<p dir="ltr">Imaging in low light is difficult because few photons can arrive at the sensor in a particular time interval. Increasing the exposure time is not always an option, as images will be blurry if the scenes are dynamic. If scenes or objects are moving, one can capture multiple frames with short exposure time and fuse them using carefully designed algorithms; however, aligning the pixels in adjacent frames is challenging due to the high photon shot noise and sensor read noise at low light. If the dynamic range of the scene is high, one needs to further blend multiple exposures from the frames. This blending requires removal of spatially varying noise at various lighting conditions while todays high dynamic range (HDR) fusion algorithms usually assume well illuminated scenes. Therefore, this low-light HDR imaging problem remains unsolved. </p><p dir="ltr">To address these dynamic low-light imaging problems, researches in this dissertation explore both conventional CMOS image sensors and a new type of image sensor, named quanta image sensor (QIS), develop models of the imaging conditions of interest, and propose new image reconstruction algorithms based on deep neural networks together with new training protocols to assist the learning. Researches in this dissertation target to reconstruct dynamic HDR scenes at a light level of 1 photon per pixel (ppp) or less than 1 lux illuminance.</p>

Thesis (M.S.)--University of Florida, 2004. / Title from title page of source document. Document formatted into pages; contains 74 pages. Includes vita. Includes bibliographical references.

HDR images have much wider range of luminance values, than photographs created and displayed in a standard 24-bit format. There are several ways to create images with high dynamic range, but this diploma thesis focuses just on one of them, and it is the method of composing out of series of standard photographs. The goal of the first part of the text consists of studying, understanding and eventually writing down the basic terms and knowledge in the subject of image composition and other processes, necessary to create HDR photographs. Next the procedure of creating images with high dynamic range, processing and converting them into viewable form, is described. The following chapter contains the design of the application, which creates this kind of photographs, and which is smoothly changing into its actual implementation afterwards. The process of experimenting and its results are presented and discussed firstly in their own chapter and secondly in the attachment. The conclusion contains the summary of the work and the options of possible expansion.

Use of positive distraction in the built healthcare environment to assist in alleviating stress in a patient was investigated. A backlit light image was mounted in the ceiling of an examination room to create a positive distraction for patients in the ETSU Pediatric Clinic in Johnson City, TN. Survey instruments were used to collect sample data from patients and physicians in a randomized, balanced controlled study designed to determine if patients experienced less stress in the room with the backlit image as compared to other rooms (treatments). Although a statistical difference was not determined between the room with the backlit image and positive and negative control rooms, patients in rooms containing nature art tended to exhibit less anxiety. Researched based knowledge for creating positive distractions in the built healthcare environment helps designers create environments that benefit the patients, their families and medical staff of healthcare facilities.

Computer vision is a key component of any autonomous system. Real world computer vision applications rely on a proper and accurate detection and classification of objects. A detection algorithm that doesn’t guarantee reasonable detection accuracy is not applicable in real time scenarios where safety is the main objective. Factors that impact detection accuracy are illumination conditions and image resolution. Both contribute to degradation of objects and lead to low classifications and detection accuracy. Recent development of Convolutional Neural Networks (CNNs) based algorithms offers possibilities for low-light (LL) image enhancement and super resolution (SR) image generation which makes it possible to combine such models in order to improve image quality and increase detection accuracy. This thesis evaluates different CNNs models for SR generation and LL enhancement by comparing generated images against ground truth images. To quantify the impact of the respective model on detection accuracy, a detection procedure was evaluated on generated images. Experimental results evaluated on images selected from NoghtOwls and Caltech Pedestrian datasets proved that super resolution image generation and low-light image enhancement improve detection accuracy by a substantial margin. Additionally, it has been proven that a cascade of SR generation and LL enhancement further boosts detection accuracy. However, the main drawback of such cascades is related to an increased computational time which limits possibilities for a range of real time applications. / Datorseende är en nyckelkomponent i alla autonoma system. Applikationer för datorseende i realtid är beroende av en korrekt detektering och klassificering av objekt. En detekteringsalgoritm som inte kan garantera rimlig noggrannhet är inte tillämpningsbar i realtidsscenarier, där huvudmålet är säkerhet. Faktorer som påverkar detekteringsnoggrannheten är belysningförhållanden och bildupplösning. Dessa bidrar till degradering av objekt och leder till låg klassificerings- och detekteringsnoggrannhet. Senaste utvecklingar av Convolutional Neural Networks (CNNs) -baserade algoritmer erbjuder möjligheter för förbättring av bilder med dålig belysning och bildgenerering med superupplösning vilket gör det möjligt att kombinera sådana modeller för att förbättra bildkvaliteten och öka detekteringsnoggrannheten. I denna uppsats utvärderas olika CNN-modeller för superupplösning och förbättring av bilder med dålig belysning genom att jämföra genererade bilder med det faktiska data. För att kvantifiera inverkan av respektive modell på detektionsnoggrannhet utvärderades en detekteringsprocedur på genererade bilder. Experimentella resultat utvärderades på bilder utvalda från NoghtOwls och Caltech datauppsättningar för fotgängare och visade att bildgenerering med superupplösning och bildförbättring i svagt ljus förbättrar noggrannheten med en betydande marginal. Dessutom har det bevisats att en kaskad av superupplösning-generering och förbättring av bilder med dålig belysning ytterligare ökar noggrannheten. Den största nackdelen med sådana kaskader är relaterad till en ökad beräkningstid som begränsar möjligheterna för en rad realtidsapplikationer.