Semester of Graduation
Fall 2020
Degree
Master of Civil Engineering (MCE)
Department
Department of Civil & Environmental Engineering
Document Type
Thesis
Abstract
One of the fundamental sources of data for traffic analysis is vehicle counts, which can be conducted either by the traditional manual method or by automated means. Different agencies have guidelines for manual counting, but they are typically prepared for particular conditions. In the case of automated counting, different methods have been applied, but You Only Look Once (YOLO), a recently developed object detection model, presents new potential in automated vehicle counting. The first objective of this study was to formulate general guidelines for manual counting based on experience gained in the field. Another goal of this study was to develop a computer program for vehicle counting from pre-recorded video applying the YOLO model. The documented general guidelines provided in this project can be useful in acquiring the required standard and minimizing the cost of a manual counting project. The accuracy of the automated counting program was found to be about 90 percent for total daily counts, although most of that error was a consistent undercounting by automated counting.
Recommended Citation
Majumder, Mishuk, "An Approach to Counting Vehicles from Pre-Recorded Video Using Computer Algorithms" (2020). LSU Master's Theses. 5231.
https://repository.lsu.edu/gradschool_theses/5231
Committee Chair
Dr. Chester G Wilmot
DOI
10.31390/gradschool_theses.5231
Included in
Civil Engineering Commons, Other Civil and Environmental Engineering Commons, Other Computer Engineering Commons, Transportation Engineering Commons