A review of remotely sensed satellite image classification

Dhingra, Sakshi; Kumar, Dharminder

doi:10.11591/ijece.v9i3.pp1720-1731

Cited by 50 publications

(29 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We further compare all the above-mentioned region-based approaches with two baseline pixel-based methods, relying respectively on Maximum Likelihood (ML) classification, and on Support Vector Machines (SVMs). ML is one of the most popular supervised classification methods in Remote Sensing (RS) [9]. Following the Bayes theorem, the ML classifier assigns a pixel to the class with the highest likelihood, considering the respective probability density functions derived from the training data.…”

Section: Methodsmentioning

confidence: 99%

A Meta-Methodology for Improving Land Cover and Land Use Classification with SAR Imagery

et al. 2020

View full text Add to dashboard Cite

Per-point classification is a traditional method for remote sensing data classification, and for radar data in particular. Compared with optical data, the discriminative power of radar data is quite limited, for most applications. A way of trying to overcome these difficulties is to use Region-Based Classification (RBC), also referred to as Geographical Object-Based Image Analysis (GEOBIA). RBC methods first aggregate pixels into homogeneous objects, or regions, using a segmentation procedure. Moreover, segmentation is known to be an ill-conditioned problem because it admits multiple solutions, and a small change in the input image, or segmentation parameters, may lead to significant changes in the image partitioning. In this context, this paper proposes and evaluates novel approaches for SAR data classification, which rely on specialized segmentations, and on the combination of partial maps produced by classification ensembles. Such approaches comprise a meta-methodology, in the sense that they are independent from segmentation and classification algorithms, and optimization procedures. Results are shown that improve the classification accuracy from Kappa = 0.4 (baseline method) to a Kappa = 0.77 with the presented method. Another test site presented an improvement from Kappa = 0.36 to a maximum of 0.66 also with radar data.

show abstract

Section: Methodsmentioning

confidence: 99%

A Meta-Methodology for Improving Land Cover and Land Use Classification with SAR Imagery

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The various techniques discussed and applied on the remote images to check the effectiveness of different approaches. The validity of the classifier and optimization approaches has been evaluated to attain the required outcomes [12].But the main drawback is that all the images to sense the required features was not covered. So, the present survey does not seems to be fruitful for the other researchers.…”

Section: Related Workmentioning

confidence: 99%

The Hybridization of Neural Network and Particle Swarm Optimization for Natural Terrain Feature Extraction

Dhingra*,

Kumar

2019

IJITEE

View full text Add to dashboard Cite

The optimization of various soft computing and metaheuristic techniques can be ameliorated in a global area network, Swarm intelligence. In this research, a hybrid algorithm of neural network and particle swarm optimization has been presented for remote sensing applications. The terrain features of the land in a remote sensing image have been classified using these algorithms. Remote sensing basically deals with the processing and interpretation of satellite images without any physical contact to that particular region. In addition, the geospatial characteristics of the data also recorded during image classification. The hybrid concept used in this research, the implementation of algorithm in this paper based on the neurons network to find the best solution, which is further resolved using the Particle Swarm Optimization approach, an optimization technique. The proposed algorithm easily classifies the terrain features with higher efficiency and kappa coefficient value. The results show that 94.36% accuracy attained from the proposed technique. The overall accuracy improved by 5.24 % and 14.93% and kappa coefficient enhancement of 6.97 % and 18.99 % in comparison to existing studies.

show abstract

“…For the supervised methods, Support Vector Machines (SVMs) have been often used for the classification of satellite images [28,29] mainly because of its high accuracy in scenarios where there are few available labeled samples. Nevertheless, a proper setup of its hyperparameters, including the appropriate kernel function, is essential to achieve good generalization.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Deep Learning Techniques for Deforestation Detection in the Brazilian Amazon and Cerrado Biomes From Remote Sensing Imagery

et al. 2020

View full text Add to dashboard Cite

Deforestation is one of the major threats to natural ecosystems. This process has a substantial contribution to climate change and biodiversity reduction. Therefore, the monitoring and early detection of deforestation is an essential process for preservation. Techniques based on satellite images are among the most attractive options for this application. However, many approaches involve some human intervention or are dependent on a manually selected threshold to identify regions that suffer deforestation. Motivated by this scenario, the present work evaluates Deep Learning-based strategies for automatic deforestation detection, namely, Early Fusion (EF), Siamese Network (SN), and Convolutional Support Vector Machine (CSVM) as well as Support Vector Machine (SVM), used as the baseline. The target areas are two regions with different deforestation patterns: the Amazon and Cerrado biomes in Brazil. The experiments used two co-registered Landsat 8 images acquired at different dates. The strategies based on Deep Learning achieved the best performance in our analysis in comparison with the baseline, with SN and EF superior to CSVM and SVM. In the same way, a reduction of the salt-and-pepper effect in the generated probabilistic change maps was noticed as the number of training samples increased. Finally, the work assesses how the methods can reduce the time invested in the visual inspection of deforested areas.

show abstract

A review of remotely sensed satellite image classification

Cited by 50 publications

References 11 publications

A Meta-Methodology for Improving Land Cover and Land Use Classification with SAR Imagery

A Meta-Methodology for Improving Land Cover and Land Use Classification with SAR Imagery

The Hybridization of Neural Network and Particle Swarm Optimization for Natural Terrain Feature Extraction

Evaluation of Deep Learning Techniques for Deforestation Detection in the Brazilian Amazon and Cerrado Biomes From Remote Sensing Imagery

Contact Info

Product

Resources

About