Segmentation for remote-sensing imagery using the object-based Gaussian-Markov random field model with region coefficients

2019 ◽  
Vol 40 (11) ◽  
pp. 4441-4472 ◽  
Author(s):  
Chen Zheng ◽  
Hongtai Yao
Keyword(s):  
Remote Sensing ◽  
Random Field ◽  
Markov Random Field ◽  
Field Model ◽  
Random Field Model ◽  
Remote Sensing Imagery ◽  
Markov Random Field Model ◽  
Gaussian Markov Random Field ◽  
Markov Random ◽  
Object Based

scholarly journals An Object-Based Markov Random Field Model with Anisotropic Penalty for Semantic Segmentation of High Spatial Resolution Remote Sensing Imagery

2019 ◽  
Vol 11 (23) ◽  
pp. 2878
Author(s):  
Chen Zheng ◽  
Xinxin Pan ◽  
Xiaohui Chen ◽  
Xiaohui Yang ◽  
Xin Xin ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Random Field ◽  
Markov Random Field ◽  
Field Model ◽  
Semantic Segmentation ◽  
Processing Scheme ◽  
Random Field Model ◽  
Markov Random Field Model ◽  
Markov Random ◽  
Object Based

The Markov random field model (MRF) has attracted a lot of attention in the field of remote sensing semantic segmentation. But, most MRF-based methods fail to capture the various interactions between different land classes by using the isotropic potential function. In order to solve such a problem, this paper proposed a new generalized probability inference with an anisotropic penalty for the object-based MRF model (OMRF-AP) that can distinguish the differences in the interactions between any two land classes. Specifically, an anisotropic penalty matrix was first developed to describe the relationships between different classes. Then, an expected value of the penalty information (EVPI) was developed in this inference criterion to integrate the anisotropic class-interaction information and the posteriori distribution information of the OMRF model. Finally, by iteratively updating the EVPI terms of different classes, segmentation results could be achieved when the iteration converged. Experiments of texture images and different remote sensing images demonstrated that our method could show a better performance than other state-of-the-art MRF-based methods, and a post-processing scheme of the OMRF-AP model was also discussed in the experiments.

Sign in / Sign up

Export Citation Format

Share Document