基于混合高斯和HOG+SVM的行人检测模型

doi:10.12066/j.issn.1007-2861.1849

上海大学学报(自然科学版) ›› 2018, Vol. 24 ›› Issue (3): 341-351.doi: 10.12066/j.issn.1007-2861.1849

基于混合高斯和HOG+SVM的行人检测模型

龚露鸣¹, 徐美华¹^,²(), 刘冬军², 张发宇¹

1.上海大学微电子研究与开发中心, 上海 200072
2.上海大学机电工程与自动化学院, 上海 200444

收稿日期:2016-09-28 出版日期:2018-06-15 发布日期:2018-06-27
通讯作者: 徐美华 E-mail:mhxu@shu.edu.cn
基金资助:
国家自然科学基金资助项目(61376028)

Novel model of pedestrian detection based on Gaussian mixture model and HOG+SVM

GONG Luming¹, XU Meihua¹^,²(), LIU Dongjun², ZHANG Fayu¹

1. Microelectronic R&D Center, Shanghai University, Shanghai 200072, China
2. School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China

Received:2016-09-28 Online:2018-06-15 Published:2018-06-27
Contact: XU Meihua E-mail:mhxu@shu.edu.cn

摘要/Abstract

摘要：

为了提高行人检测系统的检测率,提出了一种基于混合高斯背景建模结合方向梯度直方图(histogram of oriented gradient, HOG)+支持向量机(support vector machine, SVM)的行人检测模型. 首先, 采用混合高斯模型进行前景分割,有效提取出运动目标区域; 然后,在行人识别部分通过缩小检测窗口尺寸来降低HOG特征维数; 另外,利用误识别区域, 对样本库的信息进行二次更新, 以优化SVM分类器; 最后,以随机视频帧为测试样本进行模型性能验证. 结果表明,在保证检测率和检测速率的情况下,该混合高斯结合HOG+SVM模型的误检率仅为4 %,说明该模型能够在复杂场景下实时准确地进行行人检测.

关键词: 行人检测, 混合高斯模型, 区域提取, 梯度方向直方图, 降维

Abstract:

To improve detection rate of pedestrian detection system, a novel pedestrian detection model by combining the Gaussian mixture background model and histograms of oriented gradients (HOG) plus support vector machine (SVM) is proposed. First, foreground segmentation is done using the Gaussian mixture model (GMM) to extract moving target areas. In the recognition of pedestrians, the dimension of the HOG descriptor is reduced by resizing the size of the detecting window. In addition, an error recognition region is used to re-update the information of sample dataset to optimize the SVM classifier. Performance of this model is evaluated with the test frames randomly chosen from a video taken in a realistic scene. The results indicate that GMM and HOG+SVM can ensure accuracy and speed of detection, and limit false detection rate to 4 %. Real-time and accurate pedestrian detection in complex scenes are achieved.

Key words: pedestrian detection, Gaussian mixture model (GMM), region extraction, histogram of oriented gradient (HOG), dimension reduction

中图分类号:

TP312

龚露鸣, 徐美华, 刘冬军, 张发宇. 基于混合高斯和HOG+SVM的行人检测模型[J]. 上海大学学报(自然科学版), 2018, 24(3): 341-351.

GONG Luming, XU Meihua, LIU Dongjun, ZHANG Fayu. Novel model of pedestrian detection based on Gaussian mixture model and HOG+SVM[J]. Journal of Shanghai University（Natural Science Edition）, 2018, 24(3): 341-351.

图/表 15

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

表1

图14

参考文献 15

[1]	许腾, 黄铁军, 田永鸿. 车载视觉系统中的行人检测技术综述[J]. 中国图象图形学报, 2013,18(4):359-367. doi: 10.11834/jig.20130401
[2]	Sun D, Roth S, Black M J. Secrets of optical flow estimation and their principles [C]// 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2010: 2432-2439.
[3]	张正鹏, 江万寿, 张靖. 光流特征聚类的车载全景序列影像匹配方法[J]. 测绘学报, 2014,43(12):1266-1273.
[4]	杨亚东. 光流法在运动目标识别领域的理论与应用[J]. 电子设计工程, 2013,21(5):24-26.
[5]	严晓明. 一种基于改进帧差法的运动目标检测[J]. 莆田学院学报, 2011,18(5):69-72.
[6]	杨恒, 王超, 姜文涛, 等. 基于随机背景建模的目标检测算法[J]. 应用光学, 2015,36(6):880-887.
[7]	黄大卫, 胡文翔, 吴小培, 等. 改进单高斯模型的视频前景提取与破碎目标合并算法[J]. 信号处理, 2015,31(3):299-307.
[8]	Bouwmans T, El Baf F, Vachon B. Background modeling using mixture of Gaussians for foreground detection: a survey[J]. Recent Patents on Computer Science, 2008,1(3):219-237.
[9]	Stauffer C, Grimson W E L. Adaptive background mixture models for real-time tracking [C]// 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 1999: 2.
[10]	Dalal N, Triggs B. Histograms of oriented gradients for human detection [C]// 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2005: 886-893.
[11]	徐超, 高梦珠, 查宇锋, 等. 基于HOG和SVM的公交乘客人流量统计算法[J]. 仪器仪表学报, 2015,36(2):446-452.
[12]	Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995,20(3):273-297.
[13]	郭明玮, 赵宇宙, 项俊平, 等. 基于支持向量机的目标检测算法综述[J]. 控制与决策, 2014,29(2):193-200.
[14]	溪海燕, 肖志涛, 张芳. 基于线性SVM的车辆前方行人检测方法[J]. 天津工业大学学报, 2012,31(1):69-73.
[15]	田仙仙, 鲍泓, 徐成. 一种改进HOG特征的行人检测算法[J]. 计算机科学, 2014,41(9):320-324.

基于混合高斯和HOG+SVM的行人检测模型

Novel model of pedestrian detection based on Gaussian mixture model and HOG+SVM

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 15

相关文章 1

编辑推荐

Metrics

本文评价