用于疲劳检测系统的有效人眼跟踪方法

An effective eye tracking method for fatigue detection system

驾驶员疲劳检测在智能交通系统的安全驾驶方面起着主要作用。有研究人员提出基于人眼跟踪和动态模板匹配的实时驾驶员疲劳检测系统,主要由四部分构成,分别是:人脸检测、人眼检测、人眼跟踪和疲劳检测,在人眼跟踪方面传统采用平均绝对值误差匹配函数进行穷尽搜索。为了弥补该种方法在匹配方面的低精度和搜索方面的低效率,提出新的匹配函数EPC (the edge pixel count)和2D-log快速搜索算法。将采集的5段视频进行实验和对比分析,结果表明,2D-log搜索算法和EPC匹配函数在人眼跟踪方面具有非常好的性能。平均只需要23个搜索点就可以获得99. 92%的人眼跟踪准确率,且计算量只是传统方法的10. 59%。传统的穷尽搜索算法却需要441个搜索点,才能获得96. 01%的准确率。2D-log搜索算法和EPC匹配函数大大提高疲劳驾驶检测系统中人眼跟踪的效率。

Driver fatigue detection plays an important role in intelligent transportation systems for driving safety. Recently, the researchers proposed a real-time driver fatigue detection system based on eye tracking and dynamic template matching. The driver fatigue detection system consists of four parts： face detection, eye detection, eye tracking and fatigue detection. However, their work suffers from an exhaustive search in eye tracking with the conventional mean absolute difference （MAD） matching function. To remedy the low accuracy in matching and inefficiency in search, this paper first proposed one new matching functions, the edge pixel count （EPC）, to enhance matching accuracy. In addition, it utilized fast search algorithms, such as the 2D-log search, to expedite search. The experimental results show that the 2D-log search with the EPC matching function has the best performance on eye tracking; it only requires 23 search points on average to achieve 99.92% correct rate of eye tracking, the total amount of computations for eye tracking in the 2D-log search with EPC only takes up to about 10.59% of the original work. As comparing to the original work, it requires 441 search points with only 96.01% correct rate. 2D-log search algorithm and EPC matching function greatly improve the efficiency of human eye tracking in the fatigue detection system.