Alia, Putri Ariatna (2019) Perkiraan Kepadatan Kendaraan berdasarkan Pengolahan Video Menggunakan Metode Gaussian Mixture Model. Masters thesis, Institut Teknologi Sepuluh Nopember.
Text
thesis putri 17012019 BARU.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (2MB) | Request a copy |
Abstract
Kemacetan merupakan masalah yang sering terjadi di kota besar tidak terkecuali di Surabaya. Hal tersebut di karenakan semakin bertambahnya jumlah volume kendaraan tiap tahunnya dan tidak seimbangnya jumlah kendaraan dengan kapasitas jalan yang di lewati. Cara mengatasinya adalah dengan melakukan pengamatan parameter tersebut. Dahulu pengamatan dilakukan dengan perhitungan yang dilakukan oleh manusia, akan tetapi hal tersebut tidak efektif karena membutuhkan biaya yang sangat besar, sehingga dalam penelitian ini dilakukan pengamatan menggunakan pengolahan system dengan metode Gaussian mixture model.
Studi dilakukan dengan mengambil data dengan meletakkan kamera di tengah – tengah jembatan penyebrangan orang. Studi ini bertujuan untuk mengetahui nilai kepadatan dengan membandingkan volume lalu lintas dengan kecepatan kendaraan. Nilai kecepatan dan jumlah kendaraan dapat diketahui menggunakan metode Gaussian Mixture Model, dimana deteksi objek dilakukan dalam proses background substraction yaitu video dibagi beberapa frame dan pada tiap frame citra dibagi menjadi dua bagian foreground dan background. Objek akan bernilai 1 ketika analisis blob dan tracking mendeteksi foreground. Berdasarkan hasil pengujian data yang diambil adalah 10 rekaman video dalam waktu yang berdekatan dan tempat yang sama, sehingga di dapat persamaan regresi linier dari nilai kecepatan kendaraan dan kepadatan kendaraan yaitu y = 1,0316x+42,314, dengan persamaan greenshields sehingga dapat diperkirakan nilai arus jenuh ruas jalan sebesar 40,938 km/jam.
================================================================================================
Congestion is a problem that often occurs in big cities, including in Surabaya. This is because the increasing volume of vehicles each year and the imbalance in the number of vehicles with road capacity that is passed. The fix is by observing these parameters. Previously observations were carried out by calculations carried out by humans, but this was not effective because it requires a very large cost, so that in this study observations were made using system processing using the Gaussian mixture model. .
This research aims to determine the density value by comparing traffic volume with vehicle speed. The value of speed and number of vehicles can be known using Gaussian Mixture Model method, where object detection is detected by background substraction process, which is video divided into several frames and in each frame images is divided into two part there are foreground and background. Based on the results of testing the data taken are 10 video recordings in the adjacent time and the same place, so that the linear regression equation of the vehicle speed and vehicle density can be obtained, y = 1.0316x + 42,314, with the equation greenshields so that the saturated current value can be estimated road section of 40,938 km / hour.
Item Type: | Thesis (Masters) |
---|---|
Additional Information: | RTE 511.8 Ali p-1 2019 |
Uncontrolled Keywords: | Gaussian Mixture Model, vehicle speed, vehicle density, foreground |
Subjects: | Q Science > QA Mathematics > QA402.5 Genetic algorithms. Interior-point methods. T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.546 Computer algorithms |
Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis |
Depositing User: | Putri Ariatna Alia |
Date Deposited: | 22 Sep 2021 01:46 |
Last Modified: | 22 Sep 2021 01:46 |
URI: | http://repository.its.ac.id/id/eprint/60548 |
Actions (login required)
View Item |