摘要
为了快速准确地进行车型识别,提出一种基于Harris角点检测的识别方法.该方法基于背景减法提取出运动车辆目标,并提取其Harris角点,选取轿车、客车及货车Harris角点作为标准样本,分别计算待识别车辆与3种标准样本Harris角点的Hausdorff距离,认定Hausdorff距离较小的两者具有相同的车型.实验结果表明,该方法准确、有效且实时性较好.
To recognize the vehicles accurately and speedy, this paper presents a method based on Harris corner detection. This method obtains the accurate Harris corner of moving vehicles based on background subtract. It selects three Harris corners to denote three type of vehicles which are saloon car, passenger car and truck. Then calculates the distance of Hausdorff between the Harris corner and the three types of swatches which need to be recognized. The two whose distance of Hausdorff is smallest can be judged as the same type. Experiment results show that the method can get a high recognition precision with a better time-consuming.
出处
《扬州大学学报(自然科学版)》
CAS
CSCD
2008年第1期67-70,共4页
Journal of Yangzhou University:Natural Science Edition
基金
国家自然科学基金资助项目(20299030)
扬州大学自然科学基金资助项目(KK0313090)