Research on Accompanying Cars Recognition in Practical Application

In massive dynamic traffic flows, it is very common to see the cars moving in a queue. In some scenarios, these cars are regarded as accompanying cars and suspected of gang crime support each other when that condition occurs in a high rate. It is very important to identify the accompanying vehicles as early as possible and to reduce potential risks of road traffic system and to reduce road-related public security cases and criminal cases. Based on the automatic license plate recognition database and data mining technology, this paper proposes a set of algorithms in identifying accompanying cars and a field test is conducted. The results demonstrate the performance of the algorithm with effectiveness, low detection error, wide application and capability for further investigation.

摘要海量动态交通流中，经常出现结伴而行的车辆。特定区域内，当结伴车辆出现的概率较大时，即可将其视为伴随车辆，这类车辆具有相互掩护和团伙作案的重大嫌疑。及早检测和识别伴随车辆，能有效降低道路交通安全系统中的危险因素，对预防和减少与道路有关的治安和刑事案件，也具有十分重要的意义。本文在车牌自动识别数据库基础上，应用数据挖掘技术，提出伴随车辆检测和识别算法，并进行了实地测试。实验结果表明：应用数据挖掘技术对伴随车辆进行分析检测，具有检测效率高、检测误差小、应用范围广的特点，完全可以满足刑侦等部门对伴随嫌疑车辆进一步排查的需要。