Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (12): 3367-3371.DOI: 10.11772/j.issn.1001-9081.2018051066

Previous Articles     Next Articles

Zenithal pedestrian detection algorithm based on improved aggregate channel features and gray-level co-occurrence matrix

LI Lin, ZHANG Tao   

  1. Information Engineering University, Zhengzhou Henan 450001, China
  • Received:2018-05-24 Revised:2018-07-21 Online:2018-12-10 Published:2018-12-15
  • Contact: 李琳
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61572518).


李琳, 张涛   

  1. 信息工程大学, 郑州 450001
  • 通讯作者: 李琳
  • 作者简介:李琳(1994-),女,北京人,硕士研究生,主要研究方向:图像处理、模式识别;张涛(1977-),男,湖北天门人,教授,博士,主要研究方向:图像处理、模式识别、信息隐藏。
  • 基金资助:

Abstract: Aiming at the uniqueness of head feature and high detection error rate extracted by traditional zenithal pedestrian detection method, a multi-feature fusion zenithal pedestrian detection algorithm based on improved Aggregate Channel Feature (ACF) and Gray-Level Co-occurrence Matrix (GLCM) was proposed. Firstly, the extracted Hue, Sturation, Value (HSV) color features, gradient magnitude and improved Histogram of Oriented Gradients (HOG) feature were combined into ACF descriptor. Then, the improved GLCM parameter descriptor was calculated by the window method, and the texture features were extracted. The co-occurrence matrix feature descriptor was obtained by concatenating the feature vectors of each window. Finally, the aggregate channel and co-occurrence matrix features were input into Adaboost for training to get the classifier, and the final results were obtained by detection. The experimental results show that, the proposed algorithm can effectively detect targets in the presence of interference background, and improve the detection precision and recall.

Key words: zenithal pedestrian detection, Aggregate Channel Feature (ACF), Gray-Level Co-occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), Adaboost

摘要: 针对传统俯视行人检测方法提取的头部特征单一、检测错误率高的问题,提出了结合改进聚合通道特征(ACF)和灰度共生矩阵(GLCM)的俯视行人检测算法。首先,将提取到的HSV颜色特征、梯度幅值大小以及改进后的梯度方向直方图(HOG)特征组合成ACF描述子;然后,采用窗口法计算改进的GLCM参数描述子,提取纹理特征,串联每个窗口的特征向量得到共生矩阵特征描述子;最后,将聚合通道和共生矩阵特征分别输入Adaboost训练得到分类器,并进行检测得到最终结果。实验结果表明,所提算法能在干扰背景存在的情况下有效检测目标,提高了检测的准确率和召回率。

关键词: 俯视行人检测, 聚合通道特征, 灰度共生矩阵, 梯度方向直方图, Adaboost

CLC Number: