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>

Fusion Based AER System Using Deep Learning Approach for Amplitude and Frequency Analysis

2022 ◽  
Vol 21 (3) ◽  
pp. 1-19
Author(s):  
A. Pramod Reddy ◽  
Vijayarajan V.
Keyword(s):  
State Of The Art ◽  
Deep Understanding ◽  
Image Features ◽  
Frequency Scale ◽  
Proposed Model ◽  
Fused Image ◽  
Near Term ◽  
Fully Connected ◽  
Frequency Features ◽  
Fine Tune

Automatic emotion recognition from Speech (AERS) systems based on acoustical analysis reveal that some emotional classes persist with ambiguity. This study employed an alternative method aimed at providing deep understanding into the amplitude–frequency, impacts of various emotions in order to aid in the advancement of near term, more effectively in classifying AER approaches. The study was undertaken by converting narrow 20 ms frames of speech into RGB or grey-scale spectrogram images. The features have been used to fine-tune a feature selection system that had previously been trained to recognise emotions. Two different Linear and Mel spectral scales are used to demonstrate a spectrogram. An inductive approach for in sighting the amplitude and frequency features of various emotional classes. We propose a two-channel profound combination of deep fusion network model for the efficient categorization of images. Linear and Mel- spectrogram is acquired from Speech-signal, which is prepared in the recurrence area to input Deep Neural Network. The proposed model Alex-Net with five convolutional layers and two fully connected layers acquire most vital features form spectrogram images plotted on the amplitude-frequency scale. The state-of-the-art is compared with benchmark dataset (EMO-DB). RGB and saliency images are fed to pre-trained Alex-Net tested both EMO-DB and Telugu dataset with an accuracy of 72.18% and fused image features less computations reaching to an accuracy 75.12%. The proposed model show that Transfer learning predict efficiently than Fine-tune network. When tested on Emo-DB dataset, the propȯsed system adequately learns discriminant features from speech spectrȯgrams and outperforms many stȧte-of-the-art techniques.

scholarly journals LAND USE CLASSIFICATION USING DEEP MULTITASK NETWORKS

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 17-21
Author(s):  
J. R. Bergado ◽  
C. Persello ◽  
A. Stein
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Urban Areas ◽  
Large Scale ◽  
Urban Land ◽  
Urban Land Use ◽  
The Other ◽  
Classification Task ◽  
Land Use Classification ◽  
Convolutional Network

Abstract. Updated information on urban land use allows city planners and decision makers to conduct large scale monitoring of urban areas for sustainable urban growth. Remote sensing data and classification methods offer an efficient and reliable way to update such land use maps. Features extracted from land cover maps are helpful on performing a land use classification task. Such prior information can be embedded in the design of a deep learning based land use classifier by applying a multitask learning setup—simultaneously solving a land use and a land cover classification task. In this study, we explore a fully convolutional multitask network to classify urban land use from very high resolution (VHR) imagery. We experimented with three different setups of the fully convolutional network and compared it against a baseline random forest classifier. The first setup is a standard network only predicting the land use class of each pixel in the image. The second setup is a multitask network that concatenates the land use and land cover class labels in the same output layer of the network while the other setup accept as an input the land cover predictions, predicted by a subpart of the network, concatenated to the original input image patches. The two deep multitask networks outperforms the other two classifiers by at least 30% in average F1-score.

scholarly journals A Concurrent and Hierarchy Target Learning Architecture for Classification in SAR Application

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3218
Author(s):  
Mohamed Touafria ◽  
Qiang Yang
Keyword(s):  
State Of The Art ◽  
Automatic Target Recognition ◽  
Image Features ◽  
Training Data ◽  
Synthetic Aperture ◽  
Learning Networks ◽  
Sar Images ◽  
Stationary Target ◽  
Fully Connected ◽  
New Framework

This article discusses the issue of Automatic Target Recognition (ATR) on Synthetic Aperture Radar (SAR) images. Through learning the hierarchy of features automatically from a massive amount of training data, learning networks such as Convolutional Neural Networks (CNN) has recently achieved state-of-the-art results in many tasks. To extract better features about SAR targets, and to obtain better accuracies, a new framework is proposed: First, three CNN models based on different convolution and pooling kernel sizes are proposed. Second, they are applied simultaneously on the SAR images to generate image features via extracting CNN features from different layers in two scenarios. In the first scenario, the activation vectors obtained from fully connected layers are considered as the final image features; in the second scenario, dense features are extracted from the last convolutional layer and then encoded into global image features through one of the commonly used feature coding approaches, which is Fisher Vectors (FVs). Finally, different combination and fusion approaches between the two sets of experiments are considered to construct the final representation of the SAR images for final classification. Extensive experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset are conducted. Experimental results prove the capability of the proposed method, as compared to several state-of-the-art methods.

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 Multi-hop assortativities for network classification

2018 ◽  
Vol 7 (4) ◽  
pp. 603-622 ◽  
Author(s):  
Leonardo Gutiérrez-Gómez ◽  
Jean-Charles Delvenne
Keyword(s):  
Machine Learning ◽  
Scientific Collaboration ◽  
State Of The Art ◽  
Medical Engineering ◽  
Research Field ◽  
Classification Task ◽  
Collaboration Network ◽  
Structural Patterns ◽  
Art Methods

Abstract Several social, medical, engineering and biological challenges rely on discovering the functionality of networks from their structure and node metadata, when it is available. For example, in chemoinformatics one might want to detect whether a molecule is toxic based on structure and atomic types, or discover the research field of a scientific collaboration network. Existing techniques rely on counting or measuring structural patterns that are known to show large variations from network to network, such as the number of triangles, or the assortativity of node metadata. We introduce the concept of multi-hop assortativity, that captures the similarity of the nodes situated at the extremities of a randomly selected path of a given length. We show that multi-hop assortativity unifies various existing concepts and offers a versatile family of ‘fingerprints’ to characterize networks. These fingerprints allow in turn to recover the functionalities of a network, with the help of the machine learning toolbox. Our method is evaluated empirically on established social and chemoinformatic network benchmarks. Results reveal that our assortativity based features are competitive providing highly accurate results often outperforming state of the art methods for the network classification task.

scholarly journals Development of Land Use Regression Model for Seasonal Variation of Nitrogen Dioxide (NO2) in Lahore, Pakistan

2021 ◽  
Vol 13 (9) ◽  
pp. 4933
Author(s):  
Saimar Pervez ◽  
Ryuta Maruyama ◽  
Ayesha Riaz ◽  
Satoshi Nakai
Keyword(s):  
Land Use ◽  
Air Pollution ◽  
Regression Model ◽  
Urban Areas ◽  
Industrial Development ◽  
Ambient Air ◽  
Ambient Air Pollution ◽  
Land Use Classification ◽  
Land Use Regression ◽  
Air Exposure

Ambient air pollution and its exposure has been a worldwide issue and can increase the possibility of health risks especially in urban areas of developing countries having the mixture of different air pollution sources. With the increase in population, industrial development and economic prosperity, air pollution is one of the biggest concerns in Pakistan after the occurrence of recent smog episodes. The purpose of this study was to develop a land use regression (LUR) model to provide a better understanding of air exposure and to depict the spatial patterns of air pollutants within the city. Land use regression model was developed for Lahore city, Pakistan using the average seasonal concentration of NO2 and considering 22 potential predictor variables including road network, land use classification and local specific variable. Adjusted explained variance of the LUR models was highest for post-monsoon (77%), followed by monsoon (71%) and was lowest for pre-monsoon (70%). This is the first study conducted in Pakistan to explore the applicability of LUR model and hence will offer the application in other cities. The results of this study would also provide help in promoting epidemiological research in future.

scholarly journals Image Restoration by Learning Morphological Opening-Closing Network

2020 ◽  
Vol 4 (1) ◽  
pp. 87-107
Author(s):  
Ranjan Mondal ◽  
Moni Shankar Dey ◽  
Bhabatosh Chanda
Keyword(s):  
Neural Network ◽  
Image Restoration ◽  
State Of The Art ◽  
Source Code ◽  
Back Propagation ◽  
Image Features ◽  
Main Difficulty ◽  
The Right ◽  
Right Order ◽  
Morphological Opening

AbstractMathematical morphology is a powerful tool for image processing tasks. The main difficulty in designing mathematical morphological algorithm is deciding the order of operators/filters and the corresponding structuring elements (SEs). In this work, we develop morphological network composed of alternate sequences of dilation and erosion layers, which depending on learned SEs, may form opening or closing layers. These layers in the right order along with linear combination (of their outputs) are useful in extracting image features and processing them. Structuring elements in the network are learned by back-propagation method guided by minimization of the loss function. Efficacy of the proposed network is established by applying it to two interesting image restoration problems, namely de-raining and de-hazing. Results are comparable to that of many state-of-the-art algorithms for most of the images. It is also worth mentioning that the number of network parameters to handle is much less than that of popular convolutional neural network for similar tasks. The source code can be found here https://github.com/ranjanZ/Mophological-Opening-Closing-Net

scholarly journals A Comparative Analysis of Spatial Data and Land Use/Land Cover Classification in Urbanized Areas and Areas Subjected to Anthropogenic Pressure for the Example of Poland

2021 ◽  
Vol 13 (6) ◽  
pp. 3070
Author(s):  
Patrycja Szarek-Iwaniuk
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Land Cover Classification ◽  
Classification Systems ◽  
Anthropogenic Pressure ◽  
Land Use Land Cover ◽  
Land Use Classification ◽  
Land Cover Data ◽  
Spatial Changes ◽  
Land Use Types

Urbanization processes are some of the key drivers of spatial changes which shape and influence land use and land cover. The aim of sustainable land use policies is to preserve and manage existing resources for present and future generations. Increasing access to information about land use and land cover has led to the emergence of new sources of data and various classification systems for evaluating land use and spatial changes. A single globally recognized land use classification system has not been developed to date, and various sources of land-use/land-cover data exist around the world. As a result, data from different systems may be difficult to interpret and evaluate in comparative analyses. The aims of this study were to compare land-use/land-cover data and selected land use classification systems, and to determine the influence of selected classification systems and spatial datasets on analyses of land-use structure in the examined area. The results of the study provide information about the existing land-use/land-cover databases, revealing that spatial databases and land use and land cover classification systems contain many equivalent land-use types, but also differ in various respects, such as the level of detail, data validity, availability, number of land-use types, and the applied nomenclature.

Sign in / Sign up

Export Citation Format

Share Document