Zobrazeno 1 - 10
of 52
pro vyhledávání: '"Honge Ren"'
Publikováno v:
Sensors, Vol 24, Iss 10, p 3130 (2024)
Fine-grained representation is fundamental to species classification based on deep learning, and in this context, cross-modal contrastive learning is an effective method. The diversity of species coupled with the inherent contextual ambiguity of natu
Externí odkaz:
https://doaj.org/article/944102552a7c474bbe97135d8260f5bf
Publikováno v:
Drones, Vol 8, Iss 5, p 181 (2024)
Unmanned aerial vehicle (UAV) aerial images often present challenges such as small target sizes, high target density, varied shooting angles, and dynamic poses. Existing target detection algorithms exhibit a noticeable performance decline when confro
Externí odkaz:
https://doaj.org/article/c80de82169404d5cb7ad5fd59a63e09d
Publikováno v:
Sensors, Vol 22, Iss 19, p 7408 (2022)
To solve the insufficient ability of the current Thermal InfraRed (TIR) tracking methods to resist occlusion and interference from similar targets, we propose a TIR tracking method based on efficient global information perception. In order to efficie
Externí odkaz:
https://doaj.org/article/057057c1ca074816b87f0b4d593d4e18
Publikováno v:
Applied Sciences, Vol 11, Iss 16, p 7639 (2021)
With the wide increase in global forestry resources trade, the demand for wood is increasing day by day, especially rare wood. Finding a computer-based method that can identify wood species has strong practical value and very important significance f
Externí odkaz:
https://doaj.org/article/95100051384647b1924b2df9abef30f2
Publikováno v:
Sensors, Vol 21, Iss 17, p 5800 (2021)
It is difficult to achieve all-weather visual object tracking in an open environment only utilizing single modality data input. Due to the complementarity of RGB and thermal infrared (TIR) data in various complex environments, a more robust object tr
Externí odkaz:
https://doaj.org/article/5c5db8360ef0403e89e2862a545cc0de
Publikováno v:
Sensors, Vol 20, Iss 18, p 5374 (2020)
Most trackers focus solely on robustness and accuracy. Visual tracking, however, is a long-term problem with a high time limitation. A tracker that is robust, accurate, with long-term sustainability and real-time processing, is of high research value
Externí odkaz:
https://doaj.org/article/1e6bcff85c8e4a1796f658be463d69d4
Publikováno v:
Scientific Programming, Vol 2021 (2021)
In this digital era of technology and software development tools, low-cost digital cameras and powerful video editing software (such as Adobe Premiere, Microsoft Movie Maker, and Magix Vegas) have become available for any common user. Through these s
Publikováno v:
Electronics; Volume 11; Issue 4; Pages: 540
Activation functions are crucial in deep learning networks, given that the nonlinear ability of activation functions endows deep neural networks with real artificial intelligence. Nonlinear nonmonotonic activation functions, such as rectified linear
Publikováno v:
Applied Sciences, Vol 11, Iss 7639, p 7639 (2021)
Applied Sciences
Volume 11
Issue 16
Applied Sciences
Volume 11
Issue 16
With the wide increase in global forestry resources trade, the demand for wood is increasing day by day, especially rare wood. Finding a computer-based method that can identify wood species has strong practical value and very important significance f
Publikováno v:
Connection Science. 32:1-15
For the sake of enhancing the identification ability of current network and meeting the needs of the high accuracy of distinguishing similar small objects (foliage) in the complex scenes, this pape...