Shamrao, Ramasamy (2022) Study of vision based traffic congestion classification monitoring system (vbtccms). College of Engineering, Universiti Malaysia Pahang.
|
Pdf
EA18033_SHAMRAO_THESIS_V2 - Sham Rao.pdf - Accepted Version Download (1MB) | Preview |
Abstract
Image classification is the task of recognising an item or subject according to the class to which it has been allocated in the computer world. Similarly, this thesis discusses the work that was done and how traffic congestion was classified using roadside CCTV video. The goal is to use an architecture to investigate and classify traffic congestion variables into three categories: low congestion, medium congestion, and excessive congestion. The design entails a study of architecture as well as an application for detecting each class. The study of congestion factor utilising YOLO and Deep Sort, which was constructed using TensorFlow and Keras platform, will be covered in this thesis. The major purpose of this project is to develop a system for classifying traffic congestion on a busy route, with the system being able to classify traffic congestion into three categories: low, medium, and high. The entire categorization process is carried out by the system using vision. TensorFlow is an open source programming framework that provides a variety of architectures as well as an easy-to-use interface for future applications.
| Item Type: | Undergraduates Project Papers |
|---|---|
| Additional Information: | SV: Dr. Ahmad Afif bin Mohd Faudzi |
| Uncontrolled Keywords: | vision based traffic congestion classification monitoring system (vbtccms) |
| Subjects: | T Technology > TA Engineering (General). Civil engineering (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Faculty/Division: | College of Engineering |
| Depositing User: | Mr. Nik Ahmad Nasyrun Nik Abd Malik |
| Date Deposited: | 24 Oct 2023 08:07 |
| Last Modified: | 24 Oct 2023 08:07 |
| URI: | http://umpir.ump.edu.my/id/eprint/39005 |
| Download Statistic: | View Download Statistics |
Actions (login required)
 |
View Item |