A large fleet (in the hundreds) of high quality telescopes are used for tracking and imaging of launch vehicles during ascent from Cape Canaveral Air Force Station and Kennedy Space Center. A maintenance tool has been development for use with these telescopes. The tool requires rankings of telescope condition in terms of the ability to generate useful imagery. It is thus a case of ranking telescope conditions on the basis of the perceptual image quality of their imagery. Perceptual image quality metrics that are well-correlated to observer opinions of image quality have been available for several decades. However, these are quite limited in their applications, not being designed to compare various optical systems. The perceptual correlation of the metrics implies that a constant image quality curve (such as the boundary between two qualitative categories labeled as excellent and good) would have a constant value of the metric. This is not the case if the optical system parameters (such as object distance or aperture diameter) are varied. No published data on such direct variation is available and this dissertation presents an investigation made into the perceptual metric responses as system parameters are varied. This investigation leads to some non-intuitive conclusions. The perceptual metrics are reviewed as well as more common metrics and their inability to perform in the necessary manner for the research of interest. Perceptual test methods are also reviewed, as is the human visual system. iv Image formation theory is presented in a non-traditional form, yielding the surprising result that perceptual image quality is invariant under changes in focal length if the final displayed image remains constant. Experimental results are presented of changes in perceived image quality as aperture diameter is varied. Results are analyzed and shortcomings in the process and metrics are discussed. Using the test results, predictions are made about the form of the metric response to object distance variations, and subsequent testing was conducted to validate the predictions. The utility of the results, limitations of applicability, and the immediate ability to further generalize the results is presented.

In recent years, the rapid development of autonomous vehicles (AVs) has necessitated the need for high-quality perception systems. Perception is a fundamental requirement for AVs, with cameras and LiDARs being commonly used sensors for environmental understanding and localization. However, there is a research gap in assessing the quality of AVs perception systems. To address this gap, this dissertation proposes a novel paradigm for evaluating AVs perception quality by studying the perception quality of cameras and LiDARs sensors. Our proposed paradigm aims to provide a comprehensive assessment of the quality of perception systems used in AVs.To achieve our research goals, we first validate the concept of surrounding environmental complexity through subjective experiments that rate complexity scores. In this study, we propose a neural network to classify complexity. Subsequently, we study image-based perception quality assessment by using image saliency and 2D object detection algorithms to create an image-based quality index. We then develop a neural network model to regress the proposed quality index score. Furthermore, we extend our research to LiDAR-based point cloud quality assessment by using the image-based saliency map as guidance to generate a point cloud quality index score. We then develop a neural network model to regress the score. Finally, we validate the proposed perception quality index with a novel designed AVs perception algorithm. In conclusion, this dissertation makes a significant contribution to the field of AVs perception by proposing a new paradigm for assessing perception quality. Our research findings can be used to improve the overall performance and safety of AVs, which has significant implications for the transportation industry and society as a whole. / Doctor of Philosophy / This dissertation delves into the fundamentals of autonomous vehicles (AVs), which is perception, with the aim of developing a new paradigm for evaluating the quality of perception algorithms. AVs are the dream of humanity, and perception is the fundamental requirement for achieving their full potential. Our research proposes a new approach to assessing the quality of perception algorithms, which can have significant implications for the performance and safety of AVs. By studying the perception algorithm quality, we aim to identify areas for improvement, leading to better AV performance and enhancing user trust. Our findings highlight the importance of perception in the development of AVs and demonstrate the need for continuous evaluation and improvement of the perception algorithms used in AVs.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.

No description available.