论文部分内容阅读
利用光纤镜头和彩色工业摄像机实时采集激光切割厚板中切割点的图像,从彩色图像中分别选取蓝色、绿色和红色通道图像,分析各通道图像的特点和切割点的几何形状特征。首先以激光焦点在图像中的位置为中心建立坐标系,以x轴方向为起始,45°为间隔向8个方向搜索激光切割区域的边缘点,根据边缘点到坐标原点的距离信息确定激光切割方向和切割顶点;建立边缘识别用抛物线模型,根据边缘处存在灰度特征、梯度特征和方向特征设计识别目标函数,识别切割顶点两侧边缘,进而识别整个切割点处的几何形状。实验表明识别方法具有良好的适应性、准确性和实时性。
The real-time acquisition of the image of the cutting point in the laser-cut slab using a fiber lens and a color industrial camera selects the blue, green and red channel images from the color images respectively and analyzes the characteristics of each channel image and the geometric features of the cutting points. Firstly, the coordinate system is established with the focus of the laser in the image as the center. The x-axis direction is taken as the starting point, and the edge of the laser cutting area is searched in 8 directions at 45 ° intervals. The laser is determined according to the distance information from the edge point to the coordinate origin Cutting direction and cutting apex. A parabola model for edge recognition is established. According to the existence of the gray, gradient and directional features at the edge, an objective function is designed to identify the edges on both sides of the cutting apex and identify the geometry at the entire cutting point. Experiments show that the recognition method has good adaptability, accuracy and real-time.