计算机应用 ›› 2017, Vol. 37 ›› Issue (10): 3012-3016.DOI: 10.11772/j.issn.1001-9081.2017.10.3012

• 应用前沿、交叉与综合 • 上一篇    下一篇

结合纹理与轮廓特征的多通道行人检测算法

韩建栋, 邓一凡   

  1. 山西大学 计算机与信息技术学院, 太原 030006
  • 收稿日期:2017-04-07 修回日期:2017-07-01 出版日期:2017-10-10 发布日期:2017-10-16
  • 通讯作者: 韩建栋(1980-),男,山西文水人,讲师,博士,CCF会员,主要研究方向:计算机视觉、数据挖掘,E-mail:hanjiandong@sxu.edu.cn
  • 作者简介:韩建栋(1980-),男,山西文水人,讲师,博士,CCF会员,主要研究方向:计算机视觉、数据挖掘;邓一凡(1992-),男,内蒙古阿拉善左旗人,硕士研究生,主要研究方向:目标检测与跟踪.
  • 基金资助:
    国家自然科学基金资助项目(61602288)。

Multi-channel pedestrian detection algorithm based on textural and contour features

HAN Jiandong, DENG Yifan   

  1. School of Computer and Information Technology, Shanxi University, Taiyuan Shanxi 030006, China
  • Received:2017-04-07 Revised:2017-07-01 Online:2017-10-10 Published:2017-10-16
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61602288).

摘要: 针对在复杂场景下,聚合通道特征(ACF)的行人检测算法存在检测精度较低、误检率较高的问题,提出一种结合纹理和轮廓特征的多通道行人检测算法。算法由训练分类器和检测两部分组成。在训练阶段,首先提取ACF特征、局部二值模式(LBP)纹理特征和ST(Sketch Tokens)轮廓特征,然后对提取的三类特征均采用Real AdaBoost分类器进行训练;在检测阶段,应用了级联检测的思想,初期使用ACF分类器处理所有实例,保留下来的少数实例应用复杂的LBP及ST分类器进行逐次筛选。实验采用INRIA数据集对算法进行仿真,该算法的平均对数漏检率为13.32%,与ACF算法相比平均对数漏检率降低了3.73个百分点。实验结果表明LBP特征与ST特征能有对ACF特征进行信息互补,从而在复杂场景下去掉部分误判,提高了行人检测的精度,同时应用级联检测保证了多特征算法的计算效率。

关键词: 聚合通道特征, Sketch Tokens特征, LBP特征, Real AdaBoost分类器, 级联检测

Abstract: In order to solving the problem that the pedestrian detection algorithm based on Aggregated Channel Feature (ACF) has a low detection precision and a high false detection rate in complex scenes, a multi-channel pedestrian detection algorithm combined with features of texture and contour was proposed in this paper. The algorithm flows included training classifier and detection. In the training phase, the ACF, the texture features of Local Binary Patterns (LBP) and the contour features of Sketch Tokens (ST) were extracted, and trained separately by the Real AdaBoost classifier. In the detection phase, the cascading detection idea was used. The ACF classifier was used to deal with all objects, then the complicated classifier of LBP and ST were used to gradually filter the result of the previous step. In the experiment, the INRIA data set was used in the simulation of our algorithm, the results show that our algorithm achieves a Log-Average Miss Rate (LAMR) of 13.32%. Compared with ACF algorithm, LAMR is decreased by 3.73 percent points. The experimental results verify that LBP and ST can be used as a complementation of ACF. So some objects of false detection can be eliminated in the complicated scenes and the accuracy can be improved. At the same time, the efficiency of multi-feature algorithm is ensured by cascading detection.

Key words: Aggregated Channel Feature (ACF), sketch tokens feature, Local Binary Pattern (LBP) feature, Real AdaBoost classifier, cascading detection

中图分类号: