Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Serhan Gül"'
Autor:
Thomas Schierl, Cornelius Hellge, Marc A. Kastner, Sebastian Bosse, Dimitri Podborski, Jan Zahálka, Serhan Gül
Publikováno v:
ACM Multimedia
In our MM'20 paper,, we presented a Kalman filter-based approach for prediction of head motion in 6DoF. The proposed approach was employed in our cloud-based volumetric video streaming system to reduce the interaction latency experienced by the user.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b3cbaa13184e486bf3e1caaca88f8fe4
https://doi.org/10.1145/3474085.3477936
https://doi.org/10.1145/3474085.3477936
Publikováno v:
ACM Multimedia
Volumetric video allows viewers to experience highly-realistic 3D content with six degrees of freedom in mixed reality (MR) environments. Rendering complex volumetric videos can require a prohibitively high amount of computational power for mobile de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6ae41a4eb294bd23e6d925a0501e1170
http://arxiv.org/abs/2007.14084
http://arxiv.org/abs/2007.14084
Autor:
Jangwoo Son, Gurdeep Singh Bhullar, Thomas Buchholz, Thomas Schierl, Cornelius Hellge, Serhan Gül, Dimitri Podborski
Publikováno v:
MMSys
Volumetric video is an emerging technology for immersive representation of 3D spaces that captures objects from all directions using multiple cameras and creates a dynamic 3D model of the scene. However, processing volumetric content requires high am
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::224066a854c41a9130f2aad9da218d6e
https://doi.org/10.1145/3339825.3393583
https://doi.org/10.1145/3339825.3393583
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030129385
GCPR
GCPR
We propose a method for tracking objects in H.264/AVC compressed videos using a Markov Random Field model. Given an initial segmentation of the target object in the first frame, our algorithm applies a graph-cuts-based optimization to output a binary
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1acf2c6c93e9e595c0af82cb401617a5
https://doi.org/10.1007/978-3-030-12939-2_10
https://doi.org/10.1007/978-3-030-12939-2_10
Publikováno v:
ICIP
In low light or short-exposure photography the image is often corrupted by noise. While longer exposure helps reduce the noise, it can produce blurry results due to the object and camera motion. The reconstruction of a noise-less image is an ill pose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a047a779525f3ba0131ed1b79fbfd63
Publikováno v:
MMSP
In this paper we present a compressed-domain object tracking algorithm for H.264/AVC compressed videos and integrate the proposed algorithm into an indoor vehicle tracking scenario at a car park. Our algorithm works by taking an initial segmentation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a01d9af6e6ded0205ab6f9d7b396ab9f
https://doi.org/10.1109/mmsp.2018.8547120
https://doi.org/10.1109/mmsp.2018.8547120
Autor:
Serhan Gül, Daniel Becker, Ilja Radusch, Oliver Sawade, Cornelius Hellge, Matthias Schmidt, Fernando Bombardelli da Silva
Publikováno v:
MMSys
Modern driver assistance systems enable a variety of use cases which rely on accurate localization information of all traffic participants. Due to the unavailability of satellite-based localization, the use of infrastructure cameras is a promising al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::530d85444f47d396a539bf451294d5d4
https://doi.org/10.1145/3204949.3208117
https://doi.org/10.1145/3204949.3208117
Autor:
Serhan Gül
Publikováno v:
Adnan Menderes Üniversitesi Sosyal Bilimler Enstitüsü Dergisi. 1:89-98
Derrida, dilbilimi ve felsefe arasinda kurdugu kopruyle, felsefenin iletisimsel bir faaliyet olarak yeniden kurgulanmasi kadar, post-yapisalci ile tarihsel olan arasindaki iliskiyi onararak, dusunsel dunyada buyuk bir cigir acar. Dilbilimi ve fonoloj
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d072aaa7022768991fa1586fd11d23ed
https://doi.org/10.30803/adusobed.188820
https://doi.org/10.30803/adusobed.188820
Autor:
Wojciech Samek, Jan Meyer, Sebastian Bosse, Vignesh Srinivasan, Serhan Gül, Cornelius Hellge, Thomas Schierl
Publikováno v:
EUVIP
This paper investigates the robustness of two state-of-theart action recognition algorithms: a pixel domain approach based on 3D convolutional neural networks (C3D) and a compressed domain approach requiring only partial decoding of the video, based
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ae1fec2a476fd69464f2b001a5d49d3f
https://doi.org/10.1109/euvip.2016.7764584
https://doi.org/10.1109/euvip.2016.7764584
Publikováno v:
MMSP
In this paper we propose a hybrid tracking method which detects moving objects in videos compressed according to H.265/HEVC standard. Our framework largely depends on motion vectors (MV) and block types obtained by partially decoding the video bit st
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd3533ebe584659f14df70aca860a9d0
https://doi.org/10.1109/mmsp.2016.7813363
https://doi.org/10.1109/mmsp.2016.7813363