2021-2022 Senior Honors Theses
Permanent URI for this collectionhttps://hdl.handle.net/10657/10473
This collection contains theses produced by Class of 2022 Honors students
Browse
Browsing 2021-2022 Senior Honors Theses by Department "Computer Science, Department of"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item DUE-STR: A Heuristic Extension Of The Selfless Traffic Routing Model Utilizing Dynamic User Equilibrium(2022-05-05) Carroll, ThomasRouting vehicles through a traffic network such as a modern-day city has been a much- studied topic, with routing algorithms such as Dynamic User Equilibrium (DUE) having been well documented. The focus of many such works has been on the optimization of average travel time through traffic networks aiming for the more efficient routing of vehicles. In this thesis, we outline our plans for routing to satisfy arrival deadlines, where vehicles are routed with the primary objective of getting somewhere on time. We consider vehicle routing through a smaller section of a city, known as a traffic sub-network, using a centralized scheme as a guiding traffic assignment agent. We introduce our preliminary implementation of a routing algorithm built on the Selfless Traffic Routing (STR) model and Dynamic User Equilibrium (DUE) to show the viability of such a scheme on a traffic network. We present our experimental results from running this scheme on a real-world traffic network. We consider a pre-vehicle movement rerouting scheme capable of being competitive against more informative real-time models. We evaluate DUE-STR and these models using the number of arrival-deadline misses and the average travel time performance metrics for vehicles. We find mixed results between DUE-STR and other models, with our DUE- STR model mostly having better results when considering deadline misses and mostly having worse results when considering average vehicle travel time. We explore reasons why the results may not be quite as good as well as potential solutions to solve these issues.Item Review of Methods and Algorithms for Searching an Object in Images and on a Video data Stream in Various Situations(2022-04-21) Litvinov, EvgeniiIn this research work, general solutions for detecting objects in images and video streams in various situations using different methods will be considered. The intelligence of video surveillance systems will focus on moving objects, as well as on finding a specific object with given attributes for searching. At the end of the work, several technological experiments will be made, with the help of the system which is able to find a moving object in the frame and capture it, as well as send email notifications with a photo of this object. This technology should either maximally compress video quality with a still background image, or not record at all. This should thus speed up the database matching process and reduce the need for large amounts of memory.