Semantic Segmentation using K-means Clustering and Deep Learning in Satellite Image

Barthakur, Manami; Sarma, Kandarpa Kumar

doi:10.1109/iespc.2019.8902391

Cited by 7 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The figure illustrates a similar size of objects. The proposed model used mean Intersection over Union (IoU) as illustrated in equation (1) ( Barthakur & Sarma, 2019 ) distance metric to estimate the number of anchor boxes. IoU in object detection is a method to calculate the distance of similarity between the bounding box of target and predicted output.…”

Section: The Proposed Detector Modelmentioning

confidence: 99%

Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection

Loey

Manogaran

Taha

et al. 2021

Sustainable Cities and Society

400

192

View full text Add to dashboard Cite

Section: The Proposed Detector Modelmentioning

confidence: 99%

Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection

Loey

Manogaran

Taha

et al. 2021

Sustainable Cities and Society

400

192

View full text Add to dashboard Cite

“…The ADAM optimizer reaches greater accuracy than SGDM. The mean [78] Intersection over Union (IoU) is used to estimate the anchor boxes. This model could not identify masked faces from videos.…”

Section: A Cnn Based Approachesmentioning

confidence: 99%

Comprehensive Review on Facemask Detection Techniques in the Context of Covid-19

et al. 2021

View full text Add to dashboard Cite

The outbreak of Coronavirus Disease 2019 (Covid-19) had an enormous impact on humanity. Till May 2021, almost 172 million people have been affected globally due to the contagious spread of Covid-19. Although the distribution of vaccines has been started, the worldwide mass distribution is yet to happen. According to the World Health Organization, wearing a facemask can reduce the contagious spread of Covid-19 significantly. The governments of different countries have recommended implementing the "no mask, no service" method to impede the spread of Covid-19. However, even the improper wearing of a facemask can obstruct the goal and lead to the spread of the virus. Therefore, to ensure public safety, a system for monitoring facemasks on faces, commonly known as a facemask detection algorithm, is essential for overcoming this crisis. The facemask detection algorithms are part of the object detection algorithms which are used to detect objects in an image. Among the various object detection algorithms, deep learning showed tremendous performance in facemask detection for its excellent feature extraction capability than the traditional machine learning algorithms. However, there remains a lot of scope for future research to build an efficient facemask detection system. Therefore, this study aims to draw attention to the researchers by providing a narrative and meta-analytic review on all the published works related to facemask detection in the context of Covid-19. Because facemask detection algorithms are run mainly by adopting object detection algorithms, this paper also explores the progress of object detection algorithms over the last few decades. A comprehensive analysis of different datasets used in facemask detection techniques by many studies has been explored. The performance comparison among these algorithms is discussed in narrative and meta-analytic approaches. Finally, this study concludes with a discussion of some of the major challenges and future scope in the related field.INDEX TERMS Covid-19, convolutional neural network, deep neural network, facemask detection, Covid-19 health, object detection, machine learning.

show abstract

“…Fard et al [34] proposed a novel approach for addressing the problem of joint clustering and learning representations. Barthakur and Sarma [35] proposed a deep learning-based method for the semantic segmentation of satellite images in a complex background. Sodjinou et al [36] proposed a deep semantic segmentation-based algorithm to segment crops and weeds in agronomic color images.…”

Section: Deep Clustering For Hsismentioning

confidence: 99%

Deep Spatial-Spectral Subspace Clustering for Hyperspectral Images Based on Contrastive Learning

Zhou

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Hyperspectral image (HSI) clustering is a major challenge due to the redundant spectral information in HSIs. In this paper, we propose a novel deep subspace clustering method that extracts spatial–spectral features via contrastive learning. First, we construct positive and negative sample pairs through data augmentation. Then, the data pairs are projected into feature space using a CNN model. Contrastive learning is conducted by minimizing the distances of positive pairs and maximizing those of negative pairs. Finally, based on their features, spectral clustering is employed to obtain the final result. Experimental results gained over three HSI datasets demonstrate that our proposed method is superior to other state-of-the-art methods.

show abstract

Semantic Segmentation using K-means Clustering and Deep Learning in Satellite Image

Cited by 7 publications

References 8 publications

Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection

Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection

Comprehensive Review on Facemask Detection Techniques in the Context of Covid-19

Deep Spatial-Spectral Subspace Clustering for Hyperspectral Images Based on Contrastive Learning

Contact Info

Product

Resources

About