Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Angfan Zhu"'
Publikováno v:
Sensors, Vol 20, Iss 18, p 5086 (2020)
The local reference frame (LRF) acts as a critical role in 3D local shape description and matching. However, most existing LRFs are hand-crafted and suffer from limited repeatability and robustness. This paper presents the first attempt to learn an L
Externí odkaz:
https://doaj.org/article/d8b3453318624cf08e003dbc20b051b8
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 33:59-73
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::69ca5d20c55e23fca39b4abcecca6a4d
https://doi.org/10.1109/tcsvt.2022.3197212
https://doi.org/10.1109/tcsvt.2022.3197212
Publikováno v:
Journal of Electronic Imaging. 31
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c2230d19ee3d96405980121622a3502
https://doi.org/10.1117/1.jei.31.2.023007
https://doi.org/10.1117/1.jei.31.2.023007
Publikováno v:
Information Fusion. 61:24-35
This paper presents a simple yet very effective data-driven approach to fuse both low-level and high-level local geometric features for 3D rigid data matching. It is a common practice to generate distinctive geometric descriptors by fusing low-level
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8498b018b4bb80509388170388f596c2
https://doi.org/10.1016/j.inffus.2020.03.008
https://doi.org/10.1016/j.inffus.2020.03.008
Publikováno v:
Pattern Recognition. 127:108626
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eeef0a7f5b83799220e55de27aa5e4a3
https://doi.org/10.1016/j.patcog.2022.108626
https://doi.org/10.1016/j.patcog.2022.108626
Publikováno v:
ICPR
Existing deep siamese trackers are typically built on off-the-shelf CNN models for feature learning, with the demand for huge power consumption and memory storage. This limits current deep siamese trackers to be carried on resource-constrained device
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de60d308eae7d8d9614d5881349814cf
https://doi.org/10.1109/icpr48806.2021.9412840
https://doi.org/10.1109/icpr48806.2021.9412840
Publikováno v:
MIPPR 2019: Pattern Recognition and Computer Vision.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5007120de45d4b8848bd4aa165cfbdc
https://doi.org/10.1117/12.2538054
https://doi.org/10.1117/12.2538054
Publikováno v:
Intelligent Robotics and Applications ISBN: 9783319975887
ICIRA (2)
ICIRA (2)
Getting depth information by stereo matching is one of the key steps in 3D reconstruct. In many practical applications, there are high requirements for the speed of processing and the accuracy of the results. Many algorithms have obtained good result
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2a5ca1fdedb11a8b8e9e81401fa9db9
https://doi.org/10.1007/978-3-319-97589-4_32
https://doi.org/10.1007/978-3-319-97589-4_32
