scholarly journals Remote Sensing Image Classification with a Graph-Based Pre-Trained Neighborhood Spatial Relationship

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5602
Author(s):  
Xudong Guan ◽  
Chong Huang ◽  
Juan Yang ◽  
Ainong Li
Keyword(s):  
Remote Sensing ◽  
Land Cover ◽  
Image Classification ◽  
Probability Distributions ◽  
Spatial Relationship ◽  
Remote Sensing Image ◽  
Spatial Relationships ◽  
Fuzzy Classifier ◽  
Land Cover Types ◽  
Remote Sensing Image Classification

Previous knowledge of the possible spatial relationships between land cover types is one factor that makes remote sensing image classification “smarter”. In recent years, knowledge graphs, which are based on a graph data structure, have been studied in the community of remote sensing for their ability to build extensible relationships between geographic entities. This paper implements a classification scheme considering the neighborhood relationship of land cover by extracting information from a graph. First, a graph representing the spatial relationships of land cover types was built based on an existing land cover map. Empirical probability distributions of the spatial relationships were then extracted using this graph. Second, an image was classified based on an object-based fuzzy classifier. Finally, the membership of objects and the attributes of their neighborhood objects were joined to decide the final classes. Two experiments were implemented. Overall accuracy of the two experiments increased by 5.2% and 0.6%, showing that this method has the ability to correct misclassified patches using the spatial relationship between geo-entities. However, two issues must be considered when applying spatial relationships to image classification. The first is the “siphonic effect” produced by neighborhood patches. Second, the use of global spatial relationships derived from a pre-trained graph loses local spatial relationship in-formation to some degree.

scholarly journals Ensemble of Deep Learning-Based Multimodal Remote Sensing Image Classification Model on Unmanned Aerial Vehicle Networks

Mathematics ◽  
2021 ◽  
Vol 9 (22) ◽  
pp. 2984
Author(s):  
Gyanendra Prasad Joshi ◽  
Fayadh Alenezi ◽  
Gopalakrishnan Thirumoorthy ◽  
Ashit Kumar Dutta ◽  
Jinsang You
Keyword(s):  
Remote Sensing ◽  
Land Cover ◽  
Image Classification ◽  
Data Augmentation ◽  
Land Cover Classification ◽  
Remote Sensing Image ◽  
Environmental Modeling ◽  
Classification Model ◽  
Remote Sensing Images ◽  
Remote Sensing Image Classification

Recently, unmanned aerial vehicles (UAVs) have been used in several applications of environmental modeling and land use inventories. At the same time, the computer vision-based remote sensing image classification models are needed to monitor the modifications over time such as vegetation, inland water, bare soil or human infrastructure regardless of spectral, spatial, temporal, and radiometric resolutions. In this aspect, this paper proposes an ensemble of DL-based multimodal land cover classification (EDL-MMLCC) models using remote sensing images. The EDL-MMLCC technique aims to classify remote sensing images into the different cloud, shades, and land cover classes. Primarily, median filtering-based preprocessing and data augmentation techniques take place. In addition, an ensemble of DL models, namely VGG-19, Capsule Network (CapsNet), and MobileNet, is used for feature extraction. In addition, the training process of the DL models can be enhanced by the use of hosted cuckoo optimization (HCO) algorithm. Finally, the salp swarm algorithm (SSA) with regularized extreme learning machine (RELM) classifier is applied for land cover classification. The design of the HCO algorithm for hyperparameter optimization and SSA for parameter tuning of the RELM model helps to increase the classification outcome to a maximum level considerably. The proposed EDL-MMLCC technique is tested using an Amazon dataset from the Kaggle repository. The experimental results pointed out the promising performance of the EDL-MMLCC technique over the recent state of art approaches.

scholarly journals Classification of Land Cover from Remote Sensing Images using Morphological Linear Contact Distributions and Rough Sets

2019 ◽  
Vol 8 (3) ◽  
pp. 676-688
Keyword(s):  
Remote Sensing ◽  
Land Cover ◽  
Image Classification ◽  
Rough Sets ◽  
Remote Sensing Image ◽  
Google Earth ◽  
Classification Algorithm ◽  
Forest Monitoring ◽  
Remote Sensing Images ◽  
Remote Sensing Image Classification

Remote sensing image classification plays an essential role in computer vision and image processing to address the problems in the areas of agriculture, forest monitoring, urban development, environment protection, etc. A lot of literature is available on remote sensing image classification. But, it is still a research task even today because of the multitude of problems. RTBFCA (Rough Texture Based Features Classification Algorithm), a new classification algorithm has been proposed in this paper. This paper aims at classifying the remote sensing images into various cover types using mathematical morphology and rough sets. Morphological texture features (linear contact distributions) along with first order statistics are used to identify the pixels of various classes and the concepts of lower and upper approximations of rough sets are used for clustering the features of the pixels and then are finally classified to display the classified image. The proposed method was tested on Google Earth images and is able to classify even various crops patterns of a land cover image. The algorithm is compared with other algorithms like ”GLCM with rough sets”, ”intensity values with rough sets” and with ”linear contact distributions with rough sets”.

scholarly journals A Survey of Remote Sensing Image Classification Techniques Using AI Techniques

2021 ◽  
Vol 9 (VII) ◽  
pp. 2144-2148
Author(s):  
Mandeep Kaur
Keyword(s):  
Remote Sensing ◽  
Land Cover ◽  
Image Classification ◽  
Cost Effective ◽  
Remote Sensing Image ◽  
Terrain Classification ◽  
Classification Techniques ◽  
Remote Sensing Image Classification ◽  
Wide Range ◽  
Terrain Features

Subsequently Terrain Classification is one of the most liberal aspects of Remote Sensing in the field of Artificial Intelligence. Remote sensing image classification is the wide range area which first sense the part of image that is going to be classified afterwards classification takes place. The purpose of remote sensing is to get information out from the object without being coming in a direct contact with the object. The purpose of the classification process is the categorization of all the pixels in an image into several land cover classes, as well as the themes. The data that is to be categorized is then used to produce maps that are thematic of the land cover present in an image. Image classification enables the grouping of pixels to represent the coverage features of land (can be urban, forested, and agricultural and may also include other varieties of Terrain features). Image classification make use the reflectance statistics for determining the pixels and responds to Terrain features as well. There are several classification techniques which would use to manipulate the persistence for uncertainty, imprecision and cost effective solutions.

Deep Learning Based High-Resolution Remote Sensing Image classification

2017 ◽  
Vol 7 (10) ◽  
pp. 22
Author(s):  
Sumit Kaur
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Image Classification ◽  
Language Processing ◽  
Object Perception ◽  
Remote Sensing Image ◽  
Research Area ◽  
Remote Sensing Image Classification ◽  
Unsupervised Algorithms

Abstract- Deep learning is an emerging research area in machine learning and pattern recognition field which has been presented with the goal of drawing Machine Learning nearer to one of its unique objectives, Artificial Intelligence. It tries to mimic the human brain, which is capable of processing and learning from the complex input data and solving different kinds of complicated tasks well. Deep learning (DL) basically based on a set of supervised and unsupervised algorithms that attempt to model higher level abstractions in data and make it self-learning for hierarchical representation for classification. In the recent years, it has attracted much attention due to its state-of-the-art performance in diverse areas like object perception, speech recognition, computer vision, collaborative filtering and natural language processing. This paper will present a survey on different deep learning techniques for remote sensing image classification. 

Sign in / Sign up

Export Citation Format

Share Document