Pedestrian Tracking and Vehicle Speed Estimation Using Deep Learning

Date
2020
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
Effective pedestrian detection and vehicle detection have become progressively significant tasks in modern life. In this project, we propose a system to detect pedestrians by counting and to detect vehicles with speed estimation using deep learning and OpenCV. We used the MobileNet V2 SSD (Single Shot Multibox Detector) Caffe model, which was pre-trained on the Coco dataset. Our system detects pedestrians and vehicles using the deep learning Caffe model from video sources and tracks them. Using OpenCV, the system counts the number of people who are heading “Up” and “Down” on the roads and calculates speed estimation to detect the KPH (Kilometers Per Hour) of the moving vehicle. The VASCAR method is the base of our speed estimation. This system also has an implementation of Dropbox API for storing the summarized results.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN