Scene classification for aerial images based on CNN using sparse coding technique

Aerial scene classification purposes to automatically label aerial images with specific semantic categories. However, cataloguing presents a fundamental problem for high-resolution remote-sensing imagery (HRRS). Recent developments include several approaches and numerous algorithms address the task....

Full description

Saved in:
Bibliographic Details
Published in:International journal of remote sensing 2017-05, Vol.38 (8-10), p.2662-2685
Main Authors: Qayyum, Abdul, Malik, Aamir Saeed, Saad, Naufal M, Iqbal, Mahboob, Faris Abdullah, Mohd, Rasheed, Waqas, Rashid Abdullah, Tuan AB, Bin Jafaar, Mohd Yaqoob
Format: Article
Language:English
Subjects:
Aerials
Algorithms
Artificial neural networks
Biological Physics
Categories
Classification
Coding
Feature extraction
High resolution
Image classification
Image coding
Image resolution
Imagery
Imaging techniques
Mathematical models
Neural networks
Physics
Remote sensing
Satellite imagery
Satellites
Spaceborne remote sensing
Unmanned aerial vehicles
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:Aerial scene classification purposes to automatically label aerial images with specific semantic categories. However, cataloguing presents a fundamental problem for high-resolution remote-sensing imagery (HRRS). Recent developments include several approaches and numerous algorithms address the task. This article proposes a convolutional neural network (CNN) approach that utilizes sparse coding for scene classification applicable for HRRS unmanned aerial vehicle (UAV) and satellite imagery. The article has two major sections: the first describes the extraction of dense multiscale features (multiple scales) from the last convolutional layer of a pre-trained CNN models; the second describes the encoding of extracted features into global image features via sparse coding to achieve scene classification. The authors compared experimental outcomes with existing techniques such as Scale-Invariant Feature Transform and demonstrated that features from pre-trained CNNs generalized well with HRRS datasets and were more expressive than low- and mid-level features, exhibiting an overall 90.3% accuracy rate for scene classification compared to 85.4% achieved by SIFT with sparse coding. Thus, the proposed CNN-based sparse coding approach obtained a robust performance that holds promising potential for future applications in satellite and UAV imaging.
ISSN:0143-1161
1366-5901
DOI:10.1080/01431161.2017.1296206