Date Approved

8-27-2020

Embargo Period

8-28-2020

Document Type

Thesis

Degree Name

M.S. Electrical and Computer Engineering

Department

Electrical and Computer Engineering

College

Henry M. Rowan College of Engineering

First Advisor

Ramachandran, Ravi P.

Second Advisor

Bouaynaya, Nidhal C.

Third Advisor

Rasool, Ghulam

Subject(s)

Helicopters--Accidents; Computer vision

Disciplines

Aviation | Electrical and Computer Engineering

Abstract

The recent impact of deep learning algorithms and their major breakthroughs on various aspects of our lives has led to the idea to investigate the application of these algorithms in different problem spaces. One of the novel areas of investigation is the aviation and air traffic control domain; as it offers a prime opportunity to enhance safety within the aviation community. Of particular importance to this community is improving the safety of rotorcraft operations, as this segment of the aviation industry is subject to a higher fatal accident rate than other segments of the industry. The improvement of safety for rotorcraft also directly improves the safety and efficiency of air traffic control, since rotorcraft operate primarily within low-level airspace; an area that is becoming increasingly complex with new entrants such as unmanned aircraft systems, urban air mobility, etc.

The novel method for improving rotorcraft safety, and the main topic of this research, is to create an algorithm that determines the head position of helicopter pilots and copilots through automatic post-processing of onboard flight video data. This information can then be used to aid in incident/crash analysis as well as future vision systems research. Both a classical computer vision technique and a deep learning approach were taken to provide possible solutions to this problem. Both solutions successfully deal with the issues of excessive cockpit background, extreme head positions, and added noise from the pilot's operational equipment which include helmets, microphones, and sunglasses.

Share

COinS