Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/158028
Title: Automatic identification of vehicles from single view
Authors: Lim, Nicholas Shin Cheong
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Lim, N. S. C. (2022). Automatic identification of vehicles from single view. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158028
Abstract: Transportation has always been part and parcel of our daily lives. Getting from one place to another and getting there safely in one piece is two different sides of a coin. Be it public transport, private hire or your own vehicle, safety of our well-being is always paramount. With the increasing number of vehicles on the road, your safety might be dependent on the other drivers, no matter how safe you are. Thus, with the use of AI applications to perceives the vehicle’s surrounding environment, identify and keep track of multiple objects (moving or stationary), we are able to reduce the possibilities of tragedies from happening. An autonomous vehicle detection system will be developed through the process of this project, whereby it incorporates the YOLOv4 CSPDarknet 53 architecture to train on images of objects required for detection. The integration of DeepSORT tracker will assist the system in tracking the objects within the camera’s field of view, allowing the system to know the location of each unique objects detected. Implementation of counter, distance and speed estimation techniques allows the system to detect if other drivers are too near, too fast and pose a danger to the user.
URI: https://hdl.handle.net/10356/158028
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP Final Report U1921602E.pdf
  Restricted Access
7.24 MBAdobe PDFView/Open

Page view(s)

9
Updated on Jun 25, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.