Semantic Labeling of High Resolution Aerial Imagery and LiDAR Data with Fine Segmentation Network

In this paper, a novel convolutional neural network (CNN)-based architecture, named fine segmentation network (FSN), is proposed for semantic segmentation of high resolution aerial images and light detection and ranging (LiDAR) data. The proposed architecture follows the encoder–decoder paradigm and...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2018-05, Vol.10 (5), p.743
Main Authors: Pan, Xuran, Gao, Lianru, Marinoni, Andrea, Zhang, Bing, Yang, Fan, Gamba, Paolo
Format: Article
Language:English
Subjects:
Aerial photography
Artificial neural networks
Convolution
convolutional neural network (CNN)
deep learning
High resolution
high resolution aerial imagery
Image detection
Image processing
Image resolution
Image segmentation
Infrared imagery
Labeling
LiDAR
Multilayers
Multisensor fusion
Neural networks
Photogrammetry
Remote sensing
semantic segmentation
Semantics
spectral image
Transfer learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a novel convolutional neural network (CNN)-based architecture, named fine segmentation network (FSN), is proposed for semantic segmentation of high resolution aerial images and light detection and ranging (LiDAR) data. The proposed architecture follows the encoder–decoder paradigm and the multi-sensor fusion is accomplished in the feature-level using multi-layer perceptron (MLP). The encoder consists of two parts: the main encoder based on the convolutional layers of Vgg-16 network for color-infrared images and a lightweight branch for LiDAR data. In the decoder stage, to adaptively upscale the coarse outputs from encoder, the Sub-Pixel convolution layers replace the transposed convolutional layers or other common up-sampling layers. Based on this design, the features from different stages and sensors are integrated for a MLP-based high-level learning. In the training phase, transfer learning is employed to infer the features learned from generic dataset to remote sensing data. The proposed FSN is evaluated by using the International Society for Photogrammetry and Remote Sensing (ISPRS) Potsdam and Vaihingen 2D Semantic Labeling datasets. Experimental results demonstrate that the proposed framework can bring considerable improvement to other related networks.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs10050743