Engineering Commons^™

Atmospheric Turbulence Distortion In Video: Restoration Utilizing Sparse Analysis, Benjamin J. Sanda

Dissertations

The removal of atmospheric turbulence (AT) distortion in long range imaging is one of the most challenging areas of research in imaging processing with an immediate need for solutions in several applications such as in military and transportation systems. AT exacerbates distortion due to non-linear geometric blur and scintillations in long-distance images and videos, severely reducing image quality and information interpretation. AT negatively impacts both human and computer vision systems, compromising visibility essential for accurate object identification and tracking.

In this dissertation, a novel sparse analysis framework is developed to address efficient AT blur and scintillation removal in video. Operating …

Image Processing Of Technological Objects, Lyudmila Petrovna Varlamova

Chemical Technology, Control and Management

The article considers the problem of creating a smoke detection and fire detection system for technological objects. Fire detection is carried out using a vision system. Monitoring of technological objects is carried out using an unmanned aerial vehicle. For further actions, processing and classification of images is necessary. When observing the technological apparatuses of the chemical and petrochemical industry, problems arise associated with the large size, distribution and extent of objects. There may be situations in which there are violations of the technological regulations and, as a result, the occurrence of fire, fire and smoke. Using the technology of unmanned …

Image Denoising Using Deep Convolutional Autoencoder With Feature Pyramids, Ekrem Çeti̇nkaya, Mustafa Furkan Kiraç

Turkish Journal of Electrical Engineering and Computer Sciences

Image denoising is 1 of the fundamental problems in the image processing field since it is the preliminary step for many computer vision applications. Various approaches have been used for image denoising throughout the years from spatial filtering to model-based approaches. Having outperformed all traditional methods, neural-network-based discriminative methods have gained popularity in recent years. However, most of these methods still struggle to achieve flexibility against various noise levels and types. In this paper, a deep convolutional autoencoder combined with a variant of feature pyramid network is proposed for image denoising. Simulated data generated by Blender software along with corrupted …

Anatomical Fraction Segmentation In The Biomass Bales, Rahul Reddy Kancharla, William A. Smith, Elisa H. Barney Smith, Jordan L. Klinger

Electrical and Computer Engineering Faculty Publications and Presentations

According to the Bioenergy Technologies Office (BETO), creating a robust next-generation domestic bioenergy industry is an essential pathway for providing sustainable renewable energy alternatives. Using non-food feedstocks, like corn-stover and forest residue, in the biorefineries doesn't affect the food supply chain. In the commercial-scale bioenergy operations, a significant development in the technological advancements is required to determine the biomass feedstock quality at the preprocessing stage. The penetrating ability of the x-rays helps study the big biomass bales, but the feedstock heterogeneity—physical size, shape, and chemical composition—poses a significant challenge during milling, conveyance, feeding, and biofuel conversion processes. The inherent complexity …

Video And Image Super-Resolution Via Deep Learning With Attention Mechanism, Xuan Xu

Graduate Theses, Dissertations, and Problem Reports

Image demosaicing, image super-resolution and video super-resolution are three important tasks in color imaging pipeline. Demosaicing deals with the recovery of missing color information and generation of full-resolution color images from so-called Color filter Array (CFA) such as Bayer pattern. Image super-resolution aims at increasing the spatial resolution and enhance important structures (e.g., edges and textures) in super-resolved images. Both spatial and temporal dependency are important to the task of video super-resolution, which has received increasingly more attention in recent years. Traditional solutions to these three low-level vision tasks lack generalization capability especially for real-world data. Recently, deep learning methods …