Images

Land cover classification is necessary for understanding the state of the surface of the Earth at varying regions of interest. Knowledge of the Earth’s surface is critical in land-use planning, especially for the project study area Jupiter Inlet Lighthouse Outstanding Natural Area, where various vegetation, wild-life, and cultural components rely on adequate land-cover knowledge. The purpose of this research is to demonstrate the capability of UAV true color imagery for land cover classification.
In addition to the objective of land cover classification, comparison of varying spatial resolutions of the imagery will be analyzed in the accuracy assessment of the output thematic maps. These resolutions will also be compared at varying training sample sizes to see which configuration performed best.

This Thesis surveys the landscape of Data Augmentation for image datasets. Completing this survey inspired further study into a method of generative modeling known as Generative Adversarial Networks (GANs). A survey on GANs was conducted to understood recent developments and the problems related to training them. Following this survey, four experiments were proposed to test the application of GANs for data augmentation and to contribute to the quality improvement in GAN-generated data. Experimental results demonstrate the effectiveness of GAN-generated data as a pre-training metric. The other experiments discuss important characteristics of GAN models such as the refining of prior information, transferring generative models from large datasets to small data, and automating the design of Deep Neural Networks within the context of the GAN framework. This Thesis will provide readers with a complete introduction to Data Augmentation and Generative Adversarial Networks, as well as insights into the future of these techniques.