Measuring the objectness of image windows

We present a generic objectness measure, quantifying how likely it is for an image window to contain an object of any class. We explicitly train it to distinguish objects with a well-defined boundary in space, such as cows and telephones, from amorphous background elements, such as grass and road. T...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 34(2012), 11 vom: 08. Nov., Seite 2189-202
1. Verfasser: Alexe, Bogdan (VerfasserIn)
Weitere Verfasser: Deselaers, Thomas, Ferrari, Vittorio
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2012
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM214589846
003 DE-627
005 20231224023857.0
007 cr uuu---uuuuu
008 231224s2012 xx |||||o 00| ||eng c
028 5 2 |a pubmed24n0715.xml 
035 |a (DE-627)NLM214589846 
035 |a (NLM)22248633 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Alexe, Bogdan  |e verfasserin  |4 aut 
245 1 0 |a Measuring the objectness of image windows 
264 1 |c 2012 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 29.04.2013 
500 |a Date Revised 02.01.2013 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a We present a generic objectness measure, quantifying how likely it is for an image window to contain an object of any class. We explicitly train it to distinguish objects with a well-defined boundary in space, such as cows and telephones, from amorphous background elements, such as grass and road. The measure combines in a Bayesian framework several image cues measuring characteristics of objects, such as appearing different from their surroundings and having a closed boundary. These include an innovative cue to measure the closed boundary characteristic. In experiments on the challenging PASCAL VOC 07 dataset, we show this new cue to outperform a state-of-the-art saliency measure, and the combined objectness measure to perform better than any cue alone. We also compare to interest point operators, a HOG detector, and three recent works aiming at automatic object segmentation. Finally, we present two applications of objectness. In the first, we sample a small numberof windows according to their objectness probability and give an algorithm to employ them as location priors for modern class-specific object detectors. As we show experimentally, this greatly reduces the number of windows evaluated by the expensive class-specific model. In the second application, we use objectness as a complementary score in addition to the class-specific model, which leads to fewer false positives. As shown in several recent papers, objectness can act as a valuable focus of attention mechanism in many other applications operating on image windows, including weakly supervised learning of object categories, unsupervised pixelwise segmentation, and object tracking in video. Computing objectness is very efficient and takes only about 4 sec. per image 
650 4 |a Journal Article 
700 1 |a Deselaers, Thomas  |e verfasserin  |4 aut 
700 1 |a Ferrari, Vittorio  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 34(2012), 11 vom: 08. Nov., Seite 2189-202  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:34  |g year:2012  |g number:11  |g day:08  |g month:11  |g pages:2189-202 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 34  |j 2012  |e 11  |b 08  |c 11  |h 2189-202