In this paper, we propose a decision-level fusion approach using a probabilistic graphical model for the task of dense semantic labeling.

A fully-convolutional neural network and logistic regression classifier are trained for generating individual predictions for the optical imagery and LiDAR data ...

A fully-convolutional neural network and logistic regression classifier are trained for generating individual predictions for the optical imagery and LiDAR data ...

This paper proposes a decision-level fusion approach using a probabilistic graphical model for the task of dense semantic labeling of airborne remote ...

The semantic segmentation approach provides the pixel-level strategy to classify the HSI, existing studies utilize neural network frameworks and leverage CNN ...

In this paper, we propose a decision-level fusion approach using a probabilistic graphical model for the task of dense semantic labeling. Our proposed method ...

In this paper, we propose a decision-level fusion approach with a simpler architecture for the task of dense semantic labeling. Our proposed method first ...

A deep fully convolutional networks (FCNs) based ensemble learning method is proposed to label the high-resolution aerial images and achieves an overall ...

In this paper, a novel convolutional neural network (CNN)-based architecture, named fine segmentation network (FSN), is proposed for semantic segmentation ...

(2017, January 21–26). Dense semantic labeling of very-high-resolution aerial imagery and lidar with fully-convolutional neural networks and higher-order crfs.