Paper Info
Title
Representation learning with convolutional sparse autoencoders for remote sensing
Abstract
The performance of object recognition and classification on remote sensing imagery is highly dependent on the quality of extracted features and the amount of labeled data in the dataset. In this study, we concentrated on representation learning using unlabeled remote sensing data and using these representations to recognize different objects which vary in complexity, characteristics and ground resolution. In the proposed framework, randomly sampled patches from remote sensing images are first used to train a single layer sparse-auto encoder in order to learn the most efficient representation for the dataset. These representations are appeared to be as gabor filters in various orientations and parameters, color co-occurrence and color filters and edge-detection filters. Subsequently, representations are used to extract features from target object based on convolution and pooling. Finally, extracted features are used to train a machine learning algorithm and classification performances are evaluated. The proposed method is tested on recognition of dispersal areas, taxi-routes, parking areas and airplanes which are all subparts of an airfield. Performance of the proposed method is competitive with currently used rulebased and supervised methods.
Year
DOI
Venue
2013
10.1109/SIU.2013.6531525
Signal Processing and Communications Applications Conference
Keywords
Field
DocType
Gabor filters,edge detection,feature extraction,geophysical image processing,image classification,image colour analysis,image representation,image resolution,knowledge based systems,learning (artificial intelligence),remote sensing,Gabor filters,airplanes,color co-occurrence,color filters,convolutional sparse autoencoders,dispersal areas,edge detection filters,feature extraction,ground resolution,image classification,machine learning algorithm,object recognition,parking areas,remote sensing images,representation learning,rule based method,supervised method,target object,taxi routes,remote sensing,representation learning,self-taught learning,sparse auto-encoders,unsupervised feature learning
Feature detection (computer vision),Computer science,Edge detection,Remote sensing,Artificial intelligence,Contextual image classification,Computer vision,Pattern recognition,Feature (computer vision),Feature extraction,Color filter array,Feature learning,Cognitive neuroscience of visual object recognition
Conference
ISSN
ISBN
Citations 
2165-0608
978-1-4673-5561-2
0
PageRank 
References 
Authors
0.34
12
2
Name
Order
Citations
PageRank
Orhan Firat128129.13
Fatos T. Yarman-Vural2153.51