摘要
为了准确检测智能车前方目标车辆以及确定目标车辆与本车的距离信息,提出了一种应用模糊逻辑融合车辆多特征检测目标车辆的算法。该算法充分考虑到车辆多个特征的重要性,将模糊理论中的模糊隶属度函数和特征置信度值相结合实现目标车辆的验证。在生成目标假设以及提取有效特征点后,通过对不同特征进行模糊化,根据模糊推理融合得到的目标车辆的最终置信度验证车辆假设,实现前方车辆的检测。试验数据表明,该算法具有较好的适应能力和抗干扰能力,能够及时准确地检测前方目标车辆。
In order to implement the front vehicle detection and determine the distances between the host vehicle and the target vehicles accurately,one kind of algorithm for vehicle detection using fuzzy logic is proposed.Considering the importance of the features,the membership function and confidence are combined to verify the hypothesis.After vehicle hypothesis formation,features are fuzzed with membership functions and the vehicle detection is realized according to the confidence obtained by fusion of different features.The experiments indicated that this algorithm has the good adaptive ability and anti-jamming ability.It can detect the proceeding vehicles intimely and accurately.
出处
《计算机工程与设计》
CSCD
北大核心
2010年第23期5100-5103,共4页
Computer Engineering and Design
基金
北京市教委科技创新平台基金项目(JJ002790200802)
关键词
智能车
模糊逻辑
隶属度函数
特征置信度
车辆检测
intelligent vehicle
fuzzy logic
membership function
confidence of feature
vehicle detection
