python中cv2.projectPoints的用法小结

我们先看一下c++ 中的参数解释

第一个输入的点是一个, (N, 3) 维的 三维坐标系中的点, xyz

第二个是旋转向量,

第三个是平移向量.

第四个是相机内参,

第KrgZyewB五个是相机的畸变系数, 如果输入是4个时, 就是[k1, k2, p1, p2], 输入5个时就是 [k1, k2, p1, p2, k3], 也可以是更多, [k1, k2, p1, p2, k3, k4, k5, k6]

实战在python里面, 我用lidar的点往图像上投影的时候是python这么用的(lidar上的3d框, 即8个点.)

    rotation = lidar2camera_pose[:3, :3]
    translation = lidar2camera_pose[:3, 3]
    dist = np.array(camera_disinfo)
    imagePoints, _ = cv2.projectPoints(lidar_points, rotation, translation, camera_K, dist)
    imagePoints = np.reshape(imagePoints, (8, 2))
    maxrect = cv2.boundingRect(imagePoints.astype(int))

但是这样做无法把相机后面的点给排除掉, 所以可以这样改

 lidar_points = np.dot(lidar2camera_pose[:3, :3], lidar_points.T).T + lidar2camera_pose[:3, [3]].reshape(1, 3)
    lidar_points = lidar_points[pythonlidar_points[:, 2]>0]
    if len(lidar_points) < 8:
        return None
    ro编程tation = np.eye(3)
    translation = np.zeros((3, 1))
    dist = np.array(camera_disinfo)
    imagePoints, flag = cv2.proje编程客栈ctPoints(lidar_points, rotation, translation, camera_K, dist)
    imagePoints = np.reshape(imagePoints, (8, 2))
    maxrect = cv2.boundingRect(imagePoints.astype(int))

到此这篇关于python中cv2.projectPoints的用法的文章就介绍到这了,更多相关python cv2.projectPoints用法内容请搜索编程客栈(www.devze.com)以前的文章或继续浏览下面的相关文章希望大家以后多多支持编程客栈(www.devze.com)！