摘要
针对当前各种眼动跟踪方法的不足,提出一种精确定位虹膜,实现快速眼动跟踪的算法。利用基于AdaBoost算法的检测器定位虹膜,引入susan算子消除噪声,以此建立跟踪模板,分析目标与噪声的饱和度特征,使用改进的基于多特征融合CamShift算法实现眼动跟踪。实验结果表明,该方法跟踪虹膜精确、速度快、错误率低,达到准确性、鲁棒性和实时性的要求。
Aiming at the shortcomings of current various eye tracking methods, a rapid eye tracking algorithm based on precise positioning iris is proposed. Firstly, the detector based on AdaBoost algorithm is used to position iris, and susan operator is used to eliminate the influence of eyeball-like factors. The improved CamShift algorithm based on multi features fusion is used for eye tacking with the template of iris region and analysis of the feature of object and noise's saturation. The experimental results show that this method can precisely track iris, with rapid speed, low error rate, it meets the requirements of accuracy, robustness and real-time.
出处
《计算机工程与设计》
CSCD
北大核心
2014年第2期567-572,共6页
Computer Engineering and Design
基金
核高基重大专项基础软件方向基金项目(2012ZX01033001-001)
国家自然科学基金项目(61003032)
人工智能四川省重点实验室开放基金项目(2011RYJ04)
中央高校基本科研业务费专项基金项目(ZYGX2009J060)