Theses and Dissertations at Montana State University (MSU)
Permanent URI for this communityhttps://scholarworks.montana.edu/handle/1/732
Browse
2 results
Search Results
Item Machine learning pipeline for rare-event detection in synthetic-aperture radar and LIDAR data(Montana State University - Bozeman, College of Engineering, 2021) Scofield, Trey Palmer; Chairperson, Graduate Committee: Brad WhitakerIn this work, we develop a machine learning pipeline to autonomously classify synthetic aperture radar (SAR) and lidar data in rare-event, remote sensing applications. Here, we are predicting the presence of volcanoes on the surface of Venus, fish in Yellowstone Lake, and select marine-life in the Gulf of Mexico. Given the efficiency of collecting SAR images in space and airborne lidar geographical surveys, the size of the datasets are immense. Immense training data is desirable for machine learning models; however, a large majority of the data we are using do not contain volcanoes or fish, respectively. Thus, the machine learning models must be formulated in such a way to place a high emphasis on the minority, target classes. The developed pipeline includes data preprocessing, unsupervised clustering, feature extraction, and classification. For each collection of data, sub-images are initially fed through the pipeline to capture fine detail characteristics until they are mapped back to their original image to identify overall region behavior and the location of the target class(es). For both sub-images and original images, results were quantified and the most effective algorithm combinations and parameters were assigned. In this analysis, we determined the classification results are not sufficient enough to propel a completely autonomous system, rather, some manual observing of the data will need to be performed. Nonetheless, the pipeline serves as an effective tool to reduce costs associated with electronic storage and transmission of the data, as well as human labor in manually inspecting the data. It does this by removing a majority of the unimportant, non-target data in some cases while successfully retaining a high percentage of the important images.Item Phase gradient averaging for holographic aperture LIDAR in the presence of turbulence(Montana State University - Bozeman, College of Engineering, 2017) Blaszczyk, Christopher Ross; Chairperson, Graduate Committee: Joseph A. ShawThe resolution of an image is dictated by the size and quality of the imaging system. The imaging system has a physical limit to the resolution dictated by the diffraction limited resolution. This limit can be improved by making the aperture larger on the imaging system. The increase in the physical aperture size can only be practical to a certain extent. However, to get beyond these physical constraints it is possible to use synthetic aperture methods to allow for the aperture to appear to be increased. Synthetic apertures are created by adding apertures coherently together to create a larger aperture that increases the diffraction limited resolution. To sum the aperture coherently the phase information needs to be available. One way to have access to the phase information is to capture the image as hologram. These holograms are captured by using a coherent light source with a reference beam to create an interference pattern that contains the phase information of the target. Holographic apertures can be used in a synthetic aperture method called Holographic Aperture Lidar (HAL). A problem that can arise while capturing images is turbulence in the atmosphere. Turbulence is a change in the index of refraction caused by a change in the temperature and pressure of the atmosphere. This causes the phase of the light to distort dynamically as it propagates making HAL imaging difficult. This thesis will cover a method to restore the original phase of the signal that has passed through turbulence so that it can be used in digital holography and HAL. This method uses averaging of the phase gradient to remove the dynamic turbulence and keep the phase information of the static target. The improvements observed in actual experiments were small, but the basics of the method worked, and the reason for only small improvement are discussed.