| 219 | 5 | 21 |
| 下载次数 | 被引频次 | 阅读次数 |
在智能交通系统中,车流量检测对于准确提取交通参数起着重要作用。针对视频检测中虚拟线圈法由于环境和光照等因素影响导致检测不准确的问题,提出一种基于虚拟线圈法和模板链法相结合的车流量检测新方法。首先对采集的交通图像进行车道划分,根据虚拟线圈法设定判别准则,检测路面中的标记区域,同时运用相应的模板对车表面像素灰度变化均匀的区域进行标记,形成模板链,最后通过检测模板链实现车辆的检测。经过实验证明,该方法可以准确地检测出车辆,并具有较好的鲁棒性。
Abstract：In the intelligent transportation systems,traffic flow detection for an accurate traffic parameter extraction plays an important role.For the problem of detection inaccurateness of virtual coil method,a new method of traffic flow video detection based on combining of virtual coil and templates chain is proposed.Firstly,lane partition is done in the traffic image.According to the method of virtual coil,area markers are detected by judgment rule.Pixel gray uniform region of vehicle surface is marked by template.Secondly,the template chain is formed.Finally,the vehicle is detected through the templates chain detection.It is proved that this algorithm can detect vehicle accurately and has the good robustness.
[1]Tomizuka M.Automated Highway Systems:An Intelligent Transportation System for the Next Century[J].IEEE International Symposium on Industrial Electronics,1997,(1):1-4.
[2]Sun C,Ritchie S G,Tsai K.Algorithm development for derivation of section-related measures of traffic system performance using inductive loop detectors[J].Trans-portation Research Record:Journal of the Transportation Research Board.1998,(1643):171-180.
[3]王圣男,郁梅,蒋刚毅.智能交通系统中基于视频图像处理的车辆检测与跟踪方法综述[J].计算机应用研究,2005(9):9-14.
[4]史忠科,曹力.交通图像检测与分析[M].北京:科学出版社,2007.
[5]Tseng B L,Lin C Y,Smith J R.Real-time video surveillance for traffic monitoring using virtual line analysis[C].IEEE international conference,2002,2:541-544.
[6]郁梅,蒋刚毅,贺赛龙.基于路面标记的车辆检测和计数[J].仪器仪表学报,2002,23(4):386-391.
[7]李庆武,石丹,孟凡,徐立中.基于模糊集理论的车道标志线精确检测[J].交通与计算机.2007,25(6):1-3.
[7]边肇祺,张学工等.模式识别(第二版)[M].北京:清华大学出版社,2000.
基本信息:
中图分类号:TP391.41
引用信息:
[1]王慧斌,孟凡,李庆武,等.虚拟线圈和模板链相结合的车流量视频检测方法研究[J].微型电脑应用,2010,26(11):4-6+2.
基金信息:
国家高技术研究发展计划(863计划)(2007AA11Z227);; 国家自然科学基金(60972101);; 江苏省社会发展科技项目(BS2007058)
2010-11-20
2010-11-20