Block Compressive Sampling and Wiener Curvelet Denoising Approach for Satellite Images

Monika, R.; Bala, Abubakar; Suvarnamma, Adi

doi:10.1007/978-981-10-5520-1_2

Cited by 3 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sampling at block level requires various Map process modifications, mostly related to accessing the storage system (22). HDFS provides many common random ac-cess methods, but the process is expensive and deliberately useable.…”

Section: Block Level Samplingmentioning

confidence: 99%

Faster as Well as Early Measurements from Big Data Predictive Analytics Model

et al. 2022

View full text Add to dashboard Cite

Data processing in large scale system and analyses is the key problems of today's distributed systems in real-time and close to real time. These systems should be able, while meeting these constraints, to process large-scale data inputs, to expand to terabytes or larger. Volume of processing the data over the systems of large scale becomes too large. These systems use parallelization of the data and similar techniques to increase performance. The standards are increasing, though: data analyses are expected almost in real time. Among all the data treatment models Map Reduce is mostly adopted. Due to the processing of data design in this method, once work is finished, the results are returned. The growth of data is not always a preferred batch operating environment: large numbers of applications can benefit from early results. The online aggregation method used in connection databases was first discussed. In this work analysis we discuss techniques that can allow early results to be estimated. We are proposing some changes to the online system for Map Reduce. We show that the properties required for accurate evaluation of the effects of our proposed device design changes. The reduction of data bias algorithm and sampling at the block levels are provided. Consequently, with a series of particular applications and sets of data, the implementation of the proposed design of the system is defined and evaluated.

show abstract

Section: Block Level Samplingmentioning

confidence: 99%

Faster as Well as Early Measurements from Big Data Predictive Analytics Model

et al. 2022

View full text Add to dashboard Cite

show abstract

“…But the work has to be enhanced by inducing early prediction of disaster and enabling a disaster-free environment. R. Monika et al (2018) According to the literature study, an essential difficulty in aerial image landscape monitoring is the precise analysis of the landscape's state both before and after a disaster. Without monitoring and redevelopment, the altered patterns of the landscape, damaged pathways, and damaged places will have a significant impact.…”

Section: Literature Reviewmentioning

confidence: 99%

Advanced deep learning method for Aerial image segmentation of landscape changes in pre-and post-disaster scenarios

2022

Global NEST: The International Journal

View full text Add to dashboard Cite

<p>The precise analysis of conditions in the landscape before and aftermath of the disaster is a mandatory challenge in aerial image landscape monitoring. The change in patterns of landscape, damaged pathways, and damaged areas will have a major impact without monitoring and redevelopment. Therefore, semantic segmentation of the landscape is required in order to analyze the changes and avoid other risks in pre-and post-disaster scenarios. To address these queries a deep learning-based landscape monitoring method is presented in this work. A Gated Shaped Convolution Neural Network is utilized for the semantic segmentation of the aerial landscape images. Initially the aerial image undergoes pre-processing with the process of dilation and GSCNN emphasize the shaped and boundary masks of the affected landscape. To choose the best possible pathways and solutions for development the GSCNN undergoes the particle swarm optimization. In the present study, the proposed PSO-GSCNN is evaluated by comparing the accuracy, precision, and recall of the proposed method with Restricted Boltzmann Machines (RBMs), Convolutional Neural Networks, and Fuse-Net segmentation methods. In comparison with conventional RSM, CNN, and Fuse-Net, the accuracy rate of the model is 97.65%, the precision rate is 98.21%, and the recall rate is 97.23%. This technique has achieved 97.66% accuracy, 97% precision, and 96% recall, all higher than the existing methods.</p>

show abstract