MyJournals Home  

RSS FeedsRemote Sensing, Vol. 11, Pages 114: A Patch-Based Light Convolutional Neural Network for Land-Cover Mapping Using Landsat-8 Images (Remote Sensing)

 
 

10 january 2019 21:00:12

 
Remote Sensing, Vol. 11, Pages 114: A Patch-Based Light Convolutional Neural Network for Land-Cover Mapping Using Landsat-8 Images (Remote Sensing)
 




This study proposes a light convolutional neural network (LCNN) well-fitted for medium-resolution (30-m) land-cover classification. The LCNN attains high accuracy without overfitting, even with a small number of training samples, and has lower computational costs due to its much lighter design compared to typical convolutional neural networks for high-resolution or hyperspectral image classification tasks. The performance of the LCNN was compared to that of a deep convolutional neural network, support vector machine (SVM), k-nearest neighbors (KNN), and random forest (RF). SVM, KNN, and RF were tested with both patch-based and pixel-based systems. Three 30 km 30 km test sites of the Level II National Land Cover Database were used for reference maps to embrace a wide range of land-cover types, and a single-date Landsat-8 image was used for each test site. To evaluate the performance of the LCNN according to the sample sizes, we varied the sample size to include 20, 40, 80, 160, and 320 samples per class. The proposed LCNN achieved the highest accuracy in 13 out of 15 cases (i.e., at three test sites with five different sample sizes), and the LCNN with a patch size of three produced the highest overall accuracy of 61.94% from 10 repetitions, followed by SVM (61.51%) and RF (61.15%) with a patch size of three. Also, the statistical significance of the differences between LCNN and the other classifiers was reported. Moreover, by introducing the heterogeneity value (from 0 to 8) representing the complexity of the map, we demonstrated the advantage of patch-based LCNN over pixel-based classifiers, particularly at moderately heterogeneous pixels (from 1 to 4), with respect to accuracy (LCNN is 5.5% and 6.3% more accurate for a training sample size of 20 and 320 samples per class, respectively). Finally, the computation times of the classifiers were calculated, and the LCNN was confirmed to have an advantage in large-area mapping.


Del.icio.us Digg Facebook Google StumbleUpon Twitter
 
21 viewsCategory: Geology, Physics
 
Remote Sensing, Vol. 11, Pages 116: A Unified Model for Multi-Frequency PPP Ambiguity Resolution and Test Results with Galileo and BeiDou Triple-Frequency Observations (Remote Sensing)
Remote Sensing, Vol. 11, Pages 113: Ice-Gouging Topography of the Exposed Aral Sea Bed (Remote Sensing)
 
 
blog comments powered by Disqus


MyJournals.org
The latest issues of all your favorite science journals on one page

Username:
Password:

Register | Retrieve

Search:

Physics

Use these buttons to bookmark us:
Del.icio.us Digg Facebook Google StumbleUpon Twitter


Valid HTML 4.01 Transitional
Copyright © 2008 - 2019 Indigonet Services B.V.. Contact: Tim Hulsen. Read here our privacy notice.
Other websites of Indigonet Services B.V.: Nieuws Vacatures News Tweets Travel Photos Nachrichten Indigonet Finances Leer Mandarijn