Provided is creating an augmented reality video using a set-top box. The set-top box may include a communication circuit and a processor. The communication circuit may be configured to receive a first video stream including a target object image in real time from a server and to receive a second video stream captured by a user device from the user device. The processor may be configured to: extract the target object image from each frame of the first video stream using WebGL, correct a color of a boundary line of the target object image between the target object and the background, and composite the extracted target object image into an each frame of the second video stream.