The thesis details the development of computer vision and path planning algorithms in order to map an area via UAV aerial imagery and aid a UGV in navigating a roadway when the road conditions are not previously known (i.e. disaster situations). Feature detection was used for transform calculation and image warping to create mosaics. A continuous extension using dynamic cropping based on newly gathered images was used to improve performance and computation time. Road detection using k-means segmentation and binary image morphing was applied to aerial imagery with image shifting tracked by the mosaicking to develop a large road map. Improvements to computation time were developed using k-means for calibration at intervals and nearest neighbor calculating for each image. This showed a greatly reduced computation time for a series of images with only 1-2% error compared to regular k-means segmentation. Path planning for the UAV utilized a traveling wave applied to the traveling salesman genetic algorithm solution to prioritize close targets and facilitate UGV deployment. Based on the large map of road locations and road detection method, the Rapidly-exploring Random Tree (RRT) algorithm was modified for real-time application and efficient data processing. Considerations of incomplete maps and goal adjustments was also incorporated. Finally, aerial imagery from an actual UAV flight was processed using these algorithms to validate and test flight parameters. Testing of different flight parameters showed the desired image overlay of 50% to give accurate mosaics. It also helped to develop a benchmark for the altitude, image resolution and frequency for flights. Vehicle requirements and algorithm limitations for future applications of this system are also discussed. / Master of Science

Algorithms for automatic image registration and mosaicking are developed for a miniature Unmanned Aerial Vehicle (MINI-UAV) platform, assembled by Air-O-Space International (AOSI) L.L.C.. Three cameras onboard this MINI-UAV platform acquire images in a single frame simultaneously at green (550nm), red (650 nm), and near infrared (820nm) wavelengths, but with shifting and rotational misalignment. The area-based method is employed in the developed algorithms for control point detection, which is applicable when no prominent feature details are present in image scenes. Because the three images to be registered have different spectral characteristics, region of interest determination and control point selection are the two key steps that ensure the quality of control points. Affine transformation is adopted for spatial transformation, followed by bilinear interpolation for image resampling. Mosaicking is conducted between adjacent frames after three-band co-registration. Pre-introducing the rotation makes the area-based method feasible when the rotational misalignment cannot be ignored. The algorithms are tested on three image sets collected at Stennis Space Center, Greenwood, and Oswalt in Mississippi. Manual evaluation confirms the effectiveness of the developed algorithms. The codes are converted into a software package, which is executable under the Microsoft Windows environment of personal computer platforms without the requirement of MATLAB or other special software support for commercial-off-the-shelf (COTS) product. The near real-time decision-making support is achievable with final data after its installation into the ground control station. The final products are color-infrared (CIR) composite and normalized difference vegetation index (NDVI) images, which are used in agriculture, forestry, and environmental monitoring.