Pregled bibliografske jedinice broj: 785338
Towards Reversible De-Identification in Video Sequences Using 3D Avatars and Steganography
Towards Reversible De-Identification in Video Sequences Using 3D Avatars and Steganography // Proceedings of the Croatian Computer Vision Workshop, Year 3 / Lončarić, Sven ; Krapac, Josip (ur.).
Zagreb: Fakultet elektrotehnike i računarstva Sveučilišta u Zagrebu, 2015. str. 9-15 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 785338 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Towards Reversible De-Identification in Video Sequences Using 3D Avatars and Steganography
Autori
Blažević, Martin ; Brkić, Karla ; Hrkać, Tomislav
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of the Croatian Computer Vision Workshop, Year 3
/ Lončarić, Sven ; Krapac, Josip - Zagreb : Fakultet elektrotehnike i računarstva Sveučilišta u Zagrebu, 2015, 9-15
Skup
Fourth Croatian Computer Vision Workshop
Mjesto i datum
Zagreb, Hrvatska, 22.09.2015
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
reversible de-identification; 3D avatars; steganography
Sažetak
We propose a de-identification pipeline that protects the privacy of humans in video sequences by replacing them with rendered 3D human models, hence concealing their identity while retaining the naturalness of the scene. The original images of humans are steganographically encoded in the carrier image, i.e. the image containing the original scene and the rendered 3D human models. We qualitatively explore the feasibility of our approach, utilizing the Kinect sensor and its libraries to detect and localize human joints. A 3D avatar is rendered into the scene using the obtained joint positions, and the original human image is steganographically encoded in the new scene. Our qualitative evaluation shows reasonably good results that merit further exploration.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo