Localizing Adverts in Outdoor Scenes
This addresses the cumbersome and time-consuming task for advertisement and marketing agencies in automating ad localization in videos, though it is incremental as it applies existing neural network methods to a new domain.
The paper tackles the problem of manually localizing advertisements in online videos by proposing DeepAds, a deep neural network based on an encoder-decoder architecture, which achieves the best performance in localizing billboards in outdoor scenes on a public dataset.
Online videos have witnessed an unprecedented growth over the last decade, owing to wide range of content creation. This provides the advertisement and marketing agencies plethora of opportunities for targeted advertisements. Such techniques involve replacing an existing advertisement in a video frame, with a new advertisement. However, such post-processing of online videos is mostly done manually by video editors. This is cumbersome and time-consuming. In this paper, we propose DeepAds -- a deep neural network, based on the simple encoder-decoder architecture, that can accurately localize the position of an advert in a video frame. Our approach of localizing billboards in outdoor scenes using neural nets, is the first of its kind, and achieves the best performance. We benchmark our proposed method with other semantic segmentation algorithms, on a public dataset of outdoor scenes with manually annotated billboard binary maps.