Virtual ads insertion in street building views for augmented reality

Abstract

This paper is proposing a new framework of virtual ads insertion for Augmented Reality (AR) in a specific real scene, building facades of the street view videos. In this framework, specific region detection, camera orientation estimation, visual tracking, motion filtering and virtual-real blending are discussed. For the building façade, vanishing points are fully identified to detect a rectangular planar structure. Meanwhile, dynamic registration and color harmonization are designed to improve visual acuity of virtual ads insertion. Experimental results are given to show the good performance of the proposed framework.

SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities

“…In consequence, this is one of the most cost-effective forms of advertising available. Moreover, since current smartphones are equipped with a variety of embedded sensors like cameras, GPS or 3G/4G/5G, it is possible to get closer to the final user via a variety of Augmented Reality (AR) applications [ 5 ]. This way, the citizens using their smartphones can better develop and, perhaps, enjoy the contents associated with urban advertisements.…”

“…Some other related applications to be considered here are text and objects detection inside segmented billboard images [ 10 ] or the localization of billboards on streamed sport videos [ 11 ]. Another investigated problem is the insertion of virtual ads in street images based on localization of specific regions on them (e.g., buildings facades) [ 5 ]. Hussain et al in [ 12 ] more recently have worked on how to build vision systems so they can understand ads, and these authors have presented a solution for automatically understanding the advertisement content.…”