Multi-face tracking based on spatio-temporal detections

Issue title: Intelligent Computing for Pattern Recognition, Image Processing and Computer Vision Papers from CIARP 2014, November 2-5, 2014, Puerto Vallarta, Jalisco, Mexico

Guest editors: Eduardo Bayro-Corrochano

Article type: Research Article

Authors: Martínez-Díaz, Yoanna^{a; *} | Hernández, Noslen^b | Méndez-Vázquez, Heydi^a

Affiliations: [a] Advanced Technologies Application Center, Playa, Havana, Cuba | [b] Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil

Correspondence: [*] Corresponding author: Yoanna Martínez-Díaz, Advanced Technologies Application Center, 7th A Avenue # 21406 % 214 and 216, Siboney, Playa, P.C. 12200, Havana, Cuba. E-mail:ymartinez@cenatav.co.cu

Abstract: Tracking-by-detection methods have become increasingly popular recently. This work presents a new multi-face tracking algorithm based on the association of detection responses given by a spatio-temporal face detector; which are considered as initial small trajectories or tracklets. An appearance model based on the spatio-termporal information is used to guide the tracker. Besides, a new adaptive Kalman filter that dynamically adjusts its parameters on the basis of the quality of the detector output is proposed. The introduced approach is evaluated on several challenging video sequences from the YouTube Faces database, achieving a very good performance.

Keywords: Face detection, face tracking, data-association, spatio-temporal representation, video

DOI: 10.3233/IDA-160851

Journal: Intelligent Data Analysis, vol. 20, no. s1, pp. S141-S154, 2016