Next Article in Journal
Validation and Comparison of Physical Models for Soil Salinity Mapping over an Arid Landscape Using Spectral Reflectance Measurements and Landsat-OLI Data
Next Article in Special Issue
Semi-Supervised Multi-Temporal Deep Representation Fusion Network for Landslide Mapping from Aerial Orthophotos
Previous Article in Journal
Implementation of an Improved Water Change Tracking (IWCT) Algorithm: Monitoring the Water Changes in Tianjin over 1984–2019 Using Landsat Time-Series Data
Previous Article in Special Issue
Raindrop-Aware GAN: Unsupervised Learning for Raindrop-Contaminated Coastal Video Enhancement
Article

Landscape Similarity Analysis Using Texture Encoded Deep-Learning Features on Unclassified Remote Sensing Imagery

Department of Geography and Environmental Studies, Wilfrid Laurier University, Waterloo, ON N2L 3C5, Canada
*
Author to whom correspondence should be addressed.
Academic Editors: Omid Ghorbanzadeh, Omid Rahmati and Thomas Blaschke
Remote Sens. 2021, 13(3), 492; https://doi.org/10.3390/rs13030492
Received: 19 December 2020 / Revised: 20 January 2021 / Accepted: 25 January 2021 / Published: 30 January 2021
Convolutional neural networks (CNNs) are known for their ability to learn shape and texture descriptors useful for object detection, pattern recognition, and classification problems. Deeper layer filters of CNN generally learn global image information vital for whole-scene or object discrimination. In landscape pattern comparison, however, dense localized information encoded in shallow layers can contain discriminative information for characterizing changes across image local regions but are often lost in the deeper and non-spatial fully connected layers. Such localized features hold potential for identifying, as well as characterizing, process–pattern change across space and time. In this paper, we propose a simple yet effective texture-based CNN (Tex-CNN) via a feature concatenation framework which results in capturing and learning texture descriptors. The traditional CNN architecture was adopted as a baseline for assessing the performance of Tex-CNN. We utilized 75% and 25% of the image data for model training and validation, respectively. To test the models’ generalization, we used a separate set of imagery from the Aerial Imagery Dataset (AID) and Sentinel-2 for model development and independent validation. The classical CNN and the Tex-CNN classification accuracies in the AID were 91.67% and 96.33%, respectively. Tex-CNN accuracy was either on par with or outcompeted state-of-the-art methods. Independent validation on Sentinel-2 data had good performance for most scene types but had difficulty discriminating farm scenes, likely due to geometric generalization of discriminative features at the coarser scale. In both datasets, the Tex-CNN outperformed the classical CNN architecture. Using the Tex-CNN, gradient-based spatial attention maps (feature maps) which contain discriminative pattern information are extracted and subsequently employed for mapping landscape similarity. To enhance the discriminative capacity of the feature maps, we further perform spatial filtering, using PCA and select eigen maps with the top eigen values. We show that CNN feature maps provide descriptors capable of characterizing and quantifying landscape (dis)similarity. Using the feature maps histogram of oriented gradient vectors and computing their Earth Movers Distances, our method effectively identified similar landscape types with over 60% of target-reference scene comparisons showing smaller Earth Movers Distance (EMD) (e.g., 0.01), while different landscape types tended to show large EMD (e.g., 0.05) in the benchmark AID. We hope this proposal will inspire further research into the use of CNN layer feature maps in landscape similarity assessment, as well as in change detection. View Full-Text
Keywords: landscape similarity; feature maps; texture features; spatial patterns landscape similarity; feature maps; texture features; spatial patterns
Show Figures

Graphical abstract

MDPI and ACS Style

Malik, K.; Robertson, C. Landscape Similarity Analysis Using Texture Encoded Deep-Learning Features on Unclassified Remote Sensing Imagery. Remote Sens. 2021, 13, 492. https://doi.org/10.3390/rs13030492

AMA Style

Malik K, Robertson C. Landscape Similarity Analysis Using Texture Encoded Deep-Learning Features on Unclassified Remote Sensing Imagery. Remote Sensing. 2021; 13(3):492. https://doi.org/10.3390/rs13030492

Chicago/Turabian Style

Malik, Karim, and Colin Robertson. 2021. "Landscape Similarity Analysis Using Texture Encoded Deep-Learning Features on Unclassified Remote Sensing Imagery" Remote Sensing 13, no. 3: 492. https://doi.org/10.3390/rs13030492

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop