Redirigiendo al acceso original de articulo en 16 segundos...
ARTÍCULO
TITULO

Water Areas Segmentation from Remote Sensing Images Using a Separable Residual SegNet Network

Liguo Weng    
Yiming Xu    
Min Xia    
Yonghong Zhang    
Jia Liu and Yiqing Xu    

Resumen

Changes on lakes and rivers are of great significance for the study of global climate change. Accurate segmentation of lakes and rivers is critical to the study of their changes. However, traditional water area segmentation methods almost all share the following deficiencies: high computational requirements, poor generalization performance, and low extraction accuracy. In recent years, semantic segmentation algorithms based on deep learning have been emerging. Addressing problems associated to a very large number of parameters, low accuracy, and network degradation during training process, this paper proposes a separable residual SegNet (SR-SegNet) to perform the water area segmentation using remote sensing images. On the one hand, without compromising the ability of feature extraction, the problem of network degradation is alleviated by adding modified residual blocks into the encoder, the number of parameters is limited by introducing depthwise separable convolutions, and the ability of feature extraction is improved by using dilated convolutions to expand the receptive field. On the other hand, SR-SegNet removes the convolution layers with relatively more convolution kernels in the encoding stage, and uses the cascading method to fuse the low-level and high-level features of the image. As a result, the whole network can obtain more spatial information. Experimental results show that the proposed method exhibits significant improvements over several traditional methods, including FCN, DeconvNet, and SegNet.

 Artículos similares

       
 
Manuel Pulido, Jesús Barrena-González, Alberto Alfonso-Torreño, Rafael Robina-Ramírez and Saskia Keesstra    
Water is a key strategic resource, particularly in Mediterranean climate-type areas with impermeable rocks and shallow soils like Southwestern Spain. The region of Extremadura is commonly known by its large surface occupied by big dams (30% of water damm... ver más
Revista: Water

 
Saher Ayyad, Islam S. Al Zayed, Van Tran Thi Ha and Lars Ribbe    
Monitoring of crop water consumption, also known as actual evapotranspiration (ETa), is crucial for the prudent use of limited freshwater resources. Remote-sensing-based algorithms have become a popular approach for providing spatio-temporal information ... ver más
Revista: Water

 
Vrushti Mawani    
Poor access to municipal water in Ahmedabad?s Muslim areas has been tied to the difficulties of implementing a planning mechanism called the town planning scheme, which, in turn, have been premised on widespread illegal constructions that have developed ... ver más
Revista: Water

 
Byong Wook Cho and Chang Oh Choo    
Uranium concentrations (a total of 82 samples) in groundwater in Icheon, middle Korea, showed a wide range from 0.02 to 1640 µg/L with a mean of 56.77 µg/L, a median of 3.03 µg/L, and a standard deviation of 228.63 µg/L. Most groundwater samples had quit... ver más
Revista: Water

 
Margarita Garcia-Vila, Rodrigo Morillo-Velarde and Elias Fereres    
Process-based crop models such as AquaCrop are useful for a variety of applications but must be accurately calibrated and validated. Sugar beet is an important crop that is grown in regions under water scarcity. The discrepancies and uncertainty in past ... ver más
Revista: Water