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
机构地区:[1]河北科技大学信息科学与工程学院,河北石家庄050000 [2]石家庄市京华电子实业有限公司工程部,河北石家庄050000
出 处:《机械与电子》2017年第6期29-31,共3页Machinery & Electronics
基 金:河北省重大科技成果转化专项项目(16040601Z)
摘 要:光条纹中心的精确提取是线结构光三维识别系统的重要环节。环境光干扰、被测物表面反射以及图像采集系统所产生的噪声都给光条提取增加了难度。文章提出了一种快速精确的线结构光条纹中心提取法。首先,对图像进行预处理,通过边缘法对结构光中心线进行边缘检测;然后,用均方灰度梯度法确定结构光中心法线方向;最后,对法线方向上像素进行灰度加权,从而精确提取出结构光条纹中心。实验结果证明,该算法光条纹中心的提取精度达到了亚像素级别。The accurate extraction of light stripe center plays an important role in the linear structuredlight three- dimensional (3D) recognition system. The interference of ambient light, reflection of meas-ured objects and noise generated by the image acquisition system increase the difficulty in extracting thelight stripe. This paper proposed an accurate and fast method for extracting the center of linear structuredlight stripe. Firstly, the image was preprocessed, and the center of linear structure light was detected bythe edge method. Secondly, the average squared gray and gradient method was used to determine the nor-mal direction of the structured light center. Finally, the center of structured light was extracted accuratelythrough weighting the pixel in the normal direction. The experimental results demonstrate that the extrac-tion accuracy of this proposed algorithm has reached the level of the sub- pixel.
分 类 号:TN911.73[电子电信—通信与信息系统]
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:216.73.216.145