期刊文献+

行人检测分类器的研究与设计 被引量:1

Research and Design for Pedestrian Detection Classifier
下载PDF
导出
摘要 行人检测的重点在于分类器的设计,分类器的性能直接决定了行人检测的精度。选定样本特征和分类器类型之后,设计的关键就在于建立合适的行人和非行人样本库。因此,建立样本库并训练形成分类器是非常重要的工作。自建行人样本库,提取样本的梯度向量直方图特征,利用支持向量机获得行人分类器,并对分类器的性能进行测试。 The key of the pedestrian detection is the design of the classifier,which directly determines the accuracy of pedestrian detection.After the characteristics of samples and the type of classifier are chosen,the key of design is to establish proper pedestri an and non-pedestrian sample library.Therefore,the establishment of sample library and the training for classifier are important works.Pedestrian sample library was built and the Histogram of Oriented Gradient feature of the samples was extracted.The pe destrian classifier was obtained using support vector machine,and the performance of the classifier was tested.
出处 《电脑知识与技术(过刊)》 2012年第10X期7068-7072,共5页 Computer Knowledge and Technology
基金 天津工业大学大学生创新性实验计划项目(10051)资助
关键词 行人检测 梯度向量直方图 支持向量机 pedestrian detection histogram of oriented gradients support vector machine
  • 相关文献

参考文献7

二级参考文献78

  • 1郑长江,王炜,陈淑燕.行人过街信号与交叉口信号的协调控制[J].交通运输工程学报,2004,4(4):106-109. 被引量:21
  • 2刘广萍,裴玉龙.信号控制下交叉口延误计算方法研究[J].中国公路学报,2005,18(1):104-108. 被引量:53
  • 3王建军,王军锋,毕明涛.区域公路交通事故及高速公路交通事故特征[J].长安大学学报(自然科学版),2005,25(3):66-69. 被引量:41
  • 4黄文忠,杨佩昆.无控制人行横道处的行人和机动车延误分析[J].同济大学学报(自然科学版),1995,23(1):31-36. 被引量:37
  • 5Surendra G,Osama M,Robert F, et al. Detection and classification of vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2002,3(1) : 37- 47.
  • 6Osama M,Nikolaos P P. A novel method for tracking and counting pedestrians in real-time using a single camera[J],IEEE Transactions on Vehicles Technology, 2001, 50 (5):1 267-1 278.
  • 7Zhao L,Thorpe C. Stereo and neural network-based pedestrian detection[J]. IEEE Transactions on Intelligent Transportation Systems,2000,S(1) : 148-154.
  • 8Pai C; J,Tyan H R.Liang Y M. Pedestrian detection and tracking at crossroads[J ]. Pattern Recognition, 2004,37 ( 5 )1 025- 1 034.
  • 9Cristovbal C,Johann E, Thomas K. Walking pedestrian recognition[J]. IEEE Transactions on Intelligent Transportation Systems,2000,3(1) :155-163.
  • 10WU B. Detection of Multiple Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors[C]//IEEE International Conference on Computer Vision, 2005, 90-97.

共引文献97

同被引文献1

引证文献1

二级引证文献1

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