期刊文献+

一种新的无监督前景目标检测方法

A New Unsupervised Foreground Object Detection Method
下载PDF
导出
摘要 针对基于无监督特征提取的目标检测方法效率不高的问题,提出一种在无标记数据集中准确检测前景目标的方法.其基本出发点是:正确的特征聚类结果可以指导目标特征提取,同时准确提取的目标特征可以提高特征聚类的精度.该方法首先对无标记样本图像进行局部特征提取,然后根据最小化特征距离进行无监督特征聚类.将同一个聚类内的图像两两匹配,将特征匹配的重现程度作为特征权重,最后根据更新后的特征权重指导下一次迭代的特征聚类.多次迭代后同时得到聚类结果和前景目标.实验结果表明,该方法有效地提高Caltech-256数据集和Google车辆图像的检测精度.此外,针对目前绝大部分无监督目标检测方法不具备增量学习能力这一缺点,提出了增量学习方法实现,实验结果表明,增量学习方法有效地提高了计算速度. Aiming at the low accuracy of object detection methods based on unsupervised object detection, this paper proposes a foreground object detection method in unlabeled dataset. The basic idea is that correct feature clustering results can guide future object feature extraction, while the accurate foreground object features can improve the accuracy of feature clustering. The proposed method extracts local features from unlabeled images and then clusters features based on minimum feature distances. By matching pairwise images in the same cluster, feature weights are computed through feature correspondence. Finally, the updated feature weights are used to guide feature clustering in the next iteration. We simultaneously group similar images and detect foreground objects after iterations. The experimental results on Caltech-256 and Google car side images demonstrate the effectiveness of our method. Furthermore, due to the present unsupervised object detection methods lacking of incremental learning ability, we propose an incremental implementation of our method. The experimental results show the incremental learning method can improve the computation speed greatly.
出处 《计算机研究与发展》 EI CSCD 北大核心 2012年第8期1721-1729,共9页 Journal of Computer Research and Development
基金 国家自然科学基金项目(60273064) 广东省工业攻关计划基金项目(2004B10101032)
关键词 前景目标检测 无监督学习 特征聚类 增量学习 特征提取 foreground object detection unsupervised learning feature clustering incremental lear.ning feature extraction
  • 相关文献

参考文献14

  • 1Leibe B, Leonardis A, Sehiele B. Combined object categorization and segmentation with an implicit shape model /-G] //LNCS 3021 3024: Proc oE the ECCV'04 Workshop on Statistical Learning in Computer Vision. Berlin: Springer, 2006 508-524.
  • 2Galbiati J, Allende H, Becerra C. Dynamic image segmentation method using hierarchical clustering [G] // LNCS 5856: Proc oJ[ the 14th Iberoamerican Con on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Berlin.. Springer, 2009:177-184.
  • 3Lee Y J, Grauman K. Collect cut: Segmentation with top- down cues discovered in multi-object images [-C]//Proe of the IEEE Computer Society Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2009: 3185- 3192.
  • 4秦磊,高文.基于内容相关性的场景图像分类方法[J].计算机研究与发展,2009,46(7):1198-1205. 被引量:13
  • 5Bosch A, Zisserman A, Xavier M. Scene classification using a hybrid generative/discriminative approach [J. IEEE Trans on Pattern Analysis and Machine Intelligence, 2008, 30(4) 712-727.
  • 6Bosch A. Image Classification categories [D]. Catalonia, Electronics, Informatics and Girona, 2007 for large number of object Spain Department of Automation, University of.
  • 7Liu D, Chen T. Semantic-shift for unsupervised object detection EC //Proc of the IEEE Con{ on Computer Vision and Pattern Recognition Workshop. Piscataway, NJ IEEE, 2006. 16-23.
  • 8Liu D, Chen T. Unsupervised image categorization and object localization using topic models and correspondences between images -C //Proc of the 11th Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2007:1-7.
  • 9Jaechul K, Grauman K. Asymmetric region-to-image matching for comparing images with generic object categories EC] //Proc of the 23rd IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2010 2344- 2Rl.
  • 10Knopp J, Sivic J, Pajdla T. Avoiding confusing features in place recognition J-G3 //LNCS 6311: Proe of the llth European Conf on Computer Vision. Berlin : Springer, 2010 : 748-761.

二级参考文献19

  • 1Winn J.Variational message passing and its applications[D].England:University of Cambridge,2003.
  • 2Treisman A.Gelade G.A featureintcgration theory of attention[J].Cognitive Psychology.1980.12(1):97-136.
  • 3Olira A,Torralba A.Modeling the shape of the scene:A holistic representation of the spatial envelope[J].International Journal on Computer Vision,2001,42 (3):145-175.
  • 4Vogel J,Schiele B.Natural scene retrieval based on a semantic modeling step[C] //Proc of the ACM Int Conf on Image and Video Retrieval.New York:ACM,2004:207-215.
  • 5Blei D,Ng A,Jordan M.Latent Dirichlet allocation[J].Journal of Machine Learning Re,arch.2003.3 (5):993-1022.
  • 6Hofmann T.Unsupervised learning by probabilistie latent semantic analysis[J].Machine l.earning.2001,42(1):177-196.
  • 7Li Feifei,Perona P.A Bayesian hierarchical model for learning natural scene categories[C] //Proc of the IEEE Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2005:524-531.
  • 8Anna Bosch,Andrew Zisserman,Xavier Munoz.Scene classification via pLSA[C] //Proc of the European Conf on Computer Vision.Berlin:Springer,2006:517-530.
  • 9in Lei,Zeng Wei,Gap Wen,et al.Local invariant descriptor for image matching[C] //Proc of the IEEE Int Conf on Acoustics,Speech,and Signal Processing.Piscataway.NJ:IEEE,2005:1025-1028.
  • 10Sivic J,Russell B C,Eiros A A,et al.Discovering objects and their localization in images[C] //Proc of the Int Conf on Computer Vision.Washington,DC:IEEE Computer Society,2005:370-377.

共引文献12

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部