基于改进Canny边缘检测的堆叠货箱分割定位方法

为了提高集装箱卸货的自动化水平，针对集装箱内堆叠货箱难分割定位的问题，提出了一种基于改进Canny边缘检测的堆叠货箱分割定位方法。通过阈值分割和形态学处理进行图像预处理，去除背景干扰，提取堆叠货箱区域图像，基于改进Canny算法对堆叠货箱进行边缘检测，根据堆叠货箱边缘特征进行筛选并基于最小二乘法进行直线拟合，解决边缘线条不连续和虚假边缘问题，对边缘进行区域化处理，以此将堆叠货箱分割成独立的货箱区域，提取每个独立货箱的最小外接矩形，得到货箱中心点的位置信息。实验结果表明，该方法对堆叠货箱有很好的分割效果，定位精度小于5 mm，满足定位精度要求。

Segmentation and Location Method of Stacked Containers Based on Improved Canny Edge Detection

In order to improve the automation level of container unloading,aiming at the problem that stacked containers are difficult to be segmented and located,a segmented location method of stacked containers based on improved Canny edge detection is proposed.The image is preprocessed by threshold segmentation and morphological processing to remove background interference and extract the image of stacked containers.The edge detection of stacked containers is carried out based on the improved Canny algorithm.The edge features of stacked containers are screened and the linear fitting is carried out based on the least square method to solve the problems of discontinuous edge lines and false edges.By regionalizing the edges,the stacked containers are divided into independent container areas,and the minimum external rectangle of each independent container is extracted to obtain the location of the center point of the container.The experimental results show that this method has a good segmentation effect on stacked containers,and the positioning accuracy is less than 5 mm,which meets the requirements of positioning accuracy.