摘要
受相机视域限制,基于机器视觉的货车外廓测量不能一次性获取完整的车身图像。因此,在传统机器视觉测量的基础上引入图像拼接技术,设计了一种动态无接触货车尺寸测量方法,可在不停车、无接触的情况下对序列货车图像进行特征提取、图像配准与融合、外廓尺寸测算。仿真结果表明,本方法的平均测量误差为0.83%~1.87%,满足GB21861-2014的要求。
Limited by the camera's field of view,the truck contour dimension measurement based on machine vision cannot obtain a complete body image at one time.Therefore,image stitching technology is introduced on the basis of traditional machine vision measurement,and a dynamic non-contact measurement method of truck size is designed,which can be used for feature extraction,image registration and fusion,and external contour dimension measurement of sequence truck images without stopping and contacting.Simulation results show that the average measurement error of this method is 0.83%--1.87%,which meets the requirement of GB21861-2014.
作者
孔月萍
赵天悦
王佳婧
Yueping Kong;Tianyue Zhao;Jiajing Wang(College of Information and Control Engineering,Xi'an University of Architecture and Technology,Xi'an,Shanxi 710055,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2020年第21期172-177,共6页
Laser & Optoelectronics Progress
基金
陕西省自然科学基础研究计划(2019JM-183)
西安市碑林区科技计划(GX1806)。
关键词
机器视觉
外廓尺寸测量
特征提取
图像拼接
图像融合
machine vision
contour dimension measuring
feature extraction
image stitching
image fusion
