Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Mashhour Solh"'
Publikováno v:
Proceedings of the ACM Southeast Conference.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::17bb48681a7e39d17751414a854bb807
https://doi.org/10.1145/3476883.3524048
https://doi.org/10.1145/3476883.3524048
Publikováno v:
ICIP
This paper presents an approach to pedestrian detection in thermal infrared (thermal) images with limited annotations. The key idea is to adapt the abundance of color images associated with bounding box annotations to the thermal domain for training
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::add33ff97a54a898f2e1d4749bd8ba6a
https://doi.org/10.1109/icip.2019.8803104
https://doi.org/10.1109/icip.2019.8803104
Autor:
Mashhour Solh, Ghassan AlRegib
Publikováno v:
IEEE Transactions on Image Processing. 21:3902-3914
Although several subjective and objective quality assessment methods have been proposed in the literature for images and videos from single cameras, no comparable effort has been devoted to the quality assessment of multicamera images. With the incre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c7ea709f30d0b0014574604a184dd9c8
https://doi.org/10.1109/tip.2012.2200490
https://doi.org/10.1109/tip.2012.2200490
Autor:
Ghassan AlRegib, Mashhour Solh
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 6:495-504
Three-dimensional television (3DTV) is believed to be the future of television broadcasting that would replace current 2D HDTV technology. Future 3DTV would bring a more life-like and visually immersive home entertainment experience, in which users w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::04d43dfb0473718ccafb6f1cf0516955
https://doi.org/10.1109/jstsp.2012.2204723
https://doi.org/10.1109/jstsp.2012.2204723
Autor:
Mashhour Solh
Publikováno v:
Computational Imaging
Extending the depth of field using a single lens camera on a mobile device can be achieved by capturing a set of images each focused at a different depth or focal stack then combine these samples of the focal stack to form a single all-in-focus image
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bde3df7f4cf01b48168fa6f7f7080792
https://doi.org/10.1117/12.2042609
https://doi.org/10.1117/12.2042609
Publikováno v:
Visual Information Processing and Communication
In this paper, we propose a method to extract depth from motion, texture and intensity. We first analyze the depth map to extract a set of depth cues. Then, based on these depth cues, we process the colored reference video, using texture, motion, lum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8e7fe5708d2b9bdac854b54d0fc3001a
https://doi.org/10.1117/12.2005161
https://doi.org/10.1117/12.2005161
Autor:
Mashhour Solh
Publikováno v:
2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b0f49a0596d9bb46498b195b0ef5a4e2
https://doi.org/10.1109/acssc.2012.6489350
https://doi.org/10.1109/acssc.2012.6489350
Autor:
Mashhour Solh, Ghassan AlRegib
Publikováno v:
ACSCC
We propose a new view synthesis without using a depth map for stereoscopic images with small baseline. The new technique utilizes the linear relationship between local luminance changes and small horizontal shifts in an image. In this paper, we prove
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d90e6a7491acdf0a9af33e3f6a5e6537
https://doi.org/10.1109/acssc.2012.6489330
https://doi.org/10.1109/acssc.2012.6489330
Publikováno v:
ACSCC
We propose a method to reconstruct the depth map from multiple estimated depth maps relying on monocular cues. Based on extracted depth cues from luminance, chrominance, motion and texture, we obtain an optimal depth estimation by analytically derivi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d68a65e02b2910050ccd8b255704c8f0
https://doi.org/10.1109/acssc.2012.6489108
https://doi.org/10.1109/acssc.2012.6489108
Autor:
Ghassan AlRegib, Mashhour Solh
Publikováno v:
Three-Dimensional Image Processing (3DIP) and Applications
In this paper we introduce a depth adaptive approach for disocclusion removal in depth image-based rendering (DIBR). This approach extends the hierarchical hole-filling (HHF) presented in an earlier work. Similar to HHF, the depth adaptive approach r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6c580a8e6f9799a22ebf6167bbd0da7
https://doi.org/10.1117/12.906892
https://doi.org/10.1117/12.906892