Thesis Details
Určení azimutu natočení hlavy v záznamu bezpečnostní kamerou
This thesis attempts to create an application to determine head rotation angle in video recorded from a security camera. The application consists of three parts: face detection, facial landmarks detection and determination of person's head rotation. The face detection has been implemented using Viola-Jones and HOG algorithms. Facial landmarks detection has been done using algorithm based on active shape model. Two methods to calculate the head rotation angles have been used: the first method works with anthropometric head features. The second method uses Perspective-n-Point algorithm to find the right rotation angles. Finally, all algorithms implemented have been tested and the proper parameters have been determined.
CCTV, CCD, CMOS, face detection, Viola-Jones, HOG, Active Shape Model, Active Appearance Model, head rotation assessment, head anthropometry, Perspective-n-Point
Janoušek Vladimír, doc. Ing., Ph.D. (DITS FIT BUT), člen
Sedlák Petr, doc. Ing., Ph.D. (DPHYS FEEC BUT), člen
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT), člen
Španěl Michal, Ing., Ph.D. (DCGM FIT BUT), člen
Vašíček Zdeněk, doc. Ing., Ph.D. (DCSY FIT BUT), člen
@mastersthesis{FITMT20088, author = "Ond\v{r}ej Blucha", type = "Master's thesis", title = "Ur\v{c}en\'{i} azimutu nato\v{c}en\'{i} hlavy v z\'{a}znamu bezpe\v{c}nostn\'{i} kamerou", school = "Brno University of Technology, Faculty of Information Technology", year = 2017, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/20088/" }