Honors Theses
Date of Award
Spring 5-9-2020
Document Type
Undergraduate Thesis
Department
Computer and Information Science
First Advisor
Yixin Chen
Second Advisor
Byunghyun Jang
Third Advisor
Charles Fleming
Relational Format
Dissertation/Thesis
Abstract
A traffic surveillance camera system is an important part of an intelligent transportation system.(Zhang et al., 2013) This system is capable of performing useful object detections on the incoming feed. These detected objects can then be used for tracking purposes which forms the basis for monitoring important traffic data such as collisions, vehicle count, pedestrian count and so on. Furthermore, other additional information such as the weather conditions, time of day as well as date can also be extracted from a live feed. (Sun et al., 2004) Different algorithms can yield different results for any given video input. Not only that, various parameters such as the resolution, frames per second(fps) count, lighting conditions in the video input also affect performance. Therefore, it is imperative to compare between the various image processing and deep learning algorithms and evaluate their performance before deploying them in real time.
Recommended Citation
Tamrakar, Yunik, "Empirical Evaluation of Vehicle Detection, Tracking And Recognition Algorithms Operating On Real Time Video Feeds" (2020). Honors Theses. 1507.
https://egrove.olemiss.edu/hon_thesis/1507
Accessibility Status
Searchable text
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.