The benefits of dense stereo for pedestrian detection

This paper presents a novel pedestrian detection system for intelligent vehicles. We propose the use of dense stereo for both the generation of regions of interest and pedestrian classification. Dense stereo allows the dynamic estimation of camera parameters and the road profile, which, in turn, pro...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Keller, Christoph Gustav (VerfasserIn) , Enzweiler, Markus (VerfasserIn) , Rohrbach, Marcus (VerfasserIn) , Llorca, David Fernández (VerfasserIn) , Schnörr, Christoph (VerfasserIn) , Gavrila, Dariu M. (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 12 May 2011
In: IEEE transactions on intelligent transportation systems
Year: 2011, Jahrgang: 12, Heft: 4, Pages: 1096-1106
DOI:10.1109/TITS.2011.2143410
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1109/TITS.2011.2143410
Volltext
Verfasserangaben:Christoph G. Keller, Markus Enzweiler, Marcus Rohrbach, David Fernández Llorca, Christoph Schnorr, Dariu M. Gavrila

MARC

LEADER 00000caa a2200000 c 4500
001 1811893724
003 DE-627
005 20220820233329.0
007 cr uuu---uuuuu
008 220728s2011 xx |||||o 00| ||eng c
024 7 |a 10.1109/TITS.2011.2143410  |2 doi 
035 |a (DE-627)1811893724 
035 |a (DE-599)KXP1811893724 
035 |a (OCoLC)1341464624 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 28  |2 sdnb 
100 1 |a Keller, Christoph Gustav  |e VerfasserIn  |0 (DE-588)1064905536  |0 (DE-627)815304544  |0 (DE-576)424249782  |4 aut 
245 1 4 |a The benefits of dense stereo for pedestrian detection  |c Christoph G. Keller, Markus Enzweiler, Marcus Rohrbach, David Fernández Llorca, Christoph Schnorr, Dariu M. Gavrila 
264 1 |c 12 May 2011 
300 |a 11 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 28.07.2022 
520 |a This paper presents a novel pedestrian detection system for intelligent vehicles. We propose the use of dense stereo for both the generation of regions of interest and pedestrian classification. Dense stereo allows the dynamic estimation of camera parameters and the road profile, which, in turn, provides strong scene constraints on possible pedestrian locations. For classification, we extract spatial features (gradient orientation histograms) directly from dense depth and intensity images. Both modalities are represented in terms of individual feature spaces, in which discriminative classifiers (linear support vector machines) are learned. We refrain from the construction of a joint feature space but instead employ a fusion of depth and intensity on the classifier level. Our experiments involve challenging image data captured in complex urban environments (i.e., undulating roads and speed bumps). Our results show a performance improvement by up to a factor of 7.5 at the classification level and up to a factor of 5 at the tracking level (reduction in false alarms at constant detection rates) over a system with static scene constraints and intensity-only classification. 
650 4 |a Active safety 
650 4 |a Cameras 
650 4 |a computer vision 
650 4 |a Feature extraction 
650 4 |a intelligent vehicles 
650 4 |a Intelligent vehicles 
650 4 |a pedestrian detection 
650 4 |a Stereo vision 
650 4 |a Support vector machines 
700 1 |a Enzweiler, Markus  |e VerfasserIn  |4 aut 
700 1 |a Rohrbach, Marcus  |e VerfasserIn  |4 aut 
700 1 |a Llorca, David Fernández  |e VerfasserIn  |4 aut 
700 1 |a Schnörr, Christoph  |e VerfasserIn  |0 (DE-588)1023033348  |0 (DE-627)717351017  |0 (DE-576)168404540  |4 aut 
700 1 |a Gavrila, Dariu M.  |e VerfasserIn  |4 aut 
773 0 8 |i Enthalten in  |a Institute of Electrical and Electronics Engineers  |t IEEE transactions on intelligent transportation systems  |d New York, NY : Inst. of Electrical and Electronics Engineers, 2000  |g 12(2011), 4, Seite 1096-1106  |h Online-Ressource  |w (DE-627)325161909  |w (DE-600)2034300-0  |w (DE-576)094086257  |7 nnas 
773 1 8 |g volume:12  |g year:2011  |g number:4  |g pages:1096-1106  |g extent:11  |a The benefits of dense stereo for pedestrian detection 
856 4 0 |u https://doi.org/10.1109/TITS.2011.2143410  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20220728 
993 |a Article 
994 |a 2011 
998 |g 1023033348  |a Schnörr, Christoph  |m 1023033348:Schnörr, Christoph  |d 700000  |d 720000  |e 700000PS1023033348  |e 720000PS1023033348  |k 0/700000/  |k 1/700000/720000/  |p 5 
998 |g 1064905536  |a Keller, Christoph Gustav  |m 1064905536:Keller, Christoph Gustav  |d 110000  |e 110000PK1064905536  |k 0/110000/  |p 1  |x j 
999 |a KXP-PPN1811893724  |e 417340638X 
BIB |a Y 
SER |a journal 
JSO |a {"language":["eng"],"note":["Gesehen am 28.07.2022"],"origin":[{"dateIssuedDisp":"12 May 2011","dateIssuedKey":"2011"}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"title":[{"title_sort":"benefits of dense stereo for pedestrian detection","title":"The benefits of dense stereo for pedestrian detection"}],"person":[{"given":"Christoph Gustav","role":"aut","display":"Keller, Christoph Gustav","family":"Keller"},{"role":"aut","given":"Markus","display":"Enzweiler, Markus","family":"Enzweiler"},{"given":"Marcus","role":"aut","display":"Rohrbach, Marcus","family":"Rohrbach"},{"display":"Llorca, David Fernández","family":"Llorca","given":"David Fernández","role":"aut"},{"family":"Schnörr","display":"Schnörr, Christoph","role":"aut","given":"Christoph"},{"role":"aut","given":"Dariu M.","family":"Gavrila","display":"Gavrila, Dariu M."}],"id":{"eki":["1811893724"],"doi":["10.1109/TITS.2011.2143410"]},"relHost":[{"disp":"Institute of Electrical and Electronics EngineersIEEE transactions on intelligent transportation systems","corporate":[{"role":"aut","display":"Institute of Electrical and Electronics Engineers"}],"language":["eng"],"part":{"issue":"4","year":"2011","text":"12(2011), 4, Seite 1096-1106","pages":"1096-1106","extent":"11","volume":"12"},"note":["Gesehen am 05.10.06"],"title":[{"title":"IEEE transactions on intelligent transportation systems","title_sort":"IEEE transactions on intelligent transportation systems"}],"origin":[{"publisher":"Inst. of Electrical and Electronics Engineers","dateIssuedKey":"2000","publisherPlace":"New York, NY","dateIssuedDisp":"2000-"}],"titleAlt":[{"title":"Transactions on intelligent transportation systems"}],"type":{"media":"Online-Ressource","bibl":"periodical"},"recId":"325161909","pubHistory":["1.2000 -"],"physDesc":[{"extent":"Online-Ressource"}],"name":{"displayForm":["Intelligent Transportation Systems Council"]},"id":{"zdb":["2034300-0"],"eki":["325161909"]}}],"recId":"1811893724","physDesc":[{"extent":"11 S."}],"name":{"displayForm":["Christoph G. Keller, Markus Enzweiler, Marcus Rohrbach, David Fernández Llorca, Christoph Schnorr, Dariu M. Gavrila"]}} 
SRT |a KELLERCHRIBENEFITSOF1220