scholarly journals Assessment of Deep Learning Techniques for Land Use Land Cover Classification in Southern New Caledonia

2021 ◽  
Vol 13 (12) ◽  
pp. 2257
Author(s):  
Guillaume Rousset ◽  
Marc Despinoy ◽  
Konrad Schindler ◽  
Morgan Mangeas
Keyword(s):  
Land Use ◽  
Deep Learning ◽  
Land Cover ◽  
Satellite Data ◽  
Data Augmentation ◽  
New Caledonia ◽  
Data Set ◽  
Detection Techniques ◽  
Learning Techniques ◽  
The Impact

Land use (LU) and land cover (LC) are two complementary pieces of cartographic information used for urban planning and environmental monitoring. In the context of New Caledonia, a biodiversity hotspot, the availability of up-to-date LULC maps is essential to monitor the impact of extreme events such as cyclones and human activities on the environment. With the democratization of satellite data and the development of high-performance deep learning techniques, it is possible to create these data automatically. This work aims at determining the best current deep learning configuration (pixel-wise vs semantic labelling architectures, data augmentation, image prepossessing, …), to perform LULC mapping in a complex, subtropical environment. For this purpose, a specific data set based on SPOT6 satellite data was created and made available for the scientific community as an LULC benchmark in a tropical, complex environment using five representative areas of New Caledonia labelled by a human operator: four used as training sets, and the fifth as a test set. Several architectures were trained and the resulting classification was compared with a state-of-the-art machine learning technique: XGboost. We also assessed the relevance of popular neo-channels derived from the raw observations in the context of deep learning. The deep learning approach showed comparable results to XGboost for LC detection and over-performed it on the LU detection task (61.45% vs. 51.56% of overall accuracy). Finally, adding LC classification output of the dedicated deep learning architecture to the raw channels input significantly improved the overall accuracy of the deep learning LU classification task (63.61% of overall accuracy). All the data used in this study are available on line for the remote sensing community and for assessing other LULC detection techniques.

scholarly journals A deep learning segmentation strategy that minimizes the amount of manually annotated images

F1000Research ◽  
2021 ◽  
Vol 10 ◽  
pp. 256
Author(s):  
Thierry Pécot ◽  
Alexander Alekseyenko ◽  
Kristin Wallace
Keyword(s):  
Deep Learning ◽  
Data Augmentation ◽  
Training Data ◽  
Artificial Data ◽  
Deep Convolutional Neural Networks ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Segmentation Strategy ◽  
Adversarial Network ◽  
The Impact

Deep learning has revolutionized the automatic processing of images. While deep convolutional neural networks have demonstrated astonishing segmentation results for many biological objects acquired with microscopy, this technology's good performance relies on large training datasets. In this paper, we present a strategy to minimize the amount of time spent in manually annotating images for segmentation. It involves using an efficient and open source annotation tool, the artificial increase of the training data set with data augmentation, the creation of an artificial data set with a conditional generative adversarial network and the combination of semantic and instance segmentations. We evaluate the impact of each of these approaches for the segmentation of nuclei in 2D widefield images of human precancerous polyp biopsies in order to define an optimal strategy.

scholarly journals Detecting Land Use Modification And Its Influence on Resident Communities

2020 ◽  
Author(s):  
Tesfahun Admas Endalew
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Land Cover Change ◽  
Thematic Mapper ◽  
Land Use Land Cover ◽  
Tree Plantation ◽  
Data Set ◽  
Entire Study ◽  
Socioeconomic Analysis ◽  
The Impact

Abstract Background The study intended to detecting the land use land cover changes, trends and their magnitude between 1986 and 2019 years by using GIS and remote sensing in Fagita Lekoma District, Amhara region, Ethiopia. Three satellite data set of Landsat Thematic Mapper for 1986, Enhanced Thematic Mapper Plus for 2002 and Operational Land Imager for 2019 were used generate land use and land cover maps of the study area. Post classification comparison changed detection method was employed to identify gains and losses between Land Use Land Cover classes. Socioeconomic survey, key informant interview and field observation were also used conclude the encouragement of land use /land cover change in the study area. Results The result shows that cultivated land and wetland similarly decline in the entire study periods. In the 33 years, forest lands expanded by upon 200% of the original forest cover what was existed on the base year. Whereas, a result of the socioeconomic analysis the expansion of Acacia decurrens tree plantations and agricultural land are main causes of land use land cover change in the study area. The impact of this land use land cover change is more significant on the livelihood condition and status of the study area. Conclusion The land use system of the study area highly converted cultivation land into forest/tree plantation. Mainly, the expansion of Acacia decurrens tree plantation on farmland is increasing the income of local residence when compare with the previous living condition in the study area.

scholarly journals Detecting Land Use Modification And Its Influence on Resident Communities

2020 ◽  
Author(s):  
Tesfahun Admas Endalew
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Land Cover Change ◽  
Thematic Mapper ◽  
Land Use Land Cover ◽  
Tree Plantation ◽  
Data Set ◽  
Entire Study ◽  
Socioeconomic Analysis ◽  
The Impact

Abstract Background The study intended to detecting the land use land cover changes, trends and their magnitude between 1986 and 2019 years by using GIS and remote sensing in Fagita Lekoma District, Amhara region, Ethiopia. Three satellite data set of Landsat Thematic Mapper for 1986, Enhanced Thematic Mapper Plus for 2002 and Operational Land Imager for 2019 were used generate land use and land cover maps of the study area. Post classification comparison changed detection method was employed to identify gains and losses between Land Use Land Cover classes. Socioeconomic survey, key informant interview and field observation were also used conclude the encouragement of land use /land cover change in the study area. Results The result shows that cultivated land and wetland similarly decline in the entire study periods. In the 33 years, forest lands expanded by upon 200% of the original forest cover what was existed on the base year. Whereas, a result of the socioeconomic analysis the expansion of Acacia decurrens tree plantations and agricultural land are main causes of land use land cover change in the study area. The impact of this land use land cover change is more significant on the livelihood condition and status of the study area. Conclusion The land use system of the study area highly converted cultivation land into forest/tree plantation. Mainly, the expansion of Acacia decurrens tree plantation on farmland is increasing the income of local residence when compare with the previous living condition in the study area.

scholarly journals Semantic Boosting: Enhancing Deep Learning Based LULC Classification

2021 ◽  
Vol 13 (16) ◽  
pp. 3197
Author(s):  
Marvin Mc Mc Cutchan ◽  
Alexis J. Comber ◽  
Ioannis Giannopoulos ◽  
Manuela Canestrini
Keyword(s):  
Land Use ◽  
Deep Learning ◽  
Land Cover ◽  
Information Science ◽  
Ground Truth ◽  
Vector Data ◽  
Remotely Sensed Imagery ◽  
The Impact ◽  
Sentinel 2

The classification of land use and land cover (LULC) is a well-studied task within the domain of remote sensing and geographic information science. It traditionally relies on remotely sensed imagery and therefore models land cover classes with respect to their electromagnetic reflectances, aggregated in pixels. This paper introduces a methodology which enables the inclusion of geographical object semantics (from vector data) into the LULC classification procedure. As such, information on the types of geographic objects (e.g., Shop, Church, Peak, etc.) can improve LULC classification accuracy. In this paper, we demonstrate how semantics can be fused with imagery to classify LULC. Three experiments were performed to explore and highlight the impact and potential of semantics for this task. In each experiment CORINE LULC data was used as a ground truth and predicted using imagery from Sentinel-2 and semantics from LinkedGeoData using deep learning. Our results reveal that LULC can be classified from semantics only and that fusing semantics with imagery—Semantic Boosting—improved the classification with significantly higher LULC accuracies. The results show that some LULC classes are better predicted using only semantics, others with just imagery, and importantly much of the improvement was due to the ability to separate similar land use classes. A number of key considerations are discussed.

scholarly journals A Trustworthy Learning Technique for Securing Industrial Internet of Things Systems

2021 ◽  
pp. 33-48
Author(s):  
Osama Maher ◽  
◽  
◽  
Elena Sitnikova
Keyword(s):  
Deep Learning ◽  
Internet Of Things ◽  
Attack Detection ◽  
Cyber Attack ◽  
Industrial Internet Of Things ◽  
Detection Techniques ◽  
Cyber Threats ◽  
Learning Techniques ◽  
Industrial Internet ◽  
The Impact

Since the Industrial Internet of Things (IIoT) networks comprise heterogeneous manufacturing and technological devices and services, discovering advanced cyber threats is an arduous and risk-prone process. Cyber-attack detection techniques have been recently emerged to understand the process of obtaining knowledge about cyber threats to collect evidence. These techniques have broadly employed for identifying malicious events of cyber threats to protect organizations’ assets. The main limitation of these systems is that they are not able to discover and interpret new attack activities. This paper proposes a new adversarial deep learning for discovering adversarial attacks in IIoT networks. Evaluation of correlation reduction has been used as a means of feature selection for reducing the impact of data poisoning attacks on the subsequent deep learning techniques. Feed Forward Deep Neural Networks have been developed using across various parameter permutations, at differing rates of data poisoning, to develop a robust deep learning architecture. The results of the proposed technique have been compared with previously developed deep learning models, proving the increased robustness of the new deep learning architectures across the ToN_IoT datasets.

scholarly journals Detecting Land Use Modification and Its Influence on Resident Communities

2020 ◽  
Author(s):  
Tesfahun Endalew
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Land Cover Change ◽  
Thematic Mapper ◽  
Land Use Land Cover ◽  
Tree Plantation ◽  
Data Set ◽  
Entire Study ◽  
Socioeconomic Analysis ◽  
The Impact

Abstract The study intended to detecting the land use land cover changes, trends and their magnitude between 1986 and 2019 years by using GIS and remote sensing in Fagita Lekoma District, Amhara region, Ethiopia. Three satellite data set of Landsat Thematic Mapper for 1986, Enhanced Thematic Mapper Plus for 2002 and Operational Land Imager for 2019 were used generate land use and land cover maps of the study area. Post classification comparison changed detection method was employed to identify gains and losses between Land Use Land Cover classes. Socioeconomic survey, key informant interview and field observation were also used conclude the encouragement of land use /land cover change in the study area. The result shows that cultivated land and wetland similarly decline in the entire study periods. In the 33 years, forest lands expanded by upon 200% of the original forest cover what was existed on the base year. Whereas, a result of the socioeconomic analysis the expansion of Acacia decurrens tree plantations and agricultural land are main causes of land use land cover change in the study area. The impact of this land use land cover change is more significant on the livelihood condition and status of the study area. The land use system of the study area highly converted cultivation land into forest/tree plantation. Mainly, the expansion of Acacia decurrens tree plantation on farmland is increasing the income of local residence when compare with the previous living condition in the study area.

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

2020 ◽  
Vol 17 (3) ◽  
pp. 299-305 ◽  
Author(s):  
Riaz Ahmad ◽  
Saeeda Naz ◽  
Muhammad Afzal ◽  
Sheikh Rashid ◽  
Marcus Liwicki ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Recognition System ◽  
Learning Approach ◽  
Arabic Text ◽  
Data Set ◽  
Processing Step ◽  
Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

Sign in / Sign up

Export Citation Format

Share Document