计算机工程 ›› 2009, Vol. 35 ›› Issue (6): 32-34.doi: 10.3969/j.issn.1000-3428.2009.06.011

• 博士论文 • 上一篇    下一篇

一种新的汽车乘员分类视觉检测算法

刘 杰1,2,孙吉贵1,2,高振海3,冯京津3   

  1. (1. 吉林大学计算机科学与技术学院,长春 130012;2. 吉林大学符号计算与知识工程教育部重点实验室,长春 130012;3. 吉林大学汽车动态模拟国家重点实验室,长春 130022)

  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-03-20 发布日期:2009-03-20

Automobile Occupant Classification Vision Detection Algorithm

LIU Jie1,2, SUN Ji-gui1,2, GAO Zhen-hai3, FENG Jing-jin3   

  1. (1. College of Computer Science and Technology, Jilin University, Changchun 130012;2. Key Lab of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012;3. State Key Lab of Automobile Dynamic Simulation, Jilin University, Changchun 130022)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-03-20 Published:2009-03-20

摘要: 针对第5百分位(身材矮小)成年女性与第50百分位(平均身材)成年男性等不同类型的乘员,建立基于低成本CMOS摄像机的汽车乘员分类视觉检测系统及其智能模式识别算法。通过建立乘员图像测量空间的图像预处理算法和乘员边缘检测算法,利用Legendre矩描述乘员特征空间的乘员边缘主特征,以及建立基于BP神经网络的乘员类型空间模式分类器,实现不同乘员类型的模式分类。

关键词: 智能汽车乘员约束系统, 汽车乘员分类视觉检测算法, Legendre矩, BP神经网络

Abstract: This paper builds a vision sensor for occupant classification based on low cost CMOS camera and an intelligent pattern recognition algorithm, which focuses on the 5th female(runty female) and the 50th male(average stature male), etc. The image pretreatment algorithm and occupant image edge detection algorithm are founded. The critical properties of occupant edge are described by Legendre moment. The pattern classifier based on the BP neural network is set up. The pattern classification of different occupant types is realized.

Key words: intelligent occupant restraint system, occupant classification vision detection algorithm, Legendre moment, BP neural network

中图分类号: