Date of Graduation


Document Type


Degree Name

Bachelor of Science

Degree Level



Computer Science and Computer Engineering


Li, Qinghua

Committee Member/Reader

Patitz, Matthew

Committee Member/Second Reader

Luu, Khoa


One of the up and coming topics in the world of technology is that of autonomous vehicles and self-driving cars. Autonomous vehicle technology has the potential to make a dynamic impact on society, drastically altering global transportation and the automotive industry. When human beings are no longer responsible for making the decisions required of controlling a vehicle, the importance of security and accuracy will become absolutely vital for these autonomous systems. If the system can be hacked and fed false information, there is the possibility of putting innocent lives at risk. In a world of growing global terrorism, this is a key and reasonable concern that must be addressed if autonomous cars are truly the future of global transportation.

The goal of this project is to create a system that will take the output of a self-driving car’s camera and use it to detect if a stoplight is present in an image and collect information about the current state of the stoplight and how it changes over time. This collected data is paired with a supervised learning algorithm, such as the K Nearest Neighbor algorithm, which gives the system the ability to classify what type of color change is occurring in a stoplight. In addition to collecting raw data from several stoplights, the system was tested by creating and assessing several different types of forgery attack to see if they cause the identification algorithm to suffer a drop in accuracy. Ultimately, the purpose of this research is to create a more intelligent system in autonomous vehicles that will be able to detect forgery attacks on its camera system. This intelligent system would work to prevent situations where attacks on the system could result in collisions between vehicles and nearby pedestrians.


Image Processing, Stop Lights, Images, Cameras, Autonomous Vehicles, Machine Learning