Monitoring Pelanggar Social Distancing Berbasis Video Menggunakan Euclidian Distance

Reformantoko, Galang (2021) Monitoring Pelanggar Social Distancing Berbasis Video Menggunakan Euclidian Distance. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 06111740000057-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (32MB) | Request a copy

Abstract

Pengolahan citra digital dapat digunakan dalam membuat sistem yang dapat memonitor pelanggar social distancing. Pada pembuatannya, sistem harus dapat memisahkan antara objek dengan background. Dalam melakukan pemisahan tersebut, sistem menggunakan metode gaussian mixture model (GMM). Setelah objek terpisah, sistem akan memberikan bounding box. Dari bounding box tersebut, sistem akan mencari centroid dari hasil perpotongan diagonalnya. Centroid inilah yang digunakan sistem untuk mengestimasi jarak atar objek. Sebelum memberikan notifikasi, sistem memerlukan 2 parameter yaitu jarak dan waktu berkerumun. Metode euclidian distance digunakan untuk menghitung jarak antar objek. Dalam menghitung jarak, sistem menggunakan mekanisme tambahan dimana sistem hanya menghitung ulang jarak objek yang melakukan gerakan terhadap objek lain. Dari hasil uji coba, didapatkan tingkat eror sistem dalam penghitungan jarak adalah 13%.
=====================================================================================================
Image processing can be used to make a system that can monitor social distancing violators. To make a kind of system, the system itself must have the ability to seperate between object and the backgrond. In the process of doing that separation, the system is using the gaussian mixture model (GMM). After the object is separated from the background, the system will give a bounding box. From the bounding box itself, the system will look for centroid from the result of its diagonal intersection. This centroid will be used to estimate the distance between objects. Before giving any nofications, the system i needing 2 parameters which are distance and violation time. Euclidian distance method will be used to calculate the difference between objects. In calculating the distance, the system is using on more mechanism in which the system will be re-calculating the distance between objects that doing some movements of all other objects. After doing some test, the result of the system error rate for distance calulating is about 13%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Social Distance, Deep Learning, Euclidian Distance, Gaussian Mixture Model (GMM),Social Distance, Deep Learning, Euclidian Distance, Gaussian Mixture Model (GMM).
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Galang Reformantoko
Date Deposited:	30 Aug 2021 06:22
Last Modified:	30 Aug 2021 06:22
URI:	http://repository.its.ac.id/id/eprint/90613

Actions (login required)

View Item