中文摘要：

提出了一种基于改进单高斯模型的车辆检测与流量统计算法,该算法采用改进的单高斯模型对移动目标进行检测,然后选用HSV颜色空间抑制阴影,提高了目标提取的准确率,最后,按车道分别设置相应的虚拟区域,以实现车流量的统计工作.为验证算法的有效性,在标准测试视频上进行了对比实验,实验结果表明,该算法能够快速地提取车辆目标,且具有较高的车辆识别率,有一定的实用价值.

英文摘要：

A vehicle detection and traffic statistics algorithm based on improved Gaussian model is proposed. The moving target is detected by using improved single Gaussian model at first. Then the Shadows are eliminated through HSV feature space, and the accuracy rate of target extraction is raised. Finally the traffic is counted in the suppositional areas of lanes. The paper makes experiments with standard test video. The results show that the algorithm can detect vehicle quickly and have a higher recognition rates. The algorithm can work well in the actual conditions.