Title :
A Novel Viewer Counter for Digital Billboards
Author :
Chen, Duan-Yu ; Lin, Kuan-Yi
Author_Institution :
Dept. of Electr. Eng., Yuan Ze Univ., Chungli, Taiwan
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.
Keywords :
face recognition; feature extraction; image classification; image sensors; learning (artificial intelligence); AdaBoost; digital billboard; electronic billboard; feature extraction; frontal face detection technique; occlusion; online classifier; real time video stream; robust viewer recognition; stationary camera; viewer counter; Computer vision; Counting circuits; Data mining; Face detection; Feature extraction; Filtering; Merchandise; Robustness; Smart cameras; Torso; viewer counting;
Conference_Titel :
Intelligent Information Hiding and Multimedia Signal Processing, 2009. IIH-MSP '09. Fifth International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4244-4717-6
Electronic_ISBN :
978-0-7695-3762-7
DOI :
10.1109/IIH-MSP.2009.211
