ViSA

Abstract

With the constraint of limited intrusiveness, maximizing the advertising efficiency in sports video has been known as a challenging problem. In this paper, we propose a virtual advertisement system with novel advertising strategy, called Virtual Spotlighted Advertising (ViSA), for broadcasting tennis videos. We take psychology, advertising theory, and computational aesthetics into account for improving the effectiveness of advertising. ViSA system automatically detects the candidate insertion points in both temporal and spatial domains and estimates the maximum effective region for message communication. Then, the harmonically re-colored advertisements with foveation model based nonuniform transparency, are projected on the court in tennis videos. The experiments and evaluation results showed the effectiveness of ViSA, for sports video advertising, in terms of recall and recognition.

Markerless Augmented Advertising for Sports Videos

“…An example of the system's output for a video is provided online 6 . In this demonstration, the asset is also a video, thus augmenting the target crowd region with a video overlay.…”

“…ImageSence [25] solves this problem by choosing insertion content according to visual consistency. The authors in [6] work around the problem by harmonizing the asset to be visually consistent with the original content. Liu et al in [20] define intrusiveness as follows: a) if the inserted asset covers the Region of Interest (ROI), it is truly very intrusive, and b) if the asset distracts audience attention from the original attending point, it is also very intrusive.…”

“…It must be noted that a lot of the work briefly reviewed in this section are built around certain very specific use cases (tennis [5,6], soccer [29], baseball [18]), relying heavily on the presence of known, reliable markings on the ground and a rigid sporting-ground structure enabling assets to be integrated seamlessly into the scenery.…”

“…While effective, this approach is laborious and expensive. Alternative methods such as visual attention [6] and visual harmony [20] have been used to reduce human dependency while achieving similar computational aesthetics. In contrast to common video asset overlays that consistently reside in the same position, often resulting in occluding important content information, the work by Mei et al [24] detects non-salient regions in the video before overlaying relevant assets based on textual descriptions.…”