Optical flow analysis for feature tracking from vehicle camera

• Main Author: Liew, Hanwei
• Other Authors: Tay Wee Peng
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/157531
• Institution: Nanyang Technological University

In the subject of computer vision, motion tracking is one of the most active study topics. Motion tracking may be both informative and beneficial, and motion data is quite important for traffic surveillance systems. Template matching, blob tracking, and contour tracking are among the many proposed motion tracking techniques. There are two main factors that come with developing optical flow algorithms over the years. One would be higher accuracy and the other would be faster implementation. This research project will analyze the notion of applying optical flow in videos taken from a vehicle-mounted camera and evaluate its performance in order to assess its dependability and practicability.