摘要
介绍一种基于Gabor特征和多分辨率的车辆检测方法,该方法首先在假设产生阶段根据道路场景图像的消失点确定图像的兴趣区域,以垂直和水平边缘为依据产生相应兴趣区域的假设链,最后将各兴趣区域假设链合并,产生最终的假设,验证阶段用支撑向量机分类器验证假设正确与否,在保证鲁棒性的同时,提高实时性,此方法在假设产生阶段大大减少非兴趣区域对系统计算资源的消耗,减少计算负担,且在假设验证阶段有效减少伪目标对检测率的影响。实验表明,本文算法处理速度可达20帧/s,检测率在90%以上。
A vehicle detection approach based on Gabor feature and multiresolution hypothesis-verification structure is proposed. The proposed approach includes two basic phases. Firstly, the Regions of Interest （ROD in an image are determined according to the lane vanishing points. Then a hypothesis list in each ROI is created according to the vertical edges and horizontal edges. Finally, a hypothesis list for the whole image is obtained by combining these three lists. In the hypothesis validation phase, a vehicle validation approach using Support Vector Machine （ SVM ） is proposed. The proposed algorithm decreases the computational cost by eliminating un-interesting area, and in the hypothesis verification phase, the positive false is low. The experimental results show that the average right detection rate reaches 90% and the execution speed is 20fps using a Pentium（R） 4 CPU 2.4GHz.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2006年第6期722-726,共5页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金优秀创新群体资助项目(No.60021302)
关键词
车辆检测
假设验证
GABOR滤波器
支撑向量机
Vehicle Detection, Hypothesis and Validation, Gabor Filter, Support Vector Machine
