Paper Info
Title
A Novel Viewer Counter for Digital Billboards
Abstract
This paper presents a novel viewer counter for an environment in which a stationary camera can count the number of people watching an electronic billboard without counting the repetitions in real time video streams. The potential buyers actually watching an advertisement or merchandise are captured via frontal face detection techniques. To count the number of viewer precisely, the problem of occlusions between viewers is tackled. Besides, a complementary set of features is extracted from the torso of a viewer due to the fact that the part of the body contains relatively rich discriminative information than other body parts. In addition, for conducting robust viewer recognition, an online classifier trained by AdaBoost is developed. Our experiment results demonstrate the robustness of the proposed system for the viewer counting task.
Year
DOI
Venue
2009
10.1109/IIH-MSP.2009.211
IIH-MSP
Keywords
Field
DocType
novel viewer counter,real time video stream,face recognition,learning (artificial intelligence),experiment result,body part,robust viewer recognition,potential buyer,online classifier,adaboost,image sensors,feature extraction,image classification,viewer counting,proposed system,digital billboards,complementary set,frontal face detection technique,electronic billboard,occlusion,digital billboard,viewer counter,stationary camera,face,data mining,real time,face detection,detectors,learning artificial intelligence,shape
Facial recognition system,Computer vision,AdaBoost,Computer graphics (images),Computer science,Feature extraction,Robustness (computer science),Artificial intelligence,Face detection,Contextual image classification,Classifier (linguistics),Discriminative model
Conference
ISBN
Citations 
PageRank 
978-0-7695-3762-7
0
0.34
References 
Authors
8
2
Name
Order
Citations
PageRank
Duan-Yu Chen129628.79
Kuan-Yi Lin261.77