基于车牌识别流数据的车辆伴随模式发现方法

针对伴随车辆检测这一新兴的智能交通应用，在一种特殊的流式时空大数据-车牌识别流式大数据下，重新定义Platoon伴随模式，提出PlatoonFinder算法，即时地在车牌识别数据流上挖掘Platoon伴随模式.本文的主要贡献包括：第一，将Platoon伴随模式发现问题映射为数据流上的带有时空约束的频繁序列挖掘问题.与传统频繁序列挖掘算法仅考虑序列元素之间位置关系不同，本文算法能够在频繁序列挖掘的过程中有效处理序列元素之间复杂的时空约束关系；第二，本文算法融入了伪投影等性能优化技术，针对数据流的特点进行了性能优化，能够有效应对车牌识别流式大数据的速率和规模，从而实现车辆Platoon伴随模式的即时发现.通过在真实车牌识别数据集上的实验分析表明，PlatoonFinder算法的平均延时显著低于经典的Aprior和PrefixSpan等频繁模式挖掘算法，也低于真实情况下交通摄像头的车牌识别最小时间间隔.因此，本文所提出的算法可以有效的发现伴随车辆组及其移动模式.

Approach to Discover Companion Pattern Based on ANPR Data Stream

Discovery of companion vehicles is a newly emerging intelligent transportation application. Aiming at it, this paper redefines the Platoon companion pattern over a special kind of spatio-temporal data stream, called as ANPR (Automatic Number Plate Recognition Data). Correspondingly, a PlatoonFinder algorithm is also proposed, which can mine Platoon companions over ANPR data stream instantly. The main contributions include:1) we transform Platoon discovery problem into frequent sequence mining problem with customized spatio-temporal constraints. Compared to traditional frequent sequence mining algorithms, our algorithm can effectively handle complex spatio-temporal relationships among sequence elements rather than their positions. 2) our algorithm also integrates several optimization techniques like pseudo projection to greatly improve the efficiency. It can efficiently deal with high speed and large scale ANPR data stream so as to instantly discover Platoon companions. Experiments show that the latency of our algorithm is significantly lower than classic frequent pattern mining algorithms like Apriori and Prefixspan. Furthermore, it is also lower than the minimum time interval between any two real ANPR data records. Hence, our algorithm can discover Platoon companions effectively and efficiently.