摘要
提出了基于形变模板的运动汽车表示和分割方法.建立了几种具有代表性汽车的形变模板模型和参数约束函数,用最优化算法达到从图像中检测和分割运动汽车的目的.通过对EM算法改进,用几何温度进度代替对数温度进度,加快了算法的收敛时间,提高了算法的稳健性.实验结果表明:本分割方法能够达到克服多运动目标和阴影的影响,有效实现汽车的识别和分割,并且在分割率和运算时间上都有了一定提高.
A moving vehicle segmentation method in complex background image is designed based on deformable template model.Several representative deformable template models and parameter constraint functions are established.The detection and segmentation are accomplished by using optimal algorithm.The traditional EM method is amended and a geometrical anneal temperature schedule is put forward to reduce the computing time.Compared to the traditional logarithmic anneal temperature schedule,the robot and computing time are improved.
出处
《许昌学院学报》
CAS
2009年第2期85-89,共5页
Journal of Xuchang University
基金
国家自然科学基金项目(60475040)
河南省教育厅科技攻关项目(2008A520022)
许昌市科技攻关项目(07020065)
关键词
运动汽车检测
汽车分类识别
形变模板模型
moving vehicle detection
vehicle classification and recognition
deformable template model
