Markerless Augmented Advertising for Sports Videos
This addresses the need for automated, aesthetic advertising in live sports broadcasts to potentially eliminate commercial breaks, though it appears incremental as it builds on existing computer vision techniques.
The paper tackles the problem of automatically overlaying advertisements onto sports videos without markers or camera calibration, achieving seamless integration by building a 3D scene representation and using homography-based tracking for perspective-correct placement across video clips.
Markerless augmented reality can be a challenging computer vision task, especially in live broadcast settings and in the absence of information related to the video capture such as the intrinsic camera parameters. This typically requires the assistance of a skilled artist, along with the use of advanced video editing tools in a post-production environment. We present an automated video augmentation pipeline that identifies textures of interest and overlays an advertisement onto these regions. We constrain the advertisement to be placed in a way that is aesthetic and natural. The aim is to augment the scene such that there is no longer a need for commercial breaks. In order to achieve seamless integration of the advertisement with the original video we build a 3D representation of the scene, place the advertisement in 3D, and then project it back onto the image plane. After successful placement in a single frame, we use homography-based, shape-preserving tracking such that the advertisement appears perspective correct for the duration of a video clip. The tracker is designed to handle smooth camera motion and shot boundaries.