Several 2-D displacement sensing methods are reviewed. As to the crossdiffraction grating, there is no absolute zero-reference. In regards to the optical fiber method,the output signal is affected greatly by the quali...Several 2-D displacement sensing methods are reviewed. As to the crossdiffraction grating, there is no absolute zero-reference. In regards to the optical fiber method,the output signal is affected greatly by the quality of the reflecting surface and it is hard to gethigh resolution. Considering the concentric-circle gratings, the displacement can only be gainedwith complicated calculating of the experiment data. Compared with the advantages and limitations ofthe methods above, a novel 2-D zero-reference mark is especially proposed and demonstrated. Thiskind of mark has an absolute zero-reference when used in pair, and the experimental result is simpleto dispose. By superimposing a pair of specially coded 2-D marks, the correct alignment position ofthe two marks can be detected by the maximum output of the sharp intensity peak. And each slope ofthe peak is of good linearity which can be used to achieve high resolution in positioning andalignment in two dimensions. Design and fabrication of such 2-D zero-reference marks are introducedin detail. The experiment results are agreed with the theoretical ones.展开更多
为了提高夜间疲劳驾驶检测的准确率,在现有低光增强算法Zero-DCE(Zero-Reference Deep Curve Estimation)的基础上,提出改进Zero-DCE的低光增强算法。首先,引入上下采样结构,减少噪声影响。同时,引入注意力门控机制,提高网络对图像中人...为了提高夜间疲劳驾驶检测的准确率,在现有低光增强算法Zero-DCE(Zero-Reference Deep Curve Estimation)的基础上,提出改进Zero-DCE的低光增强算法。首先,引入上下采样结构,减少噪声影响。同时,引入注意力门控机制,提高网络对图像中人脸区域的敏感性,有效提高网络的检测率。然后,针对噪声相关问题,提出改进的核选择模块。进一步,使用MobileNet的深度可分离卷积替换Zero-DCE的标准卷积,提高网络的检测速度。最后,通过人脸关键点检测网络和分类网络,判断驾驶员的疲劳状态。实验表明,在夜间环境下,相比现有的疲劳驾驶检测算法,文中算法在人脸检测的准确率和眼睛状态的识别率上都有所提升,取得较令人满意的检测效果。展开更多
基金This project is supported by National Natural Science Foundation of China(No.50335050, No.50275140)Specialized Research Foundation for Doctoral Program of Higher Education (SRFDP) of China(No. 20030358020).
文摘Several 2-D displacement sensing methods are reviewed. As to the crossdiffraction grating, there is no absolute zero-reference. In regards to the optical fiber method,the output signal is affected greatly by the quality of the reflecting surface and it is hard to gethigh resolution. Considering the concentric-circle gratings, the displacement can only be gainedwith complicated calculating of the experiment data. Compared with the advantages and limitations ofthe methods above, a novel 2-D zero-reference mark is especially proposed and demonstrated. Thiskind of mark has an absolute zero-reference when used in pair, and the experimental result is simpleto dispose. By superimposing a pair of specially coded 2-D marks, the correct alignment position ofthe two marks can be detected by the maximum output of the sharp intensity peak. And each slope ofthe peak is of good linearity which can be used to achieve high resolution in positioning andalignment in two dimensions. Design and fabrication of such 2-D zero-reference marks are introducedin detail. The experiment results are agreed with the theoretical ones.
文摘为了提高夜间疲劳驾驶检测的准确率,在现有低光增强算法Zero-DCE(Zero-Reference Deep Curve Estimation)的基础上,提出改进Zero-DCE的低光增强算法。首先,引入上下采样结构,减少噪声影响。同时,引入注意力门控机制,提高网络对图像中人脸区域的敏感性,有效提高网络的检测率。然后,针对噪声相关问题,提出改进的核选择模块。进一步,使用MobileNet的深度可分离卷积替换Zero-DCE的标准卷积,提高网络的检测速度。最后,通过人脸关键点检测网络和分类网络,判断驾驶员的疲劳状态。实验表明,在夜间环境下,相比现有的疲劳驾驶检测算法,文中算法在人脸检测的准确率和眼睛状态的识别率上都有所提升,取得较令人满意的检测效果。
