Open AccessRESEARCH ON TRAFFIC CONGESTION DETECTION FROM CAMERA IMAGES IN A LOCATION OF DA LAT
Author(s) -
Nguyễn Thị Lưỡng
Publication year - 2021
Publication title -
tạp chí khoa học đại học đà lạt: kinh tế và quản lý/tạp chí khoa học đại học đà lạt: xã hội và nhân văn/khoa học đại học đà lạt (điện tử)/tạp chí khoa học đại học đà lạt: tự nhiên và công nghệ
Language(s) - English
Resource type - Journals
eISSN - 2615-9228
pISSN - 0866-787X
DOI - 10.37569/dalatuniversity.11.4.879(2021
Subject(s) - traffic congestion , computer science , traffic congestion reconstruction with kerner's three phase theory , support vector machine , road traffic , computer vision , artificial intelligence , real time computing , transport engineering , engineering
Many researchers are interested in traffic congestion detection and prediction. Traffic congestion occurs increasingly in many cities in Vietnam, including the city of Da Lat. This paper focuses on SVM, CNN, DenseNet, VGG, and ResNet models to detect traffic congestion from camera images collected at Nga 5 Dai Hoc, Da Lat. These images are labeled with the words traffic congestion or no traffic congestion. The experimental results have an accuracy of over 93%. The study is an initial contribution to a future system for predicting traffic congestion in Da Lat when the camera system is fully installed.