scholarly journals Evaluation of Semantic Segmentation Methods for Land Use with Spectral Imaging Using Sentinel-2 and PNOA Imagery

2021 ◽  
Vol 13 (12) ◽  
pp. 2292
Author(s):  
Oscar D. Pedrayes ◽  
Darío G. Lema ◽  
Daniel F. García ◽  
Rubén Usamentiaga ◽  
Ángela Alonso
Keyword(s):  
Land Use ◽  
Satellite Imagery ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Aerial Imagery ◽  
Land Use Classification ◽  
Cost Performance ◽  
Sampling Distance ◽  
Segmentation Methods ◽  
Sentinel 2

Land use classification using aerial imagery can be complex. Characteristics such as ground sampling distance, resolution, number of bands and the information these bands convey are the keys to its accuracy. Random Forest is the most widely used approach but better and more modern alternatives do exist. In this paper, state-of-the-art methods are evaluated, consisting of semantic segmentation networks such as UNet and DeepLabV3+. In addition, two datasets based on aircraft and satellite imagery are generated as a new state of the art to test land use classification. These datasets, called UOPNOA and UOS2, are publicly available. In this work, the performance of these networks and the two datasets generated are evaluated. This paper demonstrates that ground sampling distance is the most important factor in obtaining good semantic segmentation results, but a suitable number of bands can be as important. This proves that both aircraft and satellite imagery can produce good results, although for different reasons. Finally, cost performance for an inference prototype is evaluated, comparing various Microsoft Azure architectures. The evaluation concludes that using a GPU is unnecessarily costly for deployment. A GPU need only be used for training.

scholarly journals The Mapping of Land Use Using Object-Based Image Analysis (OBIA) in Klaten Regency

2020 ◽  
Vol 202 ◽  
pp. 06036
Author(s):  
Nurhadi Bashit ◽  
Novia Sari Ristianti ◽  
Yudi Eko Windarto ◽  
Desyta Ulfiana
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Image Analysis ◽  
Satellite Imagery ◽  
Agricultural Land ◽  
Scale Parameter ◽  
Land Use Classification ◽  
Object Based Image Analysis ◽  
Object Based ◽  
Sentinel 2

Klaten Regency is one of the regencies in Central Java Province that has an increasing population every year. This can cause an increase in built-up land for human activities. The built-up land needs to be monitored so that the construction is in accordance with the regional development plan so that it does not cause problems such as the occurrence of critical land. Therefore, it is necessary to monitor land use regularly. One method for monitoring land use is the remote sensing method. The remote sensing method is much more efficient in mapping land use because without having to survey the field. The remote sensing method utilizes satellite imagery data that can be processed for land use classification. This study uses the sentinel 2 satellite image data with the Object-Based Image Analysis (OBIA) algorithm to obtain land use classification. Sentinel 2 satellite imagery is a medium resolution image category with a spatial resolution of 10 meters. The land use classification can be used to see the distribution of built-up land in Klaten Regency without having to conduct a field survey. The results of the study obtained a segmentation scale parameter value of 60 and a merge scale parameter value of 85. The classification results obtained by 5 types of land use with OBIA. Agricultural land use dominates with an area of 50% of the total area.

scholarly journals LAND USE CLASSIFICATION BASED ON MULTI-STRUCTURE CONVOLUTION NEURAL NETWORK FEATURES CASCADING

2019 ◽  
Vol XLII-2/W16 ◽  
pp. 163-167
Author(s):  
J. Men ◽  
L. Fang ◽  
Y. Liu ◽  
Y. Sun
Keyword(s):  
Land Use ◽  
State Of The Art ◽  
Image Features ◽  
Classification Task ◽  
Land Use Classification ◽  
The Core ◽  
Margin Distribution ◽  
Feature Extractor ◽  
Image Representations ◽  
Fully Connected

<p><strong>Abstract.</strong> Learning efficient image representations is at the core of the classification task of remote sensing imagery. The existing methods for solving image classification task, based on either feature coding approaches extracted from convolution neural networks(CNNs) or training new CNNs, can only generate image features with limited representative ability, which essentially prevents them from achieving better performance. In this paper, we investigate how to transfer features from these successfully pre-trained CNNs for classification. We propose a scenario for generating image features via cascading features extracted from different CNNs. First, pre-trained CNNs, like CaffeNet, VGG-S and VGG-F, are used as feature extractor since their different structures help extract richer information of images. Then the fully-connected layers of the pre-trained CNNs are fine-tuned with UC Merced land use dataset. Finally, the image features generating from cascading the outputs of three networks above, are fed into multi-class Optimal Margin Distribution Machine (mcODM) to obtain the final classification results. Extensive experiments on public land use classification dataset demonstrates that the image features obtained by the proposed scenario can result in remarkable performance and improve the state-of-the-art by a significant margin. The results reveal that the features from pre-trained CNNs generalize well to land use dataset and are more expressive than features from single CNN.</p>

scholarly journals Multidimensional Land-use Information for Local Planning and Land Resources Assessment in Indonesia: Classification Scheme for Information Extraction from High-Spatial Resolution Imagery

2019 ◽  
Vol 51 (2) ◽  
pp. 131
Author(s):  
Projo Danoedoro
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Satellite Imagery ◽  
Survey Methods ◽  
Evaluation Criteria ◽  
Relevant Information ◽  
Land Use Classification ◽  
Local Planning ◽  
Specific Content ◽  
Data Source

Suitable land-cover/land-use  information is rarely available in most developing countries, particularly when newness, accuracy, relevance, and compatibility are used as evaluation criteria.  In Indonesia, various institutions developed their own maps with considerable differences in classification schemes, data sources and scales, as well as in survey methods.  Redundant land-cover/land-use surveys of the same area are frequently carried out to ensure the data contains relevant information. To overcome this problem, a multidimensional land-use classification system was developed. The system uses satellite imagery as main data source, with a multi-dimensional approach to link  land-cover information to land-use-related categories.  The land-cover/land-use layers represent image-based land-cover (spectral), spatial, temporal, ecological and socio-economic dimensions.  The final land-cover/land-use database can be used to derive a map with  specific content relevant to particular planning tasks. Methods for mapping each dimension are described in this paper, with examples using Quickbird satellite imagery covering a small part the Semarang area, Indonesia.  The approaches and methods used in this study may be applied to other countries having characteristics similar to those of Indonesia

scholarly journals Understanding deep learning in land use classification based on Sentinel-2 time series

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Manuel Campos-Taberner ◽  
Francisco Javier García-Haro ◽  
Beatriz Martínez ◽  
Emma Izquierdo-Verdiguier ◽  
Clement Atzberger ◽  
...  
Keyword(s):  
Neural Network ◽  
Land Use ◽  
Time Series ◽  
Deep Learning ◽  
Agricultural Policy ◽  
Near Infrared ◽  
Land Use Classification ◽  
Policy Compliance ◽  
Economic Return ◽  
Sentinel 2

Abstract The use of deep learning (DL) approaches for the analysis of remote sensing (RS) data is rapidly increasing. DL techniques have provided excellent results in applications ranging from parameter estimation to image classification and anomaly detection. Although the vast majority of studies report precision indicators, there is a lack of studies dealing with the interpretability of the predictions. This shortcoming hampers a wider adoption of DL approaches by a wider users community, as model’s decisions are not accountable. In applications that involve the management of public budgets or policy compliance, a better interpretability of predictions is strictly required. This work aims to deepen the understanding of a recurrent neural network for land use classification based on Sentinel-2 time series in the context of the European Common Agricultural Policy (CAP). This permits to address the relevance of predictors in the classification process leading to an improved understanding of the behaviour of the network. The conducted analysis demonstrates that the red and near infrared Sentinel-2 bands convey the most useful information. With respect to the temporal information, the features derived from summer acquisitions were the most influential. These results contribute to the understanding of models used for decision making in the CAP to accomplish the European Green Deal (EGD) designed in order to counteract climate change, to protect biodiversity and ecosystems, and to ensure a fair economic return for farmers.

scholarly journals Towards a Multi-Temporal Deep Learning Approach for Mapping Urban Fabric Using Sentinel 2 Images

2020 ◽  
Vol 12 (3) ◽  
pp. 423 ◽  
Author(s):  
Lamiae El Mendili ◽  
Anne Puissant ◽  
Mehdi Chougrad ◽  
Imane Sebari
Keyword(s):  
Land Use ◽  
Deep Learning ◽  
Urban Land ◽  
Urban Land Use ◽  
Land Use Classification ◽  
Urban Fabric ◽  
Temporal Dimension ◽  
The Future ◽  
Multi Temporal ◽  
Sentinel 2

The major part of the population lives in urban areas, and this is expected to increase in the future. The main challenges faced by cities currently and towards the future are the rapid urbanization, the increase in urban temperature and the urban heat island. Mapping and monitoring urban fabric (UF) to analyze the environmental impact of these phenomena is more necessary than ever. This coupled with the increased availability of Earth observation data and their growing temporal capabilities leads us to consider using temporal features for improving land use classification, especially in urban environments where the spectral overlap between classes makes it challenging. Urban land use classification thus remains a central question in remote sensing. Although some research studies have successfully used multi-temporal images such as Landsat-8 or Sentinel-2 to improve land cover classification, urban land use mapping is rarely carried using the temporal dimension. This paper explores the use of Sentinel-2 data in a deep learning framework, by firstly assessing the temporal robustness of four popular fully convolutional neural networks (FCNs) trained over single-date images for the classification of the urban footprint, and secondly, by proposing a multi-temporal FCN. A performance comparison between the proposed framework and a regular FCN is also conducted. In this study, we consider four UF classes typical of many European Western cities. Results show that training the proposed multi-date model on Sentinel 2 multi-temporal data achieved the best results with a Kappa coefficient increase of 2.72% and 6.40%, respectively for continuous UF and industrial facilities. Although a more definitive conclusion requires further testing, first results are promising because they confirm that integrating the temporal dimension with a high spatial resolution into urban land use classification may be a valuable strategy to discriminate among several urban categories.

scholarly journals NPALOSS: NEIGHBORING PIXEL AFFINITY LOSS FOR SEMANTIC SEGMENTATION IN HIGH-RESOLUTION AERIAL IMAGERY

2020 ◽  
Vol V-2-2020 ◽  
pp. 475-482
Author(s):  
Y. Feng ◽  
W. Diao ◽  
X. Sun ◽  
J. Li ◽  
K. Chen ◽  
...  
Keyword(s):  
High Resolution ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Aerial Imagery ◽  
Normalization Strategy ◽  
Pixel Pair ◽  
Neighboring Pixel ◽  
The Common ◽  
Object Shapes ◽  
Better Than

Abstract. The performance of semantic segmentation in high-resolution aerial imagery has been improved rapidly through the introduction of deep fully convolutional neural network (FCN). However, due to the complexity of object shapes and sizes, the labeling accuracy of small-sized objects and object boundaries still need to be improved. In this paper, we propose a neighboring pixel affinity loss (NPALoss) to improve the segmentation performance of these hard pixels. Specifically, we address the issues of how to determine the classifying difficulty of one pixel and how to get the suitable weight margin between well-classified pixels and hard pixels. Firstly, we convert the first problem into a problem that the pixel categories in the neighborhood are the same or different. Based on this idea, we build a neighboring pixel affinity map by counting the pixel-pair relationships for each pixel in the search region. Secondly, we investigate different weight transformation strategies for the affinity map to explore the suitable weight margin and avoid gradient overflow. The logarithm compression strategy is better than the normalization strategy, especially the common logarithm. Finally, combining the affinity map and logarithm compression strategy, we build NPALoss to adaptively assign different weights for each pixel. Comparative experiments are conducted on the ISPRS Vaihingen dataset and several commonly-used state-of-the-art networks. We demonstrate that our proposed approach can achieve promising results.

Sign in / Sign up

Export Citation Format

Share Document