scholarly journals NEIGHBOUR-BASED DOMAIN ADAPTATION FOR INVESTIGATION OF TRANSFERABLE ABILITY OF PREVIOUSLY LABELED DATA FOR LAND-COVER CLASSIFICATION OF AERIAL IMAGES

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 1329-1335
Author(s):  
R. Zhu ◽  
L. Yan
Keyword(s):  
Land Cover ◽  
Domain Adaptation ◽  
Land Cover Classification ◽  
Classification Performance ◽  
Aerial Images ◽  
Learning Performance ◽  
Training Dataset ◽  
Training Samples ◽  
Target Center

Abstract. Existing land-cover classification methods are usually based on adequate labelled data. But annotating enough training samples is hard and time-consuming. Therefore, we need to investigate how existing labelled data can help to increase land-cover classification. Source labelled data are proposed to be selected by calculating the target center of reliable target pseudo-labelled data for each class in this paper. Then we augment the training dataset with reliable target pesudo-labeled data and selected source labelled data to improve the quality and quantity of training dataset. We also investigate the amount of source labelled data that should be selected and the number of limited target labelled data that can produce good transfer learning performance. The UC Merced dataset is employed as the target dataset to evaluate the proposed approach while the NWPU-RESISC45 dataset is considered as the source labelled data. The experimental results show that selected source labelled data and reliable target pesudo-labeled data may improve the land-cover classification performance if selected source labelled data and reliable target pesudo-labeled data are augmented with the limited target labelled data respectively.

scholarly journals Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

2019 ◽  
Vol 11 (10) ◽  
pp. 1153 ◽  
Author(s):  
Mesay Belete Bejiga ◽  
Farid Melgani ◽  
Pietro Beraldini
Keyword(s):  
Neural Networks ◽  
Land Cover ◽  
Transfer Learning ◽  
Large Scale ◽  
Domain Adaptation ◽  
Land Cover Classification ◽  
Target Domain ◽  
Training Samples ◽  
Latent Space ◽  
Large Scale Land

Learning classification models require sufficiently labeled training samples, however, collecting labeled samples for every new problem is time-consuming and costly. An alternative approach is to transfer knowledge from one problem to another, which is called transfer learning. Domain adaptation (DA) is a type of transfer learning that aims to find a new latent space where the domain discrepancy between the source and the target domain is negligible. In this work, we propose an unsupervised DA technique called domain adversarial neural networks (DANNs), composed of a feature extractor, a class predictor, and domain classifier blocks, for large-scale land cover classification. Contrary to the traditional methods that perform representation and classifier learning in separate stages, DANNs combine them into a single stage, thereby learning a new representation of the input data that is both domain-invariant and discriminative. Once trained, the classifier of a DANN can be used to predict both source and target domain labels. Additionally, we also modify the domain classifier of a DANN to evaluate its suitability for multi-target domain adaptation problems. Experimental results obtained for both single and multiple target DA problems show that the proposed method provides a performance gain of up to 40%.

scholarly journals DEEP DOMAIN ADAPTATION BY WEIGHTED ENTROPY MINIMIZATION FOR THE CLASSIFICATION OF AERIAL IMAGES

2020 ◽  
Vol V-2-2020 ◽  
pp. 591-598
Author(s):  
D. Wittich
Keyword(s):  
Data Augmentation ◽  
Domain Adaptation ◽  
Aerial Images ◽  
Target Domain ◽  
Source Domain ◽  
Entropy Minimization ◽  
Training Samples ◽  
Order Of Magnitude ◽  
Weighted Entropy

Abstract. Fully convolutional neural networks (FCN) are successfully used for the automated pixel-wise classification of aerial images and possibly additional data. However, they require many labelled training samples to perform well. One approach addressing this issue is semi-supervised domain adaptation (SSDA). Here, labelled training samples from a source domain and unlabelled samples from a target domain are used jointly to obtain a target domain classifier, without requiring any labelled samples from the target domain. In this paper, a two-step approach for SSDA is proposed. The first step corresponds to a supervised training on the source domain, making use of strong data augmentation to increase the initial performance on the target domain. Secondly, the model is adapted by entropy minimization using a novel weighting strategy. The approach is evaluated on the basis of five domains, corresponding to five cities. Several training variants and adaptation scenarios are tested, indicating that proper data augmentation can already improve the initial target domain performance significantly resulting in an average overall accuracy of 77.5%. The weighted entropy minimization improves the overall accuracy on the target domains in 19 out of 20 scenarios on average by 1.8%. In all experiments a novel FCN architecture is used that yields results comparable to those of the best-performing models on the ISPRS labelling challenge while having an order of magnitude fewer parameters than commonly used FCNs.

scholarly journals TOWARDS BETTER CLASSIFICATION OF LAND COVER AND LAND USE BASED ON CONVOLUTIONAL NEURAL NETWORKS

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 139-146
Author(s):  
C. Yang ◽  
F. Rottensteiner ◽  
C. Heipke
Keyword(s):  
Neural Networks ◽  
Land Use ◽  
Land Cover ◽  
Convolutional Neural Networks ◽  
Land Cover Classification ◽  
Aerial Images ◽  
Infrared Band ◽  
Rgb Images ◽  
Geospatial Databases

<p><strong>Abstract.</strong> Land use and land cover are two important variables in remote sensing. Commonly, the information of land use is stored in geospatial databases. In order to update such databases, we present a new approach to determine the land cover and to classify land use objects using convolutional neural networks (CNN). High-resolution aerial images and derived data such as digital surface models serve as input. An encoder-decoder based CNN is used for land cover classification. We found a composite including the infrared band and height data to outperform RGB images in land cover classification. We also propose a CNN-based methodology for the prediction of land use label from the geospatial databases, where we use masks representing object shape, the RGB images and the pixel-wise class scores of land cover as input. For this task, we developed a two-branch network where the first branch considers the whole area of an image, while the second branch focuses on a smaller relevant area. We evaluated our methods using two sites and achieved an overall accuracy of up to 89.6% and 81.7% for land cover and land use, respectively. We also tested our methods for land cover classification using the Vaihingen dataset of the ISPRS 2D semantic labelling challenge and achieved an overall accuracy of 90.7%.</p>

scholarly journals LAND COVER CLASSIFICATION OF ALOS PALSAR DATA USING SUPPORT VECTOR MACHINE

2014 ◽  
Vol 10 (1) ◽  
Author(s):  
Katmoko Ari Sambodo ◽  
Novie Indriasari
Keyword(s):  
Support Vector Machine ◽  
Land Cover ◽  
Feature Space ◽  
Land Cover Classification ◽  
Support Vector ◽  
Rubber Plantation ◽  
Alos Palsar ◽  
Training Samples ◽  
Separating Hyperplane

Land cover classification is  one  of  the  extensive  used  applications in  the  field  of remote sensing. Recently, Synthetic Aperture Radar (SAR) data has become an increasing popular data source because  its  capability  to  penetrate  through  clouds,  haze,  and  smoke.  This  study  showed  on  an alternative  method  for  land  cover  classification  of  ALOS-PALSAR  data  using  Support  Vector Machine (SVM) classifier. SVM discriminates two classes by fitting an optimal separating hyperplane to the training data in a multidimensional feature space, by using only the closest training samples. In order  to  minimize  the  presence  of  outliers  in  the  training  samples  and  to  increase  inter-class separabilities,  prior  to  classification,  a  training  sample  selection  and  evaluation  technique  by identifying its position in a horizontal vertical–vertical horizontal polarization (HV-HH) feature space was applied. The effectiveness of our method was demonstrated using ALOS PALSAR data (25 m mosaic, dual polarization) acquired in Jambi and South Sumatra, Indonesia. There were nine different classes  discriminated:  forest,  rubber  plantation,  mangrove  &  shrubs  with  trees,  oilpalm  &  coconut, shrubs,  cropland,  bare  soil,  settlement,  and  water.  Overall  accuracy  of  87.79%  was  obtained,  with producer’s accuracies for forest, rubber plantation, mangrove & shrubs with trees, cropland, and water class were greater than 92%.

scholarly journals INVESTIGATIONS ON SKIP-CONNECTIONS WITH AN ADDITIONAL COSINE SIMILARITY LOSS FOR LAND COVER CLASSIFICATION

2020 ◽  
Vol V-3-2020 ◽  
pp. 339-346
Author(s):  
C. Yang ◽  
F. Rottensteiner ◽  
C. Heipke
Keyword(s):  
Land Cover ◽  
Spatial Resolution ◽  
Feature Space ◽  
Land Cover Classification ◽  
Classification Performance ◽  
Cosine Similarity ◽  
Aerial Images ◽  
Layer By Layer ◽  
Feature Maps ◽  
Standard Task

Abstract. Pixel-based land cover classification of aerial images is a standard task in remote sensing, whose goal is to identify the physical material of the earth’s surface. Recently, most of the well-performing methods rely on encoder-decoder structure based convolutional neural networks (CNN). In the encoder part, many successive convolution and pooling operations are applied to obtain features at a lower spatial resolution, and in the decoder part these features are up-sampled gradually and layer by layer, in order to make predictions in the original spatial resolution. However, the loss of spatial resolution caused by pooling affects the final classification performance negatively, which is compensated by skip-connections between corresponding features in the encoder and the decoder. The most popular ways to combine features are element-wise addition of feature maps and 1x1 convolution. In this work, we investigate skip-connections. We argue that not every skip-connections are equally important. Therefore, we conducted experiments designed to find out which skip-connections are important. Moreover, we propose a new cosine similarity loss function to utilize the relationship of the features of the pixels belonging to the same category inside one mini-batch, i.e. these features should be close in feature space. Our experiments show that the new cosine similarity loss does help the classification. We evaluated our methods using the Vaihingen and Potsdam dataset of the ISPRS 2D semantic labelling challenge and achieved an overall accuracy of 91.1% for both test sites.

Sign in / Sign up

Export Citation Format

Share Document