Zobrazeno 1 - 10
of 116
pro vyhledávání: '"Weimin LEI"'
Publikováno v:
IET Image Processing, Vol 18, Iss 6, Pp 1475-1490 (2024)
Abstract Despite the existence of various super‐resolution (SR) methods, most of them focus on designing models for specific upscaling factors rather than fully exploiting inter‐scale correlation to improve efficiency. In contrast, multi‐scale
Externí odkaz:
https://doaj.org/article/d19d655efacd481081271499a8018a98
Publikováno v:
IET Image Processing, Vol 17, Iss 4, Pp 1097-1110 (2023)
Abstract Compared with convolutional operation, non‐local operation can directly capture long‐range dependencies and thus has a larger receptive field. However, the computation and memory consumption of non‐local operation is much higher than c
Externí odkaz:
https://doaj.org/article/11e6122cbafe4571b7d9aa3a84f2ddef
Publikováno v:
Tongxin xuebao, Vol 44, Pp 129-141 (2023)
To solve the problems that the background reference frames are seriously contaminated by the foreground, and the bit rate increases suddenly incurred by the one-time transmission of the background frames, a progressive background frame generation met
Externí odkaz:
https://doaj.org/article/00867f34894b423a9e7acfad795e252e
Publikováno v:
Tongxin xuebao, Vol 43, Pp 194-208 (2022)
Traditional video compression technology based on pixel correlation has limited performance improvement space, semantic compression has become the new direction of video compression coding, and video image reconstruction is the key link of semantic c
Externí odkaz:
https://doaj.org/article/bcae8238b3c94682a2c4424525344567
Publikováno v:
Symmetry, Vol 15, Iss 12, p 2145 (2023)
Multi-camera video surveillance has been widely applied in crowd statistics and analysis in smart city scenarios. Most existing studies rely on appearance or motion features for cross-camera trajectory tracking, due to the changing asymmetric perspec
Externí odkaz:
https://doaj.org/article/7214af3425a74b30980d1ee0326a1e90
Publikováno v:
Frontiers in Neurorobotics, Vol 16 (2023)
We present a dual-flow network for autonomous driving using an attention mechanism. The model works as follows: (i) The perception network extracts red, blue, and green (RGB) images from the video at low speed as input and performs feature extraction
Externí odkaz:
https://doaj.org/article/461153b996084b718d0e6d1865c9c3e4
Publikováno v:
Sensors, Vol 23, Iss 18, p 7805 (2023)
Crowd counting, as a basic computer vision task, plays an important role in many fields such as video surveillance, accident prediction, public security, and intelligent transportation. At present, crowd counting tasks face various challenges. Firstl
Externí odkaz:
https://doaj.org/article/17bc26ccbb924278b73f3c3e009d76d4
Publikováno v:
IEEE Access, Vol 8, Pp 93962-93977 (2020)
It is still a challenging task to provide satisfactory quality of experience (QoE) to users by traditional routing mechanism in current public Internet for real-time multimedia services with high bandwidth and strict end-to-end latency constraint. Mu
Externí odkaz:
https://doaj.org/article/e76a651084034e60953ad0dbfe78362b
Publikováno v:
IEEE Access, Vol 8, Pp 224283-224291 (2020)
A channel frequency response estimation method based on weighted twin support vector regression (TSVR) for pilot-aided multi-input multi-output (MIMO) orthogonal frequency division multiplexing (OFDM) system is proposed in this work. Nonlinearity of
Externí odkaz:
https://doaj.org/article/8633d4b69fdd43c289e380bce91c4cbe
Publikováno v:
IEEE Access, Vol 7, Pp 59758-59770 (2019)
Real time video traffic has stringent delay requirement and is bandwidth demanding when streaming over the internet. Single path transmission may provide unsatisfactory picture quality to users due to packet loss, jitter, and low bandwidth. Multipath
Externí odkaz:
https://doaj.org/article/7f9c48441e1f4a0486a9a52aa1518607