Real-Time Acquisition of High Quality Face Sequences from an Active Pan-Tilt-Zoom Camera

Publikation: Forskning - peer reviewKonferenceartikel i proceeding

Abstrakt

Traditional still camera-based facial image acquisition systems in surveillance applications produce low quality face images. This is mainly due to the distance between the camera and subjects of interest. Furthermore, people in such videos usually move around, change their head poses, and facial expressions. Moreover, the imaging conditions like illumination, occlusion, and noise may change. These all aggregate the quality of most of the detected face images in terms of measures like resolution, pose, brightness, and sharpness. To deal with these problems this paper presents an active camera-based real-time high-quality face image acquisition system, which utilizes pan-tilt-zoom parameters of a camera to focus on a human face in a scene and employs a face quality assessment method to log the best quality faces from the captured frames. The system consists of four modules: face detection, camera control, face tracking, and face quality assessment before logging. Experimental results show that the proposed system can effectively log the high quality faces from the active camera in real-time (an average of 61.74ms was spent per frame) with an accuracy of 85.27% compared to human annotated data.

Luk

Detaljer

Traditional still camera-based facial image acquisition systems in surveillance applications produce low quality face images. This is mainly due to the distance between the camera and subjects of interest. Furthermore, people in such videos usually move around, change their head poses, and facial expressions. Moreover, the imaging conditions like illumination, occlusion, and noise may change. These all aggregate the quality of most of the detected face images in terms of measures like resolution, pose, brightness, and sharpness. To deal with these problems this paper presents an active camera-based real-time high-quality face image acquisition system, which utilizes pan-tilt-zoom parameters of a camera to focus on a human face in a scene and employs a face quality assessment method to log the best quality faces from the captured frames. The system consists of four modules: face detection, camera control, face tracking, and face quality assessment before logging. Experimental results show that the proposed system can effectively log the high quality faces from the active camera in real-time (an average of 61.74ms was spent per frame) with an accuracy of 85.27% compared to human annotated data.

OriginalsprogEngelsk
Titel2013 10th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS) : Workshop on Low-Resolution Face Analysis (LRFA 2013)
Antal sider6
ForlagIEEE Press
Publikationsdato27 aug. 2013
Sider443-448
ISBN (Trykt)978-1-4799-0703-8, 9781479907045
ISBN (Elektronisk)9781479907021
DOI
StatusUdgivet - 27 aug. 2013
PublikationsartForskning
Peer reviewJa
BegivenhedAVSS 2013 - Kraków, Polen
Varighed: 27 aug. 201330 aug. 2013

Konference

KonferenceAVSS 2013
LandPolen
ByKraków
Periode27/08/201330/08/2013

Projekter

Download-statistik

Ingen data tilgængelig
ID: 77490522