Inicio  /  Applied Sciences  /  Vol: 8 Núm: 5 Par: May (2018)  /  Artículo
ARTÍCULO
TITULO

An Improved Image Semantic Segmentation Method Based on Superpixels and Conditional Random Fields

Wei Zhao    
Yi Fu    
Xiaosong Wei and Hai Wang    

Resumen

This paper proposed an improved image semantic segmentation method based on superpixels and conditional random fields (CRFs). The proposed method can take full advantage of the superpixel edge information and the constraint relationship among different pixels. First, we employ fully convolutional networks (FCN) to obtain pixel-level semantic features and utilize simple linear iterative clustering (SLIC) to generate superpixel-level region information, respectively. Then, the segmentation results of image boundaries are optimized by the fusion of the obtained pixel-level and superpixel-level results. Finally, we make full use of the color and position information of pixels to further improve the semantic segmentation accuracy using the pixel-level prediction capability of CRFs. In summary, this improved method has advantages both in terms of excellent feature extraction capability and good boundary adherence. Experimental results on both the PASCAL VOC 2012 dataset and the Cityscapes dataset show that the proposed method can achieve significant improvement of segmentation accuracy in comparison with the traditional FCN model.

 Artículos similares

       
 
Lingzhi Wang, Yingpin Chen, Fan Lin, Yuqun Chen, Fei Yu and Zongfu Cai    
Models based on total variation (TV) regularization are proven to be effective in removing random noise. However, the serious staircase effect also exists in the denoised images. In this study, two-dimensional total variation with overlapping group spars... ver más
Revista: Applied Sciences

 
Yiwen Liu, Zhongbin Wang, Lei Si, Lin Zhang, Chao Tan and Jing Xu    
To eliminate the noise of infrared thermal image without reference and noise model, an improved dual-tree complex wavelet transform (DTCWT), optimized by an improved fruit-fly optimization algorithm (IFOA) and bilateral filter (BF), is proposed in this p... ver más
Revista: Applied Sciences

 
Robert O. Ojwang, Jörg Dietrich, Prajna Kasargodu Anebagilu, Matthias Beyer, Franz Rottensteiner     Pág. 1 - 19
Mombasa faces severe water scarcity problems. The existing supply is unable to satisfy the demand. This article demonstrates the combination of satellite image analysis and modelling as tools for the development of an urban rainwater harvesting policy. F... ver más
Revista: Water

 
Jitendra Saturwar,D.N. Chaudhari     Pág. 93 - 100
With the growth in digital world, it is becoming more important to find a method toprotect the security of digital media. An image watermarking model based on visual secretsharing (VSS) is proposed for protection of ownership. In the embedding phase, the... ver más

 
Yan Zhou, Jinwei Dong, Xiangming Xiao, Tong Xiao, Zhiqi Yang, Guosong Zhao, Zhenhua Zou, Yuanwei Qin     Pág. 1 - 16
Open surface water bodies play an important role in agricultural and industrial production, and are susceptible to climate change and human activities. Remote sensing data has been increasingly used to map open surface water bodies at local, regional, an... ver más
Revista: Water