基于自适应高斯核支持向量机的室内人体存在检测  

Human Detection Based on Support Vector Machine of Adaptive Gaussian Kernel for Indoor Application

作　　者：胡春华[1] 马旭东[1] 戴先中[1] 

机构地区：[1]东南大学自动化学院,南京210096

出　　处：《模式识别与人工智能》2007年第4期492-498,共7页Pattern Recognition and Artificial Intelligence

基　　金：国家973计划项目(No.2002CB312200);国家863计划项目(No.2004AA420110)

摘　　要：服务监控对象人体存在检测是室内移动机器人应用中定位、识别与跟踪人的基础,但室内环境的复杂多变性与视觉系统的移动给人体检测带来很大的困难,使得人体检测结果不稳定且有效性差,为此,本文提出一种基于室内移动机器人视觉系统的人体存在检测方法.首先采用多尺度小波变换检测法与边缘连接算子相结合的方法提取图片边缘特征,并提出一种形态学方法去除非目标小区域、不封闭的边缘线或孤立点,利用边缘图片的不变Hu 矩作为模式识别特征向量.然后应用自适应高斯核函数软间隔支持向量机建立两类识别分类器,并与基于不同特征建立分类器的人体存在检测法和基于不同分类方法建立分类器的人体存在检测法进行分析比较,结果表明本文算法是更稳定有效的.Human detection is fundamental for human localization, recognition, and tracking. And it is a difficult problem because of environment complexity and vision system movement. A new human detection algorithm based on mobile robot vision system is proposed to solve the problem effectively. The approach consists of the following two steps： （1）Wavelet-based multi-scale edge detection combined with edge-linked operator method is introduced to extract the edges of images. In this image a new morphology method is employed to get the object contour-closed for improvement of the correct recognition rate . And invariant Hu moments are calculated as pattern features vectors. （2）The adaptive Gaussian kernel soft margin support vector machine （C-SVM）＂ classifier is designed to distinguish human images from non-human ones. Experimental comparisons have been conducted,including adaptive Gaussian C-SVM classifiers based on different features and the classifiers with different classification methods. The results validate effectiveness and robustness of the algorithm.

关 键 词：多尺度小波 边缘检测 自适应 支持向量机(SVM) 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]