Traffic light status classification and vehicle tracking at intersections | |
| Author | Htet Naing Aung |
| Call Number | AIT Caps Proj no.ICT-15-03 |
| Subject(s) | Traffic signs and signals Vehicle tracking system |
| Note | A capstone project submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Engineering Information and Communication Technology, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Caps. Proj. ; no. ICT-15-03 |
| Abstract | This project investigates the use of support vector machines (SVMs) with image hue infor- mation to classify traffic lights as red, yellow, or green. It also evaluates the application of the Lucas-Kanade and Farneback optical flow methods with DBSCAN for tracking vehicles at urban intersections. The traffic light classification results for a limited test provide excellent accuracy at 100%. The Farneback optical flow method with DBSCAN clustering produces acceptable vehicle tracking accuracy but lacks real time performance. The accuracy of Lucas-Kanade optical flow with DBSCAN is not as good as the Farneback method with DBSCAN, but it provides better speed. |
| Year | 2015 |
| Corresponding Series Added Entry | Asian Institute of Technology. Caps. Proj. ; no. ICT-15-03 |
| Type | Capstone Project |
| School | School of Engineering and Technology (SET) |
| Department | Bachelor Degree |
| Academic Program/FoS | Information and Communication Technology (ICT) |
| Chairperson(s) | Dailey, Matthew; |
| Examination Committee(s) | Monhkol Ekpanyapong; |
| Degree | Capstone Project (M.Eng.) - Asian Institute of Technology, 2015 |