期刊文献+

基于随机森林的层次行人检测算法 被引量:11

Random forests for hierarchical pedestrian detection
在线阅读 下载PDF
导出
摘要 针对视频和图像中快速、准确的行人检测问题,提出了一种分层次的、全局信息和局部信息相结合的行人检测算法。该方法以随机森林分类器为基础,利用图像金字塔模型融合行人的多层信息。首先,在低尺度空间利用主方向模板(DOT)特征和随机森林算法训练行人的全局分类器,第一层检测在低尺度空间中进行,找到行人的候选区域;然后,在高尺度空间提取图像块集合,基于部件随机森林训练行人的局部外观和几何约束模型;最后,基于上层的候选区域,在高尺度空间利用霍夫投票进行第二层精确检测。实验结果表明,该方法有更低的时间复杂度,并提升了行人检测的准确率,全局信息和局部信息的层次融合,能有效解决快速、准确的行人检测问题。 For detecting pedestrians in video and image fast and accurately, this paper proposed a hierarchical method for pedestrian detection, which could combine holistie information and local information. The method was based on random forests and used image pyramid for multi-layer information fusion. Firstly, it trained a holistic random forest classifier with dominant orientation templates (DOT) at the first low spatial resolution layer. And it could be used for detecting candidate areas for pedestrian. Secondly,it extracted image patches with offset vectors to learn the appearance model and geometric constraint with part-based random forest at the second high spatial resolution layer. Finally, it detected pedestrian accurately in candidate areas at the second layer by Hough voting. According to the theory analysis and experimental results, the method obtains lower computation complexity and higher precisions than previous works. Multi-layer information fusion can effectively solve the problem of fast and accurate pedestrian detection.
出处 《计算机应用研究》 CSCD 北大核心 2015年第7期2196-2199,共4页 Application Research of Computers
基金 河南省科技厅科技攻关项目(142102210010) 河南省教育厅重大专项资助项目(14A520028 14A520052)
关键词 行人检测 随机森林 图像金字塔 主方向模板 霍夫投票 pedestrian detection random forests image pyramid dominant orientation templates(DOT) Hough voting
作者简介 向涛(1984-),男,湖北孝感人,博士研究生,主要研究方向为机器学习、图像处理、人工智能; 李涛(1979-),男(通信作者),讲师,博士,主要研究方向为机器学习、图像处理、人工智能(cvlablitao@gmail.com); 李旭冬(1988-),男,博士研究生,主要研究方向为机器学习、图像处理、人工智能; 李冬梅(1981-),女,讲师,硕士,主要研究方向为自动控制、图像处理、软件开发.
  • 相关文献

参考文献17

  • 1Dalai N, Triggs B. Histograms of oriented gradients for human detec- tion[C]//Proc of IEEE Conference on Computer Vision and Patter Recognition. 2005 : 886-893.
  • 2Wang Xiaoyu, Hart T X, Yah Shuicheng. An HOG-LBP human detec- tor with partial occlusion handling[ C]//Proc of IEEE Conference on Computer Vision. 2009:32-39.
  • 3Hinterstoisser S,Lepetit V,11ic S,et al. Dominant orientation templates for real-time detection of texture-less objects[ C ]//Proc of IEEE Con- ference on Computer Vision and Patter Recognition. 2010:2257-2264.
  • 4胡庆新,张春阳,方静.基于多特征的行人检测算法[J].计算机应用研究,2014,31(10):3161-3164. 被引量:4
  • 5洪朝群,朱建科,李娜,卜佳俊,陈纯.金字塔评分改进主方向模板匹配的实时目标检索[J].中国图象图形学报,2012,17(5):700-706. 被引量:3
  • 6Wu B, Nevatia R. Cluster boosted tree classifier for multi-view, muhi- pose object detection[ C ]//Proc of IEEE Conference on International Conference on Computer Vision. 2007 : 1-8.
  • 7Marin J, Vazquez D, Lopez A M,et al. Random forests of local experts for pedestrian detection [ C ]//Proc of International Conference on Computer Vision. 2013:2592-2599.
  • 8Felzenszwalb P F,Girshick R B, McAllester D,et al. Object detection with discriminatively trained part-based models[ J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2010,32 ( 9 ) : 1627- 1645.
  • 9Pishchulin L,Jain A,Andriluka M,et aL Articulatexl people detection and pose estimation : reshaping the future [ C ]//Proc of IEEE Confer- enee on Computer Vision and Patter Recognition. 2012 : 3178-3185.
  • 10Boursev L, Maji S, Brox T, et al. Describing people : a poselet-based approach to attribute classification[ C ]//Proc of 1EEE Conference on International Conference on Computer Vision. 20l I : 1543-1550.

二级参考文献14

  • 1LI Bo, YAO Qing-ming, WANG Kun-feng.A review on vision-based pedestrian detection in intelligent transportation systems[C]//Proc of IEEE International Conference on Networking, Sensing and Control.2012:393-398.
  • 2ZHENG Gang, CHEN You-bin.A review on vision-based pedestrian detection[C]//Proc of IEEE Global High Tech Congress on Electro-nics.2012:49-54.
  • 3DALAL N , TRIGGS B.Histograms of oriented gradients for human detection[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition.2005:886-893.
  • 4VIOLA P, JONES M.Rapid object detection using a boosted cascade of simple features[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition.2001:511-518.
  • 5SABZMEYDANI P, MORI G.Detecting pedestrians by learning shapelet features[C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition.2007:1-8.
  • 6WU Bo, NEVATIA R.Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors[C]//Proc of IEEE International Conference on Computer Vision.2005:90-97.
  • 7TUZEL O, PORIKLI F, MEER P.Region covariance:a fast descriptor for detection and classification[C]//Proc of ECCV.2006:589-600.
  • 8WANG Wei-hong, ZHANG Jian, SHEN Chun-hua.Improved human detection and classification in thermal images[C]//Proc of IEEE International Conference on Image Processing.2010:2313-2316.
  • 9KOVESI P.Image features from phase congruency[J].Computer Vision Research,1999,1(3):1-26.
  • 10OJALA T, PIETIKAINEN M, MAENPAA T.Multiresolution gray scale and rotation invariant texture classification with local binary patterns[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.

共引文献5

同被引文献57

引证文献11

二级引证文献37

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