scholarly journals Efficient Learning of Spatial Patterns with Multi-Scale Conditional Random Fields for Region-Based Classification

2014 ◽  
Vol 6 (8) ◽  
pp. 6727-6764 ◽  
Author(s):  
Mitchel Alioscha-Perez ◽  
Hichem Sahli
Keyword(s):  
Spatial Patterns ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Multi Scale ◽  
Efficient Learning

scholarly journals Efficient Learning of Sparse Conditional Random Fields for Supervised Sequence Labeling

2010 ◽  
Vol 4 (6) ◽  
pp. 953-964 ◽  
Author(s):  
Nataliya Sokolovska ◽  
Thomas Lavergne ◽  
Olivier Cappe ◽  
François Yvon
Keyword(s):  
Random Fields ◽  
Conditional Random Fields ◽  
Sequence Labeling ◽  
Efficient Learning

scholarly journals An Automatic Extraction Method for Hatched Residential Areas in Raster Maps Based on Multi-Scale Feature Fusion

2021 ◽  
Vol 10 (12) ◽  
pp. 831
Author(s):  
Jianhua Wu ◽  
Jiaqi Xiong ◽  
Yu Zhao ◽  
Xiang Hu
Keyword(s):  
Random Fields ◽  
Conditional Random Fields ◽  
Feature Fusion ◽  
Gabor Filter ◽  
Residential Areas ◽  
Change Analysis ◽  
Land Quality ◽  
Multi Scale ◽  
Raster Maps ◽  
Fully Connected

Extracting the residential areas from digital raster maps is beneficial for research on land use change analysis and land quality assessment. In traditional methods for extracting residential areas in raster maps, parameters must be set manually; these methods also suffer from low extraction accuracy and inefficiency. Therefore, we have proposed an automatic method for extracting the hatched residential areas from raster maps based on a multi-scale U-Net and fully connected conditional random fields. The experimental results showed that the model that was based on a multi-scale U-Net with fully connected conditional random fields achieved scores of 97.05% in Dice, 94.26% in Intersection over Union, 94.92% in recall, 93.52% in precision and 99.52% in accuracy. Compared to the FCN-8s, the five metrics increased by 1.47%, 2.72%, 1.07%, 4.56% and 0.26%, respectively and compared to the U-Net, they increased by 0.84%, 1.56%, 3.00%, 0.65% and 0.13%, respectively. Our method also outperformed the Gabor filter-based algorithm in the number of identified objects and the accuracy of object contour locations. Furthermore, we were able to extract all of the hatched residential areas from a sheet of raster map. These results demonstrate that our method has high accuracy in object recognition and contour position, thereby providing a new method with strong potential for the extraction of hatched residential areas.

scholarly journals CHEMDNER system with mixed conditional random fields and multi-scale word clustering

2015 ◽  
Vol 7 (S1) ◽  
Author(s):  
Yanan Lu ◽  
Donghong Ji ◽  
Xiaoyuan Yao ◽  
Xiaomei Wei ◽  
Xiaohui Liang
Keyword(s):  
Random Fields ◽  
Conditional Random Fields ◽  
Multi Scale ◽  
Word Clustering

scholarly journals Building Extraction from High Spatial Resolution Remote Sensing Images via Multiscale-Aware and Segmentation-Prior Conditional Random Fields

2020 ◽  
Vol 12 (23) ◽  
pp. 3983
Author(s):  
Qiqi Zhu ◽  
Zhen Li ◽  
Yanan Zhang ◽  
Qingfeng Guan
Keyword(s):  
Remote Sensing ◽  
Spatial Resolution ◽  
Random Fields ◽  
Conditional Random Fields ◽  
High Spatial Resolution ◽  
Conditional Random Field ◽  
Binary Classification ◽  
Building Extraction ◽  
Remote Sensing Images ◽  
Multi Scale

Building extraction is a binary classification task that separates the building area from the background in remote sensing images. The conditional random field (CRF) is directly modelled by the maximum posterior probability, which can make full use of the spatial neighbourhood information of both labelled and observed images. CRF is widely used in building footprint extraction. However, edge oversmoothing still exists when CRF is directly used to extract buildings from high spatial resolution (HSR) remote sensing images. Based on a computer vision multi-scale semantic segmentation network (D-LinkNet), a novel building extraction framework is proposed, named multiscale-aware and segmentation-prior conditional random fields (MSCRF). To solve the problem of losing building details in the downsampling process, D-LinkNet connecting the encoder and decoder is correspondingly used to generate the unary potential. By integrating multi-scale building features in the central module, D-LinkNet can integrate multiscale contextual information without loss of resolution. For the pairwise potential, the segmentation prior is fused to alleviate the influence of spectral diversity between the building and the background area. Moreover, the local class label cost term is introduced. The clear boundaries of the buildings are obtained by using the larger-scale context information. The experimental results demonstrate that the proposed MSCRF framework is superior to the state-of-the-art methods and performs well for building extraction of complex scenes.

Sign in / Sign up

Export Citation Format

Share Document