The lamina cribrosa thickness（LCT） could be affected by dynamic changes in its structure.Using spectral-domainoptical coherence tomography（SD-OCT）,we have studied the behaviour of the laminar region in 14 young su...The lamina cribrosa thickness（LCT） could be affected by dynamic changes in its structure.Using spectral-domainoptical coherence tomography（SD-OCT）,we have studied the behaviour of the laminar region in 14 young subjects over 24 h.Significant changes in LCT were observed,depending on the time at which the measurement was taken,with the maximum thickness being observed at 7.30 p.m.,and the minimum at 7.30 a.m.This finding could suggests a circadian pattern in the LCT thickness in healthy subjects,which could have implications for the classification,diagnosis and prognosis of both normal and glaucomatous subjects.展开更多
提出了实时条件下裸手单目的手部定位和跟踪算法。结合改进的差分法提出了实用的手部约束条件,从每帧图像中提取手部图像,确定感兴趣区域(ROI,region of interesting),得到较为满意的手部分割结果,再对手部图像特征进行深入分析和提取,...提出了实时条件下裸手单目的手部定位和跟踪算法。结合改进的差分法提出了实用的手部约束条件,从每帧图像中提取手部图像,确定感兴趣区域(ROI,region of interesting),得到较为满意的手部分割结果,再对手部图像特征进行深入分析和提取,利用改进的相干映射算法(VCM,vector coherence mapping)进行跟踪,针对手的运动增加了约束,保证了顽健性。在这个基础上,提出了时间相关的运动预测模型,满足了实时性的要求,保证前后分析结果的一致性。实验结果证明,在不同光照和复杂背景下系统有最高达99%的识别率,与已有的系统相比,性能显著提高。展开更多
文摘The lamina cribrosa thickness（LCT） could be affected by dynamic changes in its structure.Using spectral-domainoptical coherence tomography（SD-OCT）,we have studied the behaviour of the laminar region in 14 young subjects over 24 h.Significant changes in LCT were observed,depending on the time at which the measurement was taken,with the maximum thickness being observed at 7.30 p.m.,and the minimum at 7.30 a.m.This finding could suggests a circadian pattern in the LCT thickness in healthy subjects,which could have implications for the classification,diagnosis and prognosis of both normal and glaucomatous subjects.
文摘提出了实时条件下裸手单目的手部定位和跟踪算法。结合改进的差分法提出了实用的手部约束条件,从每帧图像中提取手部图像,确定感兴趣区域(ROI,region of interesting),得到较为满意的手部分割结果,再对手部图像特征进行深入分析和提取,利用改进的相干映射算法(VCM,vector coherence mapping)进行跟踪,针对手的运动增加了约束,保证了顽健性。在这个基础上,提出了时间相关的运动预测模型,满足了实时性的要求,保证前后分析结果的一致性。实验结果证明,在不同光照和复杂背景下系统有最高达99%的识别率,与已有的系统相比,性能显著提高。
