基于LabVIEW的双目视觉测距系统设计  

DESIGN OF BINOCULAR VISION RANGING SYSTEM BASED ON LABVIEW

在线阅读下载全文

作  者:杨慧闻 张嘉琪[2] Yang Huiwen;Zhang Jiaqi(CNNC Geology&Ming Technology Co.,Ltd.,Beijing 100013,China;College of Environmental Science and Safety Engineering,Tianjin University of Technology,Tianjin 300384,China)

机构地区:[1]中核地矿科技集团有限公司,北京100013 [2]天津理工大学环境科学与安全工程学院,天津300384

出  处:《计算机应用与软件》2023年第2期124-129,143,共7页Computer Applications and Software

摘  要:在对障碍物进行测距的过程中,双目视觉测距技术拥有的成本低、高效、精确度高与构造简单的特点。鉴于此,设计一种基于灰度值金字塔图像匹配算法的双目视觉测距系统。通过搭建立体视觉硬件平台,利用LabVIEW软件平台编写硬件控制和测距程序,采用灰度值金字塔算法进行双目图像匹配获取视差数据,利用几何关系求出障碍物深度计算公式,并且在实验室中随机选用8个标志物进行仿真实验,检验理论深度与真实距离间的误差率。实验表明,通过视差数据求得的理论深度信息,所选特征点清晰、纹理复杂度较高的ROI(Region of Interest)区域的误差率在2%左右,特征点模糊、纹理复杂度较低区域误差率在5%左右,图像匹配相似度在900左右,在允许的误差范围内验证了图像匹配的准确性和双目测距系统的可靠性。In the process of measuring obstacles, the binocular vision ranging technology has the characteristics of low cost, high efficiency, high accuracy and simple structure. In view of this, a binocular vision ranging system based on gray value pyramid image matching algorithm is designed. By building a stereo vision hardware platform, the LabVIEW platform was used to write hardware control and ranging programs, the gray value pyramid algorithm for binocular image matching was used to obtain parallax data, and the geometric relation was used to calculate the obstacle depth calculation formula. In the laboratory, eight markers were randomly selected for simulation experiments to test the error rate between the theoretical depth and the real distance. The experiment shows that the error rate of ROI area with clear feature points and high texture complexity is about 2%, and the error rate of area with fuzzy feature points and low texture complexity is about 5% for the theoretical depth information obtained from disparity data. The similarity of image matching is about 900, which verifies the accuracy of image matching and the reliability of binocular ranging system within the allowable error range.

关 键 词:LABVIEW 双目视觉 金字塔算法 图像匹配 测距 

分 类 号:TP3[自动化与计算机技术—计算机科学与技术]

 

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