Regulatory Mechanisms in Biosystems (E-Journal - Dnipro National University)
Not a member yet
2311 research outputs found
Sort by
Deep learning-based single image super-resolution: an Investigation for dense scene reconstruction with UAS photogrammetry
No full textThe deep convolutional neural network (DCNN) has recently been applied to the highly challenging and ill-posed problem of single image super-resolution (SISR), which aims to predict high-resolution (HR) images from their corresponding low-resolution (LR) images. In many remote sensing (RS) applications, spatial resolution of the aerial or satellite imagery has a great impact on the accuracy and reliability of information extracted from the images. In this study, the potential of a DCNN-based SISR model, called enhanced super-resolution generative adversarial network (ESRGAN), to predict the spatial information degraded or lost in a hyper-spatial resolution unmanned aircraft system (UAS) RGB image set is investigated. ESRGAN model is trained over a limited number of original HR (50 out of 450 total images) and virtually-generated LR UAS images by downsampling the original HR images using a bicubic kernel with a factor ×4 . Quantitative and qualitative assessments of super-resolved images using standard image quality measures (IQMs) confirm that the DCNN-based SISR approach can be successfully applied on LR UAS imagery for spatial resolution enhancement. The performance of DCNN-based SISR approach for the UAS image set closely approximates performances reported on standard SISR image sets with mean peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) index values of around 28 dB and 0.85 dB, respectively. Furthermore, by exploiting the rigorous Structure-from-Motion (SfM) photogrammetry procedure, an accurate task-based IQM for evaluating the quality of the super-resolved images is carried out. Results verify that the interior and exterior imaging geometry, which are extremely important for extracting highly accurate spatial information from UAS imagery in photogrammetric applications, can be accurately retrieved from a super-resolved image set. The number of corresponding keypoints and dense points generated from the SfM photogrammetry process are about 6 and 17 times more than those extracted from the corresponding LR image set, respectively.The deep convolutional neural network (DCNN) has recently been applied to the highly challenging and ill-posed problem of single image super-resolution (SISR), which aims to predict high-resolution (HR) images from their corresponding low-resolution (LR) images. In many remote sensing (RS) applications, spatial resolution of the aerial or satellite imagery has a great impact on the accuracy and reliability of information extracted from the images. In this study, the potential of a DCNN-based SISR model, called enhanced super-resolution generative adversarial network (ESRGAN), to predict the spatial information degraded or lost in a hyper-spatial resolution unmanned aircraft system (UAS) RGB image set is investigated. ESRGAN model is trained over a limited number of original HR (50 out of 450 total images) and virtually-generated LR UAS images by downsampling the original HR images using a bicubic kernel with a factor ×4 . Quantitative and qualitative assessments of super-resolved images using standard image quality measures (IQMs) confirm that the DCNN-based SISR approach can be successfully applied on LR UAS imagery for spatial resolution enhancement. The performance of DCNN-based SISR approach for the UAS image set closely approximates performances reported on standard SISR image sets with mean peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) index values of around 28 dB and 0.85 dB, respectively. Furthermore, by exploiting the rigorous Structure-from-Motion (SfM) photogrammetry procedure, an accurate task-based IQM for evaluating the quality of the super-resolved images is carried out. Results verify that the interior and exterior imaging geometry, which are extremely important for extracting highly accurate spatial information from UAS imagery in photogrammetric applications, can be accurately retrieved from a super-resolved image set. The number of corresponding keypoints and dense points generated from the SfM photogrammetry process are about 6 and 17 times more than those extracted from the corresponding LR image set, respectively
Wanda Fusillo Garcia poses for a photograph in front of an open window
No full textWanda Fusillo Garcia poses for a photograph in front of an open windo
Jim Akers and Cecilia Akers-Garcia standing next to a decorated Christmas Tree
No full textJim Akers and Cecilia Akers-Garcia standing next to a decorated Christmas Tre
A barefoot man reading a book in the garden of Wanda Fusillo Garcia.
No full textA barefoot man reading a book in the garden of Wanda Fusillo Garcia
Angled View of Roberto brush-on silicone
No full textArtist, Roberto, surveying the brush-on silicone to the Dr. Hector P. Garcia statu
Wooden and metal chairs resting on a patio in a garden
No full textWooden and metal chairs resting on a patio in a garde
Removing mold from clay statue head of Dr. Hector P. Garcia
No full textArtist removing mother mold from original clay statue
A photograph of monkeys in their enclosure at a zoo.
No full textA photograph of monkeys in their enclosure at a zoo
Freddie Martinez and advertising his ideal Recording Orchestra.
No full textA green poster showing a photograph of Freddie Martinez and advertising his ideal Recording Orchestra
Dr. Hector P. Garcia holds out a hand for his wife, Wanda Fusillo Garcia, to hold as they stand in their garden
No full textDr. Hector P. Garcia holds out a hand for his wife, Wanda Fusillo Garcia, to hold as they stand in their garde