Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Gi-Mun Um"'
Publikováno v:
IEEE Access, Vol 12, Pp 160254-160266 (2024)
Although there are many advantages (e.g., occlusion-robust properties) to be gained by using multi-view inputs for human mesh reconstruction, relatively few studies have been conducted due to the complexity of the fusion process. In this paper, we de
Externí odkaz:
https://doaj.org/article/b600cd7bb6cd4d70bae71d1b1561818b
Publikováno v:
ETRI Journal, Vol 44, Iss 1, Pp 62-72 (2021)
In this study, we propose a multi-GPU-based 8KVR stitching system that operates in real time on both local and cloud machine environments. The proposed system first obtains multiple 4 K video inputs, decodes them, and generates a stitched 8KVR video
Externí odkaz:
https://doaj.org/article/81e2fa1490624e01a9ab3f3da3479ca5
Publikováno v:
Sensors, Vol 21, Iss 19, p 6680 (2021)
In this paper, we propose a multi-view stereo matching method, EnSoft3D (Enhanced Soft 3D Reconstruction) to obtain dense and high-quality depth images. Multi-view stereo is one of the high-interest research areas and has wide applications. Motivated
Externí odkaz:
https://doaj.org/article/ba56920a988f4b518d08f3e4a301718a
Autor:
Mi-Gyeong Gwon, Jinhee Kim, Gi-Mun Um, HeeKyung Lee, Jeongil Seo, Seong-Yong Lim, Seung-Jun Yang, Wonjun Kim
Publikováno v:
IEIE Transactions on Smart Processing & Computing. 11:24-33
Publikováno v:
IEEE Transactions on Multimedia. :1-12
Publikováno v:
ETRI Journal. 44:62-72
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197864
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f648d646a5a7ce42e689c4378c5f1793
https://doi.org/10.1007/978-3-031-19787-1_4
https://doi.org/10.1007/978-3-031-19787-1_4
Publikováno v:
ICTC
In the MPEG-VCM framework, an efficient video coding technique while maintaining task performance such as object segmentation is required. In this paper, we introduce the MPEG- VCM framework and show some results of VCM anchor generation on Cityscape
Publikováno v:
BigComp
We present an moving object performance analysis system using multi-camera video and position sensors. The proposed system firstly adopted a multi-camera video based tracking technique with moving object identification. Moreover, technology for more
Publikováno v:
BMSB
We present an ice hockey player tracking and identification system based on the videos acquired from multiple camera system. The proposed system reduces tracking errors by global tracking with multi-camera video and player identification using SVM (s