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。
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.