectionIEEE Trans Pattern Anal Mach Intell20143681532154510.1109/TPAMI.2014.2300479 – reference: DollárPWojekCSchieleBPeronaPPedestrian detection: an evaluation of the state of the artIEEE Trans Pattern Anal Mach Intell201234474376110.1109/TPAMI.2011.155 – reference: FelzenszwalbPGirshickRMcAllesterDRamananDObject detection with discriminatively trained part based modelsIEEE Trans Pattern Anal Mach Intell20093291627164510.1109/TPAMI.2009.167 – reference: LiXShenCDickAZhangZZhuangYOnline metric-weighted linear representations for robust visual trackingIEEE Trans Pattern Anal Mach Intell201638593195010.1109/TPAMI.2015.2469276 – reference: PaisitkriangkraiSShenCHengelAVDPedestrian detection with spatially pooled features and structured ensemble learningIEEE Trans Pattern Anal Mach Intell20163861243125710.1109/TPAMI.2015.2474388 – reference: LiXHuWShenCZhangZDickAHengelAVDA survey of appearance models in visual object trackingACM Trans Intell Syst Technol20134414810.1145/2508037.2508039 – reference: Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28(2):337–407 – reference: Gu B, Sun X, Sheng VS (2016) Structural minimax probability machine. IEEE Trans Neural Netw Learn Syst 28(7):1646–1656 – reference: ZhangBLiZCaoXYeQChenCShenLPerinaAJillROutput constraint transfer for kernelized correlation filter in trackingIEEE Trans Syst Man Cybern Syst201747469370310.1109/TSMC.2016.2629509 – reference: Yang B, Yan J, Lei Z, Li SZ (2015) Convolutional channel features. In: IEEE international conference on computer vision, pp 82–90 – reference: Yang Y, Wang Z, Wu F (2015) Exploring prior knowledge for pedestrian detection. In: Proceedings of the British machine vision conference, pp 176.1–176.12 – ident: 9746_CR31 doi: 10.1109/CVPR.2009.5206638 – volume: 63 start-page: 127 year: 2017 ident: 9746_CR24 publication-title: Pattern Recogn doi: 10.1016/j.patcog.2016.09.010 – ident: 9746_CR15 doi: 10.1214/aos/1016218223 – volume: 38 start-page: 1243 issue: 6 year: 2016 ident: 9746_CR33 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2015.2474388 – volume: 32 start-page: 1627 issue: 9 year: 2009 ident: 9746_CR17 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2009.167 – ident: 9746_CR28 doi: 10.5244/C.23.91 – volume: 27 start-page: 424 year: 2014 ident: 9746_CR20 publication-title: Adv Neural Inf Process Syst – ident: 9746_CR34 doi: 10.5244/C.29.176 – ident: 9746_CR22 doi: 10.1109/CVPR.2015.7298784 – volume: 4 start-page: 1 issue: 4 year: 2013 ident: 9746_CR6 publication-title: ACM Trans Intell Syst Technol doi: 10.1145/2508037.2508039 – volume: 249 start-page: 19 year: 2017 ident: 9746_CR12 publication-title: Neurocomputing doi: 10.1016/j.neucom.2017.03.007 – ident: 9746_CR26 doi: 10.1007/978-3-319-46475-6_28 – volume: 36 start-page: 1532 issue: 8 year: 2014 ident: 9746_CR10 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2014.2300479 – volume: 47 start-page: 490 year: 2016 ident: 9746_CR11 publication-title: Sig Process Image Commun doi: 10.1016/j.image.2016.06.002 – ident: 9746_CR18 – ident: 9746_CR16 – volume: 2 start-page: 1 issue: 3 year: 2011 ident: 9746_CR13 publication-title: ACM Trans Intell Syst Technol doi: 10.1145/1961189.1961199 – volume: 23 start-page: 1937 issue: 7–8 year: 2013 ident: 9746_CR19 publication-title: Neural Comput Appl doi: 10.1007/s00521-012-1153-5 – volume: 38 start-page: 931 issue: 5 year: 2016 ident: 9746_CR5 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2015.2469276 – ident: 9746_CR32 doi: 10.5244/C.29.32 – volume: 184 start-page: 66 year: 2016 ident: 9746_CR23 publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.08.107 – volume: 18 start-page: 2006 year: 2006 ident: 9746_CR27 publication-title: Neural Comput doi: 10.1162/neco.2006.18.7.1527 – ident: 9746_CR25 doi: 10.1109/ICCV.2015.18 – volume: 99 start-page: 1 year: 2016 ident: 9746_CR14 publication-title: IEEE Trans Neural Netw Learn Syst – volume: 31 start-page: 1831 issue: 10 year: 2009 ident: 9746_CR30 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2009.109 – volume: 34 start-page: 743 issue: 4 year: 2012 ident: 9746_CR29 publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2011.155 – ident: 9746_CR8 doi: 10.1109/CVPR.2005.177 – volume: 295 start-page: 395 year: 2015 ident: 9746_CR7 publication-title: Inf Sci doi: 10.1016/j.ins.2014.10.040 – volume: 99 start-page: 1 year: 2016 ident: 9746_CR2 publication-title: IEEE Trans Circuits Syst Video Technol – volume: 47 start-page: 693 issue: 4 year: 2017 ident: 9746_CR3 publication-title: IEEE Trans Syst Man Cybern Syst doi: 10.1109/TSMC.2016.2629509 – ident: 9746_CR21 doi: 10.1109/CVPR.2014.126 – volume: 118 start-page: 364 issue: 3 year: 2016 ident: 9746_CR4 publication-title: Int J Comput Vis doi: 10.1007/s11263-016-0880-y – ident: 9746_CR9 doi: 10.1109/ICCV.2009.5459207 – volume: 74 start-page: 2767 issue: 17 year: 2011 ident: 9746_CR35 publication-title: Neurocomputing doi: 10.1016/j.neucom.2011.03.032 – ident: 9746_CR1 doi: 10.1109/ICCV.2015.312 |
| SSID | ssj0010020 |
| Score | 2.1455681 |
| Snippet | Following the recent progress of the pixel-level filtering for pedestrian detection, we propose a window differential feature (WDF) based on the multiple... |
| SourceID | proquest crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 403 |
| SubjectTerms | Accuracy Artificial Intelligence Complex Systems Computational Intelligence Computer Science Deep learning Feature selection Filtration Pixels Random variables Reduction |
| SummonAdditionalLinks | – databaseName: SpringerLink Journals (ICM) dbid: U2A link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8QwEA26Xrz4La6ukoMnJdCvpOlxdS2Logi6uLeSdBIQpCtuxb_vJNtuUVTwVmiawySZ96YzmUfIqS2zyIaJZVIEJUtsxJlClsF4xsFIi6DtxWBu78R4klxP-bS5xz1vq93blKT31N1lN4xeXO1PypADCyZXyRrH0N3VcU2i4TJ14AiQj7LSgCUiCttU5k9TfAWjjmF-S4p6rMm3yEZDEulwsarbZMVUO2SzFWCgzXncJTe5mtf03oDx6hsVHZnal1ZV9ALRCSg-IMGjD17sBv0afcIQfPZBR40sCh7vF5o_u4z5HpnkV4-XY9aoI7AyDkXNFJSq5BloNK0EDsqGZazcv0GVgEQgtly5doJRDNoGEEAqM66sMhoxW4Uq3ie9alaZA0K1CECDlEmYiiTNRCZB2Fi7zvNagIz6JGjNVJRN63CnYPFSdE2PnWULtGzhLFvIPjlbfvK66Jvx1-BBa_uiOULzIsrQ23iP0ifn7Xp0r3-d7PBfo4_IOlIguSjpG5Be_fZujpFm1PrEb6tPGuTHrQ priority: 102 providerName: Springer Nature |
| Title | Fast Pedestrian Detection Based on the Selective Window Differential Filter |
| URI | https://link.springer.com/article/10.1007/s11063-017-9746-8 https://www.proquest.com/docview/2918342578 |
| Volume | 48 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB60vXjxLVZr2YMnZTHPzeYkrW0URRG1qKewyWZBKGm1Ef--s9uNQcHeQh57mNmd-eaR-QCOVR57yg0U5czJaaC8kApEGTSMQ1lwhU7bkMHc3rGrcXD9Er7YhNvctlXWNtEYajnNdY78zItx85kNdj57p5o1SldXLYXGKrTRBHPegvZgdHf_8FNH0GjIhFyRQwPmuXVd0_w8h9GQ7iWKKGJqRvlvz9TAzT8VUuN4kk1Yt4iR9Bcq3oKVotyGjZqNgdjDuQM3iZhX5L6QhaHiKMmwqEyfVUkG6KokwQtEe-TRMN-gkSPPGI9Pv8jQcqTgWZ-Q5E2Xz3dhnIyeLq6opUqgue-yigqZizyMZYZy5jKUQrm5L3SiUASSo1dWodCzBT1fZsqRjox4HAoligwduHCFvwetcloW-0Ay5shMch64EQuimMVcMuVnegx9xiT3OuDUYkpzO0dc01lM0mYCspZsipJNtWRT3oGTn09miyEay17u1rJP7Xmap432O3Ba66N5_O9iB8sXO4Q1BEB80dDXhVb18VkcIciosh6s8uSyB-3-5evNqGf3Fd4de_1v9-TP6w |
| linkProvider | ProQuest |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LS8QwEB58HPTiW1xdNQe9KME-0_Qgoq51dVUEFb3VtElAWLrqVhb_lL_RSbZ1UdCbt0LbUCbTmW8yjw9gS-exp91AU86cnAbaC6lAlEHDOJSKa3Talgzm8oq174Lzh_BhDD7qXhhTVlnbRGuoZS83Z-R7XozKZxXs4PmFGtYok12tKTSGatFR7wMM2fr7Zy3c323PS05uj9u0YhWgue-ykgqZizyMZYafxGUohXZzX5gzNRFIjg5Mh8KM4fN8mWlHOjLicSi0UBn6OuEKH9cdh8nAR09uOtOT06-shcFeNsCLHBowz62zqLZVD2MvU7kUUUTwjPLvfnAEbn_kY62bS-ZgpsKn5HCoUPMwpooFmK25H0hlChahk4h-Sa6VVJb4oyAtVdqqroIcoWOUBC8QW5Iby7ODJpXcY_TfG5BWxciClqVLkieTrF-Cu38R4TJMFL1CrQDJmCMzyXngRiyIYhZzybSfmaH3GZPca4BTiynNq6nlhjyjm47mLRvJpijZ1Eg25Q3Y-XrleTiy46-Hm7Xs0-rv7acjXWvAbr0fo9u_Lrb692KbMNW-vbxIL86uOmswjdCLD0sJmzBRvr6pdYQ3ZbZhdYrA438r8SexlAmb |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LS8QwEB58gHjxLa7PHPSiBNu0TdODB3Ut6qoIuuitpk0CwlLFrYi_yr_oJNu6KCp48FZoGsIkmfmm8_gANk2RMOOHhgruFTQ0LKISUQaNkkhpYdBoOzKY8wt-3A1Pb6PbEXhramFctnsTkhzUNNguTWW1-6jM7rDwDT0ZmwcUU8TDnIo6q7KjX1_QZ-vvnbRxg7cYS4-uD49pTStAi8DnFZWqkEWUqBzXJFSkpPGLQNqfajJUAi2YiaTtw8cClRtPeSoWSSSN1DkaO-nLAOcdhfHQFh_jBeqy_Y-whQVfzsOLPRpy5jdh1O-W_NkQDtHtl4Css3PpDEzVAJXsD07ULIzocg6mG_IHUuuCeeiksl-RS620Y_4oSVtXLq2rJAdoGRXBBwSX5MoR7aBOJTfo_j-8kHZNyYKqpUfSexutX4Duv4hwEcbKh1IvAcm5p3IlROjHPIwTngjFTZDbrvc5V4K1wGvElBV123LLntHLhg2XrWQzlGxmJZuJFmx_fPI46Nnx2-DVRvZZfX37GUtQ0zlt1oKdZj-Gr3-cbPlPozdg4rKdZmcnF50VmEQkJgaZhaswVj096zVEO1W-7k4Ygbv_PtLvYbcKeA |
| 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=Fast+Pedestrian+Detection+Based+on+the+Selective+Window+Differential+Filter&rft.jtitle=Neural+processing+letters&rft.date=2018-08-01&rft.pub=Springer+Nature+B.V&rft.issn=1370-4621&rft.eissn=1573-773X&rft.volume=48&rft.issue=1&rft.spage=403&rft.epage=417&rft_id=info:doi/10.1007%2Fs11063-017-9746-8 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1370-4621&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1370-4621&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1370-4621&client=summon |