检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:马启玮 韩慧妍[1] 韩燮[1] 张增一 MA Qi-wei;HAN Hui-yan;HAN Xie;ZHANG Zeng-yi(School of Data Science and Technology,North University of China,Taiyuan 030051,China;School of Telecommunication Engineering,Xidian University,Xi’an 710100,China)
机构地区:[1]中北大学大数据学院,山西太原030051 [2]西安电子科技大学通信工程学院,陕西西安710100
出 处:《计算机工程与设计》2021年第5期1409-1417,共9页Computer Engineering and Design
基 金:国家重点研发计划基金项目(2018YFB2101504);山西省重点研发计划基金项目(201803D121081)。
摘 要:为解决红外图像中人眼瞳孔中心定位存在的眼睑遮挡、睫毛遮挡和角膜反射引起的白斑干扰等问题,采用由粗到精的瞳孔中心定位策略。对红外图像进行预处理,通过YoloV3深度学习模型检测瞳孔区域,实现瞳孔中心的粗略定位;在此基础上,采用星射线法提取瞳孔边缘点,剔除因眼睑遮挡导致的伪瞳孔边缘点;将剩下的边缘点基于最小二乘法进行椭圆拟合,对椭圆进行修正,精确定位瞳孔中心。实验结果表明,在眼睑遮挡、睫毛遮挡和白斑干扰的情况下,该方法可以准确定位,具有较好的鲁棒性和实时性。To solve the problem of eyelid occlusion,eyelash occlusion and white spot interference caused by corneal reflex in infrared image of human pupil center positioning,the pupil center was located from coarse to fine.The infrared image was preprocessed,and the pupil area was detected using YoloV3 deep learning model,and the pupil center was roughly located.On this basis,the star ray method was used to extract the pupil edge points and eliminate the pseudo pupil edge points caused by eyelid occlusion.The remaining edge points were fitted to the ellipse based on the least square method.The ellipse was modified to accurately locate the pupil center.Experimental results show that the proposed method can accurately locate the target in the case of eyelid occlusion,eyelash occlusion and white spot interference,and has good robustness and real-time performance.
关 键 词:瞳孔中心定位 星射线 眼睑遮挡 椭圆拟合 瞳孔边缘
分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.231