Zobrazeno 1 - 10
of 4 346
pro vyhledávání: '"superpixel"'
Autor:
Li Yang
Publikováno v:
Open Computer Science, Vol 14, Iss 1, Pp 44-52 (2024)
Foreground segmentation (FS) plays a fundamental and important role in computer vision, but it remains a challenging task in dynamic backgrounds. The supervised method has achieved good results, but the generalization ability needs to be improved. To
Externí odkaz:
https://doaj.org/article/e9647f0e17044d0b9031d9c9c8ce0e4d
Publikováno v:
Heliyon, Vol 10, Iss 14, Pp e34711- (2024)
The progressive evolution of the spatial and temporal resolutions of Earth observation satellites has brought multiple benefits to scientific research. The increasing volume of data with higher frequencies and spatial resolutions offers precise and t
Externí odkaz:
https://doaj.org/article/13088e135bf649a5a9e7d0eacc77f099
Autor:
Guangpu Dang, Zhongan Mao, Tingyu Zhang, Tao Liu, Tao Wang, Liangzhi Li, Yu Gao, Runqing Tian, Kun Wang, Ling Han
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-12 (2024)
Abstract Deep neural networks combined with superpixel segmentation have proven to be superior to high-resolution remote sensing image (HRI) classification. Currently, most HRI classification methods that combine deep learning and superpixel segmenta
Externí odkaz:
https://doaj.org/article/20c77aaa61c84c9aba668cbf0526f4f7
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 15746-15760 (2024)
The pervasive presence of mixed pixels in hyperspectral remote sensing imagery poses a substantial constraint on the quantitative progress of remote sensing technology. Hyperspectral unmixing (HU) techniques serve as effective means to address this i
Externí odkaz:
https://doaj.org/article/87c406cb9b2a43128b362679e3d5c545
Autor:
Wang Fuzhi, Song Changlin
Publikováno v:
IEEE Access, Vol 12, Pp 100086-100101 (2024)
Deep convolutional neural networks(DCNN) has recently significantly pushed the state of the art of semantic image segmentation. However, as the network depth increases, the progressively lower resolution leads to a loss of feature information and a l
Externí odkaz:
https://doaj.org/article/c73485211c2248e5830aace0eb7374ce
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 9503-9516 (2024)
This study provides the first long-time series of spatial and temporal distributions for small lakes in the Larsemann Hills (69°23′S, 76°20′E) in the East Antarctic. In the Larsemann oasis, there is a significant number of over 150 small lakes,
Externí odkaz:
https://doaj.org/article/b793638296eb4cf0810eae23f365737f
Publikováno v:
IEEE Photonics Journal, Vol 16, Iss 2, Pp 1-5 (2024)
Realizing a spatial phase modulation (SPM) from 0 to 2π is vital for achieving precise light field manipulation, when the phase-only spatial light modulator (SLM) is driven by the voltage. However, insufficient bias voltage degrades the quality of t
Externí odkaz:
https://doaj.org/article/e273096cab5446059a816bb84fbdde8c
Autor:
Xiaoli Li, Jinsong Chen, Longlong Zhao, Hongzhong Li, Jin Wang, Luyi Sun, Shanxin Guo, Pan Chen, Xuemei Zhao
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 7621-7639 (2024)
Superpixel segmentation is an essential step of object-oriented remote sensing image classification; the accuracy of the superpixel segmentation boundary will directly affect the classification result. Most of the traditional superpixel segmentation
Externí odkaz:
https://doaj.org/article/63e2200c5fb949428aebb49d911fba79
Publikováno v:
IEEE Access, Vol 12, Pp 6615-6627 (2024)
Saliency detection is increasingly a crucial task in the computer vision area. In previous graph-based saliency detection, superpixels are usually regarded as the primary processing units to enhance computational efficiency. Nevertheless, most method
Externí odkaz:
https://doaj.org/article/5b7b10d4fb3942e4bc8a218edec60b47
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 17, Pp 5580-5593 (2024)
Using object-based deep learning for the urban land cover classification has become a mainstream method. This study proposed an urban land cover classification method based on segments’ object features, deep features, and spatial association featur
Externí odkaz:
https://doaj.org/article/c97a81c957c84d2189357cff7cf68923