共 50 条
A Multiscale Spatiotemporal Fusion Network Based on an Attention Mechanism
被引:4
|作者:
Huang, Zhiqiang
[1
,2
]
Li, Yujia
[2
,3
]
Bai, Menghao
[1
,2
]
Wei, Qing
[1
]
Gu, Qian
[1
]
Mou, Zhijun
[1
]
Zhang, Liping
[2
]
Lei, Dajiang
[1
,2
]
机构:
[1] Chongqing Univ Posts & Telecommun, Coll Comp, Chongqing 400065, Peoples R China
[2] Chongqing Univ Posts & Telecommun, Chongqing Key Lab Image Cognit, Chongqing 400065, Peoples R China
[3] Chongqing Univ Posts & Telecommun, Sch Cyber Secur & Informat Law, Chongqing 400065, Peoples R China
基金:
中国国家自然科学基金;
关键词:
spatiotemporal fusion;
multiscale feature fusion;
attention mechanism;
compound loss function;
CONVOLUTIONAL NEURAL-NETWORK;
MODIS;
LANDSAT;
IMAGES;
D O I:
10.3390/rs15010182
中图分类号:
X [环境科学、安全科学];
学科分类号:
08 ;
0830 ;
摘要:
Spatiotemporal fusion is an effective and cost-effective method to obtain both high temporal resolution and high spatial resolution images. However, existing methods do not sufficiently extract the deeper features of the image, resulting in fused images which do not recover good topographic detail and poor fusion quality. In order to obtain higher quality spatiotemporal fusion images, a novel spatiotemporal fusion method based on deep learning is proposed in this paper. The method combines an attention mechanism and a multiscale feature fusion network to design a network that more scientifically explores deeper features of the image for different input image characteristics. Specifically, a multiscale feature fusion module is introduced into the spatiotemporal fusion task and combined with an efficient spatial-channel attention module to improve the capture of spatial and channel information while obtaining more effective information. In addition, we design a new edge loss function and incorporate it into the compound loss function, which helps to generate fused images with richer edge information. In terms of both index performance and image details, our proposed model has excellent results on both datasets compared with the current mainstream spatiotemporal fusion methods.
引用
收藏
页数:18
相关论文