以視覺模型為輔助且適用於網球影片之虛擬探照游移廣告系統

Abstract

如何在有限的干擾下，於運動影片中置入廣告並使廣告效益最大化已被公認是一個極具挑戰性的問題。在這篇論文中，我們提出了一種嶄新的廣告策略，稱之為虛擬探照游移廣告 (virtual spotlighted advertising, ViSA)，並將其實作、應用於網球影片。這種廣告策略應用了包含心理學、廣告行銷、計算美學在內的相關學理，藉以達到提昇廣告效果及降低干擾的目的。我們實作出的系統，能自動找尋觀看者較感興趣的時間、空間，並選出最具廣告溝通效果的區域，將虛擬廣告投影於網球場上。同時，為了降低置入廣告造成的干擾，廣告會經過適當的色彩和諧化(color harmonization)，使其與網球場顏色更加融洽。除此之外，我們也利用人類視覺模型(human visual system model, HVS model)為輔助，調整廣告出現的透明度。實驗結果顯示，我們的系統能在不影響觀看者欣賞球賽的情況下，有效地讓觀看者對置入的廣告擁有不錯的回憶度及辨識度，並且干擾程度在可接受的範圍之內。我們認為這種廣告策略，能有效提昇廣告效果且能廣泛應用於其它運動影片之中。

With the constraint of limited intrusiveness, maximizing the advertising efficiency in sports video has been known as a challenging problem. In this thesis, 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 non-uniform 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.