The invention relates to an ORB (object request broker) operator-based reference-free video smoothness evaluation method. The method comprises the following steps: taking continuous n frames of images of a video, and extracting ORB feature points from the n frames of images; matching the ORB feature points in every two adjacent frames of images; screening and removing the mismatched ORB feature points of two adjacent frames of images; generating an affine transformation matrix between every two adjacent frames of images, namely a homography matrix between every two adjacent frames of images, according to a motion affine transformation model, and gradually performing iterative solution on the homography matrix A; calculating motion parameters between every two adjacent frames of images, wherein the motion parameters comprise translation and rotation angels of the images; generating a translational motion trajectory and a rotary motion trajectory of a video sequence; performing filtering processing on the translational motion trajectory and the rotary motion trajectory by utilizing a Gauss filter to obtain a filtered translational motion trajectory and a filtered rotary motion trajectory; calculating a transitional jitter number and a rotary jitter number, calculating a horizontal smoothness value and a rotary smoothness value, and judging the smoothness of the video.