An Alternative Method for Snow Cover Mapping on Satellite Images by Modern Applied Mathematics

Kuter, Semih; Akyürek, Zuhal; Kuter, Nazan; Weber, Gerhard‐Wilhelm

doi:10.1007/978-3-319-55236-1_13

Cited by 3 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…35 Multiresponse MARS approach is adopted for snow mapping on MODIS images. 36 The classification methods such as ML classification and SVMs are applied to two Landsat 7 ETM+ image of different times to assess the land-cover and land-use changes. 37 Existing classifiers such as Baye's classifier, SVM, ANN, and ML technique require training dataset to delineate the urban and vegetation area.…”

Section: Related Workmentioning

confidence: 99%

“…However, atmospheric correction models are constructed using conic multivariate adaptive regression splines to overcome the drawbacks of MARS 35 . Multiresponse MARS approach is adopted for snow mapping on MODIS images 36 . The classification methods such as ML classification and SVMs are applied to two Landsat 7 ETM+ image of different times to assess the land‐cover and land‐use changes 37…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Mixed pixel removal in north Tamil Nadu region for accurate area measurement

Mani¹,

Nagalingam²,

Aruldoss³

et al. 2021

Computational Intelligence

View full text Add to dashboard Cite

In remote sensing, vegetation and water areas delineation from satellite image plays a vital role for urban and rural planning. Delineation of vegetation and water area is a challenging task due to mixed pixels and geometric distortion over the boundary region. Geometric distortion arises due to change in velocity and speed of satellite during image acquisition, and mixed pixels arises due to different surfaces in a particular area. Traditional methods apply classifier algorithms such as support vector machine, neural network, and fuzzy for vegetation and water area delineation. The traditional methods require more training dataset and consume more interpretation time for delineation. In this article, we propose transverse dyadic wavelet transform (TDyWT) to delineate vegetation and water area from Landsat 8 images. The TDyWT method enhances the boundary and curvature area of satellite image for accurate delineation. From the experimental results, the proposed TDyWT approach delineates the area of subclass for vegetation and water areas with 95% of accuracy with respect to the ground truth.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Mixed pixel removal in north Tamil Nadu region for accurate area measurement

Mani¹,

Nagalingam²,

Aruldoss³

et al. 2021

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…A number of these applications use cameras and recording devices that produce low‐resolution (LR) images and low‐quality footage due to the devices being low‐cost and using cheap equipment. Super‐resolution imaging techniques have been employed in a large number of possible use cases, including satellite (Kuter et al, 2014a; Kuter et al, 2014b; Tekeli et al, 2005; Xu et al, 2023; Xu Pan, et al, 2022) and aerial imagery (Arun et al, 2020; Chakravarthy et al, 2022; Guo ret al, 2022; Jain et al, 2021; Lin et al, 2022; Raman, Soni, et al, 2022; Wang et al, 2022), intelligence monitoring, medical image processing, and fingerprint enhancement. The pixel density inside an image is significant in high resolution.…”

Section: Introductionmentioning

confidence: 99%

A novel generative adversarial network‐based super‐resolution approach for face recognition

Chougule,

Kolte,

Chamola

et al. 2024

Expert Systems

View full text Add to dashboard Cite

Face recognition is an essential feature required for a range of computer vision applications such as security, attendance systems, emotion detection, airport check‐in, and many others. The super‐resolution of subject images is an important and challenging element in numerous scenarios. At times the images are low resolution and need to be processed through super‐resolution techniques to gain more accurate results. For the problem of image super‐resolution, deep learning‐based face recognition systems have been explored in recent years; however, low‐resolution face recognition remains an arduous task. Generative adversarial network (GAN) based models are a promising approach to address this challenge. However, conventional GAN‐based models may generate images that differ significantly from an original high‐resolution image in the test set to the point that the identity of the target face may be changed. To address this shortcoming, we propose a novel U‐Net style generator architecture, where skip‐connections between the encoder and decoder layer can help in preserving the facial characteristics of the input image in the generated image, thus curbing the generator's ability to generate an entirely new image and training it to generate an image more similar in characteristics to the original image. In addition to statistical metrics like structural similarity index measure and Fréchet inception distance, we compute the pixel‐wise distance between the original and model‐generated images to ascertain that our model generates as close to the original images as possible. While we train the model for 4× super‐resolution (64 × 64 images to 256 × 256), our architecture can also be trained for an arbitrary resizing scale. Finally, the number of faces detected over high‐resolution images generated by our model is shown to be higher than state‐of‐the‐art high‐resolution image creation models for face recognition tasks.

show abstract