The invention discloses a crane swing angle three-dimensional measurement method based on binocular vision, and relates to the field of computer vision measurement, and the method comprises the following steps: S1, installing a binocular vision camera, and collecting a video in real time; s2, correcting the internal reference of the camera based on an improved BP neural network binocular calibration method, and calculating the relative position relation of the camera; s3, obtaining a light spot image according to the binocular vision camera, carrying out secondary calibration, establishing a coordinate system according to the position of the light spot, and calculating the position relation with the coordinate system of the camera; s4, according to left and right camera imaging in combination with a gray centroid algorithm, extracting a light spot sub-pixel level gravity center; s5, converting the pixel coordinate into a three-dimensional coordinate, and solving a light spot three-dimensional coordinate value in combination with a least square method; and S6, calculating a load swing angle according to the light spot coordinates. According to the method, the measurement precision is improved by using the improved BP neural network binocular calibration method, the load swing angle is calculated according to the position change of the three-dimensional coordinates of the light spots on the load, and the real-time performance and accuracy of swing angle measurement are improved.

    本发明公开了一种基于双目视觉的吊车摆角三维测量方法,涉及计算机视觉测量领域,包括以下步骤:S1:安装双目视觉相机,实时采集视频;S2:基于改进后的BP神经网络双目标定方法矫正相机内参,计算相机相对位置关系;S3:根据双目视觉相机获得光斑图像,进行二次标定,以光斑位置建立坐标系,计算与相机坐标系的位置关系;S4:根据左右相机成像结合灰度质心算法,提取光斑亚像素级别重心;S5:将像素坐标转换为三维坐标,结合最小二乘法求解光斑三维坐标值;S6:根据光斑坐标,计算负载摆动角度。本发明利用改进后的BP神经网络双目标定方法提高了测量精度,以负载上光斑三维坐标的位置变化计算负载摆动角度,提高了摆角测量的实时性与准确性。


    Access

    Download


    Export, share and cite



    Title :

    Crane swing angle three-dimensional measurement method based on binocular vision


    Additional title:

    一种基于双目视觉的吊车摆角三维测量方法


    Contributors:
    YU LILI (author) / SONG HENG (author) / OUYANG HUIMIN (author)

    Publication date :

    2023-11-17


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B66C Krane , CRANES / G01B MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS , Messen der Länge, der Dicke oder ähnlicher linearer Abmessungen / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL



    Bridge crane load swing angle detection method based on computer vision

    LU BIAO / LIU ZHONGYAN / ZHANG JING et al. | European Patent Office | 2023

    Free access

    Automatic tower crane loading method based on binocular vision

    YU WENJIE / ZHANG SHUJIAN / YE SONG et al. | European Patent Office | 2021

    Free access

    Crane anti-swing method based on machine vision

    DUAN PEIPEI / CHEN JINGMENG / PENG CONG | European Patent Office | 2020

    Free access

    Rotor disc inclination angle measurement method based on binocular vision

    FAN FENG / ZHANG YUBIN / WANG WENTAO et al. | European Patent Office | 2025

    Free access

    Binocular Vision Location with Swing Compensation Based on Fisheye Lens

    Cai, Chengtao / Wang, Boyu / Zhou, Yueyuan | British Library Conference Proceedings | 2018