@InProceedings{NogueiraMiraSant:2015:ImSpFe,
author = "Nogueira, Keiller and Miranda, Waner O. and Santos, Jefersson A.
dos",
affiliation = "{Universidade Federal de Minas Gerais} and {Universidade Federal
de Minas Gerais} and {Universidade Federal de Minas Gerais}",
title = "Improving Spatial Feature Representation from Aerial Scenes by
Using Convolutional Networks",
booktitle = "Proceedings...",
year = "2015",
editor = "Papa, Jo{\~a}o Paulo and Sander, Pedro Vieira and Marroquim,
Ricardo Guerra and Farrell, Ryan",
organization = "Conference on Graphics, Patterns and Images, 28. (SIBGRAPI)",
publisher = "IEEE Computer Society",
address = "Los Alamitos",
keywords = "Deep Learning, Remote Sensing, Feature Learning, Image
Classification, Machine Learning, High-resolution Images.",
abstract = "The performance of image classification is highly dependent on the
quality of extracted features. Concerning high resolution remote
image images, encoding the spatial features in an efficient and
robust fashion is the key to generating discriminatory models to
classify them. Even though many visual descriptors have been
proposed or successfully used to encode spatial features of remote
sensing images, some applications, using this sort of images,
demand more specific description techniques. Deep Learning, an
emergent machine learning approach based on neural networks, is
capable of learning specific features and classifiers at the same
time and adjust at each step, in real time, to better fit the need
of each problem. For several task, such image classification, it
has achieved very good results, mainly boosted by the feature
learning performed which allows the method to extract specific and
adaptable visual features depending on the data. In this paper, we
propose a novel network capable of learning specific spatial
features from remote sensing images, with any pre-processing step
or descriptor evaluation, and classify them. Specifically,
automatic feature learning task aims at discovering hierarchical
structures from the raw data, leading to a more representative
information. This task not only poses interesting challenges for
existing vision and recognition algorithms, but also brings huge
opportunities for urban planning, crop and forest management and
climate modelling. The propose convolutional neural network has
six layers: three convolutional, two fully-connected and one
classifier layer. So, the five first layers are responsible to
extract visual features while the last one is responsible to
classify the images. We conducted a systematic evaluation of the
proposed method using two datasets: (i) the popular aerial image
dataset UCMerced Land-use and, (ii) a multispectral
high-resolution scenes of the Brazilian Coffee Scenes. The
experiments show that the proposed method outperforms
state-of-the-art algorithms in terms of overall accuracy.",
conference-location = "Salvador, BA, Brazil",
conference-year = "26-29 Aug. 2015",
doi = "10.1109/SIBGRAPI.2015.39",
url = "http://dx.doi.org/10.1109/SIBGRAPI.2015.39",
language = "en",
ibi = "8JMKD3MGPBW34M/3JMKD35",
url = "http://urlib.net/ibi/8JMKD3MGPBW34M/3JMKD35",
targetfile = "sibgrapi2015.pdf",
urlaccessdate = "2024, Apr. 30"
}