基于计算机视觉的激光测距定位技术研究  被引量:1

Research on Laser Ranging and Positioning Technology Based on Computer Vision

在线阅读下载全文

作  者:傅媛[1] FU Yuan(Wuhan Universtty of Technology Huaxia College,Hubei Wuhan 430223,China)

机构地区:[1]武汉理工大学华夏学院,武汉湖北430223

出  处:《新一代信息技术》2019年第16期82-88,共7页New Generation of Information Technology

摘  要:传统激光测距方法随着测量距离的增加,对于被测目标的定位会出现偏差,进而降低目标位置测量精度。提出基于计算机视觉的激光测距定位技术。采用张正友标定理论进行摄像机与激光测距仪之间的联合标定,通过相同目标上激光点的水平距离最大差距和图像中的水平像素最大差距的关系,获取目标深度图像,求解被测目标的范围信息,提高对被测目标的空间定位精度;借助OpenCV实现立体校正与立体匹配,完成对被测目标位置的判定。依据立体匹配获得的视差图,求解待测目标移动前后两幅图像中激光点水平像素间的距离,实现对被测目标位置的精确测量。实验结果表明,该方法对700米以内的目标测量相对精度优于0.1%,满足远距离、高精度测定需求,可推广至对动态目标的位置测量。With the increase of the measurement distance,the traditional laser ranging method will have a deviation for the positioning of the measured target,and thus reduce the accuracy of the target position measurement.A laser ranging and positioning technology based on computer vision is proposed.Using Zhang Zhengyou's calibration theory to perform joint calibration between the camera and the laser range finder,obtain the target depth image and solve the range of the target by the maximum distance between the horizontal distance of the laser point on the same target and the maximum difference of the horizontal pixels in the image.The information is used to improve the spatial positioning accuracy of the measured object;the stereo correction and the stereo matching are implemented by using OpenCV,and the determination of the position of the measured target is completed.According to the disparity map obtained by stereo matching,the distance between the horizontal pixels of the laser points in the two images before and after the movement of the object to be tested is solved,so as to accurately measure the position of the measured object.The experimental results show that the method can measure the relative accuracy of target measurement within 700 meters better than 0.1%,meet the requirements of long-distance and high-precision measurement,and can be extended to the position measurement of dynamic targets.

关 键 词:计算机视觉 激光测距 目标定位 双目立体视觉 

分 类 号:TN247[电子电信—物理电子学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象