Publicación:
Face detection on real low resolution surveillance videos
Face detection on real low resolution surveillance videos
No hay miniatura disponible
Fecha
2018
Autores
Cardenas R.J.T.
Castañón C.A.B.
Cáceres J.C.G.
Título de la revista
Revista ISSN
Título del volumen
Editor
Association for Computing Machinery
Proyectos de investigación
Unidades organizativas
Número de la revista
Abstracto
The use of video cameras for security reasons has increased in recent times. Identify a person with automatic face detection systems have greater importance today; but the low-quality of the videos make it difficult and are still an open problem that many researchers are trying to solve. We propose a novel methodology for face detection on low-resolution videos based on parallel Gunnar Farnebäck optical flow algorithm, Haar Cascades and Local Binary Patterns. Our model does not use illumination normalization or super-resolution techniques, commonly used in literature. The results on the Caviar Database prove a better detection rate compared with OpenCv Library, Dlib C++ Library and Matlab function, which use the known Viola-Jones Haar cascade algorithm and HOGs. Even though these tools not have a number of detections up to 1%, our proposal can detect faces in a rate of 50%.
Descripción
This research was supported by CIENCIACTIVA, CONCYTEC and the National University of San Agustin (UNSA). We thank all professors who collaborate in the research.
Palabras clave
Security systems,
Data handling,
Information analysis,
Optical flows