Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks

Marmanis, Dimitrios; Datcu, Mihai; Esch, Thomas; Stilla, Uwe

doi:10.1109/lgrs.2015.2499239

Cited by 554 publications

(298 citation statements)

References 9 publications

Supporting

Mentioning

295

Contrasting

Unclassified

Order By: Relevance

“…Several deep architectures [Deng, 2014, Schmidhuber, 2015 have been employed, with the Deep Belief Networks, Autoencoders, Convolutional Neural Networks and Deep Boltzmann Machines being some of the most commonly used in the literature for a variety of problems. In particular, for the classification of remote sensing data certain deep architectures have provided highly accurate results [Mnih and Hinton, 2010, Chen et al, 2014, Vakalopoulou et al, 2015, Basu et al, 2015, Makantasis et al, 2015, Marmanis et al, 2016.…”

Section: Classmentioning

confidence: 99%

See 1 more Smart Citation

Benchmarking Deep Learning Frameworks for the Classification of Very High Resolution Satellite Multispectral Data

Papadomanolaki¹,

Vakalopoulou²,

Zagoruyko³

et al. 2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:In this paper we evaluated deep-learning frameworks based on Convolutional Neural Networks for the accurate classification of multispectral remote sensing data. Certain state-of-the-art models have been tested on the publicly available SAT-4 and SAT-6 high resolution satellite multispectral datasets. In particular, the performed benchmark included the AlexNet, AlexNet-small and VGG models which had been trained and applied to both datasets exploiting all the available spectral information. Deep Belief Networks, Autoencoders and other semi-supervised frameworks have been, also, compared. The high level features that were calculated from the tested models managed to classify the different land cover classes with significantly high accuracy rates i.e., above 99.9%. The experimental results demonstrate the great potentials of advanced deep-learning frameworks for the supervised classification of high resolution multispectral remote sensing data.

show abstract

Section: Classmentioning

confidence: 99%

“…Similar to [Vakalopoulou et al, 2015, Marmanis et al, 2016] the already pretrained AlexNet network [Krizhevsky et al, 2012] has been employed, here, for feature extraction. In particular, features from the last layer (FC7) were extracted using two spectral band combinations (red-green-blue and NIR-red-green).…”

Section: Alexnet-pretrained Networkmentioning

confidence: 99%

Benchmarking Deep Learning Frameworks for the Classification of Very High Resolution Satellite Multispectral Data

Papadomanolaki¹,

Vakalopoulou²,

Zagoruyko³

et al. 2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…Pretrained model for CNNs like Alexnet (Krizhevsky and Sutskever, 2010), VGGNet or GoogleNet (Szegedy and Liu, 2015) that have been trained on large dataset such as ImageNet can be used for other visual recognition tasks without any needing to train the first few layers. Such a property is very useful for classification tasks in remote sensing, where the acquisition of large sets of training data need a lot of effort and cost (Marmanis et al, 2016). In addition to fine-tuning a pretrained model for a new classification task, a pre-trained CNN can be treated as fixed feature extractor.…”

Section: Cnn and Pre-trained Modelsmentioning

confidence: 99%

“…As training of CNNs, from scratch needs large datasets with labels which are hard to obtain in the remote sensing community, using a pre-trained CNN models is suggested. Marmanis et al, (2016) used a pre-trained CNN model which was pre-trained on ImageNet dataset (Krizhevsky, et al, 2012) and successfully achieved good results in the classification of remote sensing datasets. To select the roof types, two methodologies are utilized for classification of roof patches.…”

Section: Introductionmentioning

confidence: 99%

Roof Type Selection Based on Patch-Based Classification Using Deep Learning for High Resolution Satellite Imagery

Partovi

Fraundorfer

Azimi

et al. 2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:3D building reconstruction from remote sensing image data from satellites is still an active research topic and very valuable for 3D city modelling. The roof model is the most important component to reconstruct the Level of Details 2 (LoD2) for a building in 3D modelling. While the general solution for roof modelling relies on the detailed cues (such as lines, corners and planes) extracted from a Digital Surface Model (DSM), the correct detection of the roof type and its modelling can fail due to low quality of the DSM generated by dense stereo matching. To reduce dependencies of roof modelling on DSMs, the pansharpened satellite images as a rich resource of information are used in addition. In this paper, two strategies are employed for roof type classification. In the first one, building roof types are classified in a state-of-the-art supervised pre-trained convolutional neural network (CNN) framework. In the second strategy, deep features from deep layers of different pre-trained CNN model are extracted and then an RBF kernel using SVM is employed to classify the building roof type. Based on roof complexity of the scene, a roof library including seven types of roofs is defined. A new semi-automatic method is proposed to generate training and test patches of each roof type in the library. Using the pre-trained CNN model does not only decrease the computation time for training significantly but also increases the classification accuracy.

show abstract

“…The results showed that fine-tuning tends to be the best-performing strategy. In [31], Marmanis et al proposed a two-stage framework for earth observation classification. In the first stage, an initial set of representations is extracted by using a pre-trained CNN, namely ImageNet.…”

Section: Introductionmentioning

confidence: 99%

Siamese-GAN: Learning Invariant Representations for Aerial Vehicle Image Categorization

et al. 2018

View full text Add to dashboard Cite

Abstract:In this paper, we present a new algorithm for cross-domain classification in aerial vehicle images based on generative adversarial networks (GANs). The proposed method, called Siamese-GAN, learns invariant feature representations for both labeled and unlabeled images coming from two different domains. To this end, we train in an adversarial manner a Siamese encoder-decoder architecture coupled with a discriminator network. The encoder-decoder network has the task of matching the distributions of both domains in a shared space regularized by the reconstruction ability, while the discriminator seeks to distinguish between them. After this phase, we feed the resulting encoded labeled and unlabeled features to another network composed of two fully-connected layers for training and classification, respectively. Experiments on several cross-domain datasets composed of extremely high resolution (EHR) images acquired by manned/unmanned aerial vehicles (MAV/UAV) over the cities of Vaihingen, Toronto, Potsdam, and Trento are reported and discussed.

show abstract

Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks

Cited by 554 publications

References 9 publications

Benchmarking Deep Learning Frameworks for the Classification of Very High Resolution Satellite Multispectral Data

Benchmarking Deep Learning Frameworks for the Classification of Very High Resolution Satellite Multispectral Data

Roof Type Selection Based on Patch-Based Classification Using Deep Learning for High Resolution Satellite Imagery

Siamese-GAN: Learning Invariant Representations for Aerial Vehicle Image Categorization

Contact Info

Product

Resources

About