University of Hawaii

Electrical Engineering

Computer Vision Applications for UAVs

Date: 2018-07-12           Add to Google Calendar
Time: 9:30am
Location: Holmes Hall 389
Speaker: Evan Law, EE MS Candidate


Computer vision is a hot topic and its rapidly growing application allows for unique ways to extract data from visual media without wasting resources or man hours. In this work, we discuss the use of computer vision to detect and classify deteriorating infrastructure and biological specimens using visual media from Unmanned Ariel Vehicles (UAVs). Existing solutions require manual inspection or outdated computationally exhaustive methods, this can be simplified and optimized. Various solutions were explored such as Haar Cascades, neural networks and multiple models used for identifying and comparing images. Current solutions are analyzed to select the best application to detect and classify objects of interest from visual media.