期刊文献+

基于无监督学习的行人检测算法 被引量:2

下载PDF
导出
摘要 提出了一种基于无监督学习的行人检测方法,用以解决学习样本未标记的问题。将深度学习应用于行人识别,数据增强用来生成额外的训练数据而无需对训练样本进行标记。利用无监督卷积稀疏自动编码器进行前期训练获得特征,在此基础上,利用端对端监督训练对分类器进行训练,同时对获得的特征进行微调得到最终的行人特征。INRIA数据集中的实验结果表明,无监督学习获得的特征提高了检测率,证明本文方法的可行性和有效性。
出处 《广东通信技术》 2015年第2期43-48,共6页 Guangdong Communication Technology
  • 相关文献

参考文献9

  • 1苏松志,李绍滋,陈淑媛,蔡国榕,吴云东.行人检测技术综述[J].电子学报,2012,40(4):814-820. 被引量:159
  • 2李斌,史忠科.基于计算机视觉的行人检测技术的发展[J].计算机工程与设计,2005,26(10):2565-2568. 被引量:16
  • 3Enzweiler M, Gavrila D M. Monocular pedestrian detection: Survey and experiments[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2009, 31 (12): 2179- 2195.
  • 4Vzquez D, L6pez A M, Ponsa D. Unsupervised domain adaptation of virtual and real worlds for pedestrian detection[C]//Pattern Recognition (ICPR), 2012 21st International Conference on. IEEE, 2012: 3492-3495.
  • 5Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
  • 6Kavukcuoglu K, Sermanet P, Boureau Y L, et al. Learning convolutional feature hierarchies for visual recognition[C]// Advances in neural information processing systems. 2010: 1090-1098.
  • 7Lee H, Battle A, Raina R, et al. Efficient sparse coding algorithms[C]//Advances in neural information processing systems. 2006: 801-808.
  • 8Beck A, Teboulle M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems[J]. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202.
  • 9Lee H, Grosse R, Ranganath R, et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations[C]//Proceedings of the 26th Annual International Conference on Machine Learning. ACM. 2009: 609-616.

二级参考文献82

  • 1贾慧星,章毓晋.车辆辅助驾驶系统中基于计算机视觉的行人检测研究综述[J].自动化学报,2007,33(1):84-90. 被引量:69
  • 2杜友田,陈峰,徐文立,李永彬.基于视觉的人的运动识别综述[J].电子学报,2007,35(1):84-90. 被引量:79
  • 3Geronimo D, Lopez A, Sappa A, et al. Survey of pedestrian de- tection for advanced driver assistance systems[ J]. IEEE, Trans. on Pattern Analysis and Machine Intelligence, 2010, 32 ( 7 ) : 1239- 1258.
  • 4Dollfr P,Wojek C,Schiele B,et al. Pedestrian detection:an e- valuation of the state of the art.IEEE, Trans. on Pattern Analysis and Machine InteUigence,2011,99:1 - 20.
  • 5Aggarwal J, Ryoo M. Human activity analysis: a review[J]. ACM Computing Surveys,2011,43(3),16:1-47.
  • 6Reilly V, Solmaz B, and Shah M. Geometric constraints for hu- man detection in aerial hnagery[ A] .In Proc. ECCV[C] ,2010.
  • 7Andfiluka M, Schnitzspan P, Meyer J, et al. Vision based victim detection from unmanned aerial vehicles [ A ]. In Proc. IEEE/ RSJ International Conference on Intelligent Robots and Systems (IROS) [ C]. Talpei, Taiwan, 2010.
  • 8Dollar P, Belongie S, Pemna P. The fastest pedeslrian detector in the west[A]. In Proc. BMVC[C] ,2010.
  • 9Enzweiler M, Gavrila D. Monocular pedestrian detection: sur- vey and experiments[ J]. IEEE, Trans. on Pattern Analysis and Machine Intelligence, 2009,31 (12) :2179 - 2195.
  • 10Dalai N, Tdggs B. I-listograms of oriented gradients for human detection[ A]. In Proc. 1EEE CVPR[ C], 2005,886 - 893.

共引文献173

同被引文献12

引证文献2

二级引证文献13

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