本发明涉及图像处理技术领域,具体涉及一种基于图像处理的起重机卷筒工作异常预警方法。该方法通过对卷筒图像中的边缘信息进行分类获得边缘类别后进一步筛选,获得卷筒轮廓边缘。根据标准线槽边缘与卷筒轮廓边缘的边缘类别的相似度获得线槽边缘。通过线槽边缘和标准线槽边缘上边缘类别的主成分方向获得表示方向对齐的匹配程度,以最大的匹配程度的边缘类别作为参考边缘类别组。通过参考边缘类别组获得对齐参数,利用对齐参数进行旋转缩放对齐,获得参考线槽边缘。根据参考线槽边缘获得卷筒磨损的危险程度。本发明通过将标准线槽边缘和线槽边缘对齐,消除了检测过程的视觉误差,准确的分析了卷筒危险程度。

    The invention relates to the technical field of image processing, in particular to an image processing-based early warning method for abnormal operation of a crane drum. According to the method, the method comprises the steps of classifying the edge information in a reel image to obtain edge categories, and then further screening the edge categories to obtain reel contour edges; obtaining the trunking edge according to the similarity between the standard trunking edge and the edge category of the winding drum contour edge; obtaining the matching degree representing direction alignment through principal component directions of edge categories on the trunking edge and the standard trunking edge, and adopting the edge category with the maximum matching degree as a reference edge category group; obtaining an alignment parameter through the reference edge category group, and carrying out rotation zooming alignment by using the alignment parameter to obtain a reference wire slot edge; and obtaining the danger degree of wear of the reel according to the edge of the reference slot. According to the invention, the edge of the standard wire slot is aligned with the edge of the wire slot, visual errors in the detection process are eliminated, and the danger degree of the winding drum is accurately analyzed.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    一种基于图像处理的起重机卷筒工作异常预警方法


    Erscheinungsdatum :

    2021-11-16


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / B66D Haspeln , CAPSTANS / G06K Erkennen von Daten , RECOGNITION OF DATA