期刊文献+

基于后验多重稀疏字典的多姿态行人检测

Multi-pose Pedestrian Detection Based on Posterior Multiple Sparse Dictionaries
下载PDF
导出
摘要 为了有效检测行人,提出一种基于后验多重稀疏字典的多姿态行人检测方法。根据多个不同稀疏度字典对图像稀疏编码,构成分布直方图作为行人图像多重稀疏字典特征;统计全部正样本特征的共性信息,对单个行人样本特征加权,获得表征行人的后验多重稀疏字典特征;根据视角和行人姿态的不同利用聚类方法划分子类,且训练等权重加和方式的多姿态分类器。在多个数据集上的测试表明,所提方法的特征维数低,描述能力优,有效提高了行人检测精度。 In order to detect pedestrians effectively, a multi-pose pedestrian detection method based on posterior multiple sparse dictionaries was proposed. Through pre-learning multiple different sparse dictionaries, and sparse coding the image, statistics for each dictionary corresponds to sparse coding histogram as the pedestrian image feature descriptor. The common information of multiple sparse dictionary features of all positive samples was obtained, and the feature of a single pedestrian sample was weighted, and the features of a posteriori multiple sparse dictionary could be obtained. Then pedestrians of different poses and views were divided into subclasses with clustering algorithm. A classifier was trained for each subclass. A multi-pose-view ensemble classifier was trained to combine the output values of different subclass classifiers with an equally weighted sum rule. Experimental results on different datasets suggest that the proposed posterior feature is more than the classical sparse dictionary and other typical features. Compared with the existing methods, by combining the posterior feature and the multi-pose-view ensemble classifier, the proposed method improves the detection accuracy effectively.
作者 谷灵康 周鸣争 汪军 修宇 Gu Lingkang Zhou Mingzheng Wang Jun Xiu Yu(College of Computer and Information, Anhui Polytechnic University, Wuhu 241000, China)
出处 《系统仿真学报》 CAS CSCD 北大核心 2017年第2期326-331,共6页 Journal of System Simulation
基金 安徽省自然科学基金(KJ2015A311) 安徽省自然科学研究(TSKJ2014B11)
关键词 行人检测 稀疏字典 特征提取 后验多重稀疏 多姿态 pedestrian detection sparse dictionaries feature extraction posterior multiple sparse multi-pose
  • 相关文献

参考文献2

二级参考文献60

  • 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
  • 3GE Junfeng, LUO Yupin, TEl Gyomei. Real - time pedestrian detection and tracking at nighttime for driver - assistance systems [ J ]. IEEE Trans. Intelligent Transportation Systems,2009,10 (2) :283-298.
  • 4TOMIUC C,NEDEVSCHI S, MEINECKE M M. Pedestrian detection and classification based on 2D and 3D information for driving assistance sys- tems[ C]//Prec. IEEE International Conference on Intelligent Computer Communication and Processing. Cluj - Napeca, Romanian: IEEE Press, 2007 : 133-139.
  • 5DOLLAR P,WOJEK C,SCHIELE B,et al. Pedestrian detection: an e- valuation of the state of the art [ J ]. IEEE Trans. Pattern Analysis and Ma- chine Intelligence,2011 (9) : 1-20.
  • 6GERON1MO D, LOPEZ A M, SAPPA A D, et al. Survey of pedestrian de- tection for advanced driver assistance systems[ J ]. IEEE Trans. Pattern A- nalysis and Machine Intelligence ,2010,32 (7) : 1239-1258.
  • 7BYUN K Y,KIM B S,KIM H K,et al. An effective pedestrian detection method for driver assistance system[ C]//Proc. IEEE International Con- ference on Consumer Electronics. : Vegas, USA: IEEE Press, 2012: 229-230.
  • 8AGGARWAL J K, RYOO M S. Human activity analysis : a review [ J ]. ACM Computing Surveys,2011,43 (3) : 1-47.
  • 9KELLER C, ENZWEILER M, GAVRILA D M. A new benchmark for stereo-based pedestrian detection[ C]//Proc. IEEE Intelligent Vehicles Symposium. Baden-Baden, Germany: IEEE Press ,2011:691-696.
  • 10GERMA T,LERASLE F,OUADAH N ,et al. Vision and RFID data fu- sian for tracking people in crowds by a mobile robot [ J ]. Computer Vi- sion and Image Understanding,2010,114(6) :641-651.

共引文献41

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