论文部分内容阅读
提出了基于Kinect摄像机的机器视觉测速方法,用于实时的测量运用目标的速度信息。首先,设计出固定在运动目标上的由五个已知位置关系的圆组成的标识物,利用图像处理算法根据标志物的拓扑关系检测出运动目标标志物在Kinect坐标系下的位置;然后,将Kinect坐标系坐标通过坐标变换转换到世界坐标系;最后,根据采样时间内测出的距离求出速度信息。通过以上3步骤,依次解决运动目标检测和运动目标测速问题。理论分析和试验结果表明,本文方法在移动机器人运动或者静止情况下能够处理运动目标作直线运动、原地转动及其合成的曲线运动等不同运动形式下的速度测量,应用范围广泛,计算实时性和准确性高。
A Kinect camera-based method of machine vision velocity measurement is proposed to measure the velocity of the target in real time. First of all, we design a marker that is fixed on the moving target and consists of five circles with known positions, and use the image processing algorithm to detect the position of the moving target marker under the Kinect coordinate system according to the topological relationship of the marker. The coordinates of the Kinect coordinate system are converted to the world coordinate system by coordinate transformation; finally, the velocity information is obtained according to the distance measured during the sampling time. Through the above three steps, in order to solve the moving target detection and moving target speed measurement. The theoretical analysis and experimental results show that the proposed method can deal with the velocity measurement of moving targets in different motion forms such as linear motion, in-situ rotational motion and their synthesized curve motion under the condition of moving or stationary mobile robot. The proposed method can be used in a wide range of applications, And high accuracy.