Redirigiendo al acceso original de articulo en 22 segundos...
ARTÍCULO
TITULO

Multi-Supervised Feature Fusion Attention Network for Clouds and Shadows Detection

Huiwen Ji    
Min Xia    
Dongsheng Zhang and Haifeng Lin    

Resumen

Cloud and cloud shadow detection are essential in remote sensing imagery applications. Few semantic segmentation models were designed specifically for clouds and their shadows. Based on the visual and distribution characteristics of clouds and their shadows in remote sensing imagery, this paper provides a multi-supervised feature fusion attention network. We design a multi-scale feature fusion block (FFB) for the problems caused by the complex distribution and irregular boundaries of clouds and shadows. The block consists of a fusion convolution block (FCB), a channel attention block (CAB), and a spatial attention block (SPA). By multi-scale convolution, FCB reduces excessive semantic differences between shallow and deep feature maps. CAB focuses on global and local features through multi-scale channel attention. Meanwhile, it fuses deep and shallow feature maps with non-linear weighting to optimize fusion performance. SPA focuses on task-relevant areas through spatial attention. With the three blocks above, FCB alleviates the difficulties of fusing multi-scale features. Additionally, it makes the network resistant to background interference while optimizing boundary detection. Our proposed model designs a class feature attention block (CFAB) to increase the robustness of cloud detection. The network achieves good performance on the self-made cloud and shadow dataset. This dataset is taken from Google Earth and contains remote sensing imagery from several satellites. The proposed model achieved a mean intersection over union (MIoU) of 94.10% on our dataset, which is 0.44% higher than the other models. Moreover, it shows high generalization capability due to its superior prediction results on HRC_WHU and SPARCS datasets.

 Artículos similares

       
 
Qingyan Zhou, Hao Li, Youhua Zhang and Junhong Zheng    
Traditional product evaluation research is to collect data through questionnaires or interviews to optimize product design, but the whole process takes a long time to deploy and cannot fully reflect the market situation. Aiming at this problem, we propos... ver más
Revista: Future Internet

 
Liming Zhou, Xiaohan Rao, Yahui Li, Xianyu Zuo, Baojun Qiao and Yinghao Lin    
In recent years, significant progress has been obtained in object detection using Convolutional Neural Networks (CNNs). However, owing to the particularity of Remote Sensing Images (RSIs), common object detection methods are not well suited for RSIs. Aim... ver más

 
Yao Zhao, Guangxia Wang, Jian Yang, Lantian Zhang and Xiaofei Qi    
The geographical feature extraction of historical maps is an important foundation for realizing the transition from human map reading to machine map reading. The current methods for building block extraction from historical maps have many problems, such ... ver más

 
Hangwei Feng, Jinlin Wang and Yang Li    
In the era of the digital economy, blockchain has developed well in various fields, such as finance and digital copyright, due to its unique decentralization and traceability characteristics. However, blockchain gradually exposes the storage problem, and... ver más
Revista: Future Internet

 
Siming Yin, Xian Guo and Jie Jiang    
Accurate extraction of urban landscape features in the historic district of China is an essential task for the protection of the cultural and historical heritage. In recent years, deep learning (DL)-based methods have made substantial progress in landsca... ver más