文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > IT/计算机 > Online Learning Asymmetric Boosted Classifiers for Object Detection
侵权投诉

Online Learning Asymmetric Boosted Classifiers for Object Detection

研究boosting必看

In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Minneapolis, MN, 2007

OnlineLearningAsymmetricBoostedClassi ersforObjectDetection

Minh-TriPham

Tat-JenCham

SchoolofComputerEngineeringNanyangTechnologicalUniversity

Singapore{mtpham,astjcham}@ntu.edu.sg

Abstract

Wepresentanintegratedframeworkforlearningasym-metricboostedclassi ersandonlinelearningtoaddresstheproblemofonlinelearningasymmetricboostedclassi ers,whichisapplicabletoobjectdetectionproblems.Inpar-ticular,ourmethodseekstobalancetheskewnessofthelabelspresentedtotheweakclassi ers,allowingthemtobetrainedmoreequally.Inonlinelearning,weintroduceanextraconstraintwhenpropagatingtheweightsofthedatapointsfromoneweakclassifertoanother,allowingthealgorithmtoconvergefaster.IncomparedwiththeOn-lineBoostingalgorithmrecentlyappliedtoobjectdetectionproblems,weobservedabout0-10%increaseinaccuracy,andabout5-30%gaininlearningspeed.

However,inthetasksofobjectdetectionandrecogni-tion(e.g.,facedetectionordatabaseretrieval),oneoftenfaceswithabinaryclassi cationproblemwheretheproba-bilityofobservingthepositiveexamples(i.e.thetargetob-ject)ismuchlowerthantheprobabilityofobservingthenegativeexamples(e.g.background,non-targetobject).Insuchdomains,anasymmetricclassi erthatcanavoidthedangerofmissingpositivepatternsisoftenmoredesirablethantheoneminimizingtheclassi cationerror.Andthen,highdetectionratescanbeachievedbycascadingtheclas-si ers(e.g.[15,16])orhierarchicallyorganizingthem(e.g.[8,10])fromcoarseto ne.

Therehavebeenworksaddressingtheproblemoflearn-ingasymmetricclassi ers[1,7,11,16].Thoughbeingdif-feredindetails,thecommonapproachofthesemethodsistosetupanasymmetricexpectedlosswherefalsenegativesarepenalizedmorethanfalsepositives.ViolaandJones[16]introducedanasymmetricloss:falsenegativescostsktimesmorethanfalsepositives.Theyappliedanasym-metricre-weightingtechniquebeforetrainingeachweakclassi ersothattheresultisequivalenttominimizingtheirasymmetricloss.MaandDing[11]appliedcost-sensitivelearningtechnique[1]tofacedetectionwithre-weightingschemesimilartothatofViolaandJones[16].However,theweight-updatingrule[1]involvesaparametercwhichisapplication-dependentandneedsextensivetrialsforbestperformance.Houetal.[7]proposedaninterestingadap-tivetechniqueavoidingtheneedforapplication-dependentparameters,buttheirmethodrequiresre-trainingtheweakclassi ersmultipletimesto ne-tunetheirasymmetricpa-rameterat.Toourbestknowledge,theirmethodcouldnotbedoneonline.

Inthispaper,weintroduceanovelboostingalgorithmwhichaddressestheproblemoflearningonlineanasym-metricboostedclassi er.Theideaoflearningonlineissim-ilartotheOnlineBoostingalgorithm[12]havingbeenbeenrecentlyused[5,9,13],butwithafasterconvergencespeed.Ontheaspectoflearningasymmetrically,ourmethodis

1.Introduction

AdaBoost[3,14]hasbeensuccessfullyusedinmanymachinelearningandpatternrecognitiontasksincom-putervision.Itsunderlyingideaistocombineanensem-bleofMweaklearnerstoproducethe nalclassi erwithveryhighaccuracy.Inthetasksofobjectdetectionandrecognition,especiallyforfacedetection,impressiveresults[8,10,15,16]havebeenreportedwhencascadingorhier-archicallyorganizingsuchboostedclassi ersfromcoarseto ne,achievinga nalclassi erwithhighdetectionratesandfastdetectionspeed.

Recently,therehasbeenconsiderableinterestinapply-ingboostingtechniquesoncomputervisionproblemsthatrequireonlinelearning.Examplesare:onlineselectionofdiscriminativefeaturesofGrabnerandBischof[5],onlineconservativelearningofRothetal.[13],andonlineco-trainingofJavedetal.[9].Thesemethodsusethesameun-derlyingOnlineBoostingalgorithmproposedbyOza[12]tolearnonline.Thealgorithmminimizestheclassi cationerrorwhileupdatingtheweakclassi ersonline.

第1页

你可能喜欢

热门文档

相关文档

  • 综述-级联AdaBoost

    提出一种新的策略在 false positive 和检测率中取得平衡 Learning Boosted Asymmetric Classifiers for Object Detection Proceedings of the 2006 IEEE Computer Society...

  • ...Boosted Classifiers for Rapid Object Detection

    Rapid object detection u... 8页 免费 Online Learning Asymmetr... 8页 ... Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid ...

  • Rapid_Object_Detection_using_a_Boosted_Cascade_of

    ? A machine learning approach for visual object detection ? ? Capable of ...A combining classifiers method ? cascade classifiers Discard the background ...

  • 分类器算法

    SCHAPIRE 和 YORAM SINGER,于 Machine Learning 发表论文: Improved Boosting ...Detection Cascades of Boosted Classifiers for Rapid Object Detection 中提出在 ...

  • Rapid_Object_Detection(AdaBoost)

    Rapid Object Detection using a Boosted Cascade of...? ? A machine learning algorithm Perform ...Classifiers Weight (α) ffinal(x) = α final,...

  • 数字图像的增强方法研究

    Modeling, Learning, Computing, and Sampling, Vancouver, Canada, July 13, ... of detection cascades of boosted classifiers for rapid object detection. ...

  • 基于OpenCV人脸检测算法在嵌入式系统上的实现

    Modeling, Learning, Computing, and Sampling, Vancouver, Canada, July 13, ... of detection cascades of boosted classifiers for rapid object detection. ...

  • opencv_objectdetection_2007june10

    too. See "Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection" technical report by R.Lienhart et al for empirical ...

  • adaboost的一些说明

    SCHAPIRE 和 YORAM SINGER,于 Machine Learning 发表论文: Improved Boosting ... of Detection Cascades of Boosted Classifiers for Rapid Object Detection. ...

  • OpenCV_FaceDetection_June10

    too. See “Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection” technical report by R.Lienhart et al for empirical ...

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email