【摘要】 无人汽车以多传感器测量数据融合的方法实现环境感知。针对数据融合中三维激光雷达和双目相机坐标系联合标定问题,提出一种基于空间圆心的联合标定方法。首先通过棋盘格标定板得到双目相机的内外参数,然后使用激光雷达和双目相机同时检测圆孔标定板中的圆心坐标,进行粗标定计算激光雷达坐标系变换到摄像机坐标系的平移矩阵,最后通过中心化的特征点集对旋转平移矩阵进行优化。实验结果表明,该方法只需采集3次数据就可以实现联合标定,简化了标定过程。平均标定误差为1.86像素,标准差为0.41像素,证明其结果准确可靠。更多还原

【Abstract】 The method of multi-sensor measurement data fusion is used by unmanned vehicles to realize environment perception. Aiming at the problem of joint calibration of 3D lidar and stereo camera coordinate system in data fusion,a joint calibration method based on space center is proposed.First,the internal and external parameters of the stereo camera are obtained through the checkerboard calibration board. Then,the laser radar and the stereo camera are used to detect the center coordinates of the circle hole calibration plate at the same time,and the rough calibration is performed to calculate the translation matrix from the laser radar coordinate system to the camera coordinate system. Finally,the rotation and translation matrix is optimized through the centralized feature point set. Experimental results show that the average calibration error of this method is 1.86 pixels,and the standard deviation is 0.41 pixels. The results of the proposed method are accurate and reliable,and the joint calibration can be realized only by collecting three data,which simplifies the calibration process.更多还原