def getPCandBBfromPandas(self, box, calib):
center = [box["x"], box["y"] - box["height"] / 2, box["z"]]
size = [box["width"], box["length"], box["height"]]
orientation = Quaternion(
axis=[0, 1, 0], radians=box["rotation_y"]) * Quaternion(
axis=[1, 0, 0], radians=np.pi / 2)
Using this function to convert point cloud coordinates to camera coordinates,the orientation use to move the cut point cloud to the origin of the camera coordinate system and turn it in a positive direction,I think orientation = Quaternion(axis=[0, 1, 0], radians=box["rotation_y"]) is ok,so why you choose to multiply Quaternion(axis=[1, 0, 0], radians=np.pi / 2)
def getPCandBBfromPandas(self, box, calib): center = [box["x"], box["y"] - box["height"] / 2, box["z"]] size = [box["width"], box["length"], box["height"]] orientation = Quaternion( axis=[0, 1, 0], radians=box["rotation_y"]) * Quaternion( axis=[1, 0, 0], radians=np.pi / 2) Using this function to convert point cloud coordinates to camera coordinates,the orientation use to move the cut point cloud to the origin of the camera coordinate system and turn it in a positive direction,I think orientation = Quaternion(axis=[0, 1, 0], radians=box["rotation_y"]) is ok,so why you choose to multiply Quaternion(axis=[1, 0, 0], radians=np.pi / 2)