Perhitungan Kecepatan Kendaraan Menggunakan Drone Bergerak dengan Metode Deep Learning

Fatchurozi, Moh. Iqbal (2024) Perhitungan Kecepatan Kendaraan Menggunakan Drone Bergerak dengan Metode Deep Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5024201009-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (9MB) | Request a copy

Abstract

Perhitungan kecepatan kendaraan di jalan raya adalah salah satu komponen kritikal dalam pengawasan lalu lintas dan keamanan jalan. Teknologi drone, yang semakin banyak digunakan dalam berbagai aplikasi, menawarkan platform yang unik untuk pemantauan dari udara. Penelitian ini memperkenalkan metode baru untuk menghitung kecepatan kendaraan dengan menggunakan drone bergerak melalui pendekatan deep learning. Dalam metode ini, sebuah model deep learning dilatih untuk mendeteksi dan mengestimasi kecepatan kendaraan berdasarkan rekaman video dari drone. Model ini dioptimalkan untuk menghadapi berbagai tantangan, seperti perubahan kondisi pencahayaan, jenis kendaraan yang beragam, dan gerakan drone itu sendiri. Hasil awal menunjukkan bahwa metode ini dapat menghasilkan estimasi kecepatan dengan tingkat akurasi yang tinggi dalam berbagai kondisi operasional. Implementasi ini tidak hanya meningkatkan efisiensi pengawasan lalu lintas tetapi juga menawarkan solusi untuk penelitian lalu lintas dan aplikasi keamanan lainnya.
=====================================================================================================================================
The calculation of vehicle speed on highways is a critical component in traffic surveillance and road safety. Drone technology, increasingly used across various applications, offers a unique platform for aerial monitoring. This research introduces a novel method to compute vehicle speed using a moving drone through a deep learning approach. In this method, a deep learning model is trained to detect and estimate vehicle speed based on video footage from the drone. The model is optimized to tackle various challenges, such as changing lighting conditions, diverse vehicle types, and the drone's own movement. Preliminary results indicate that this method can produce speed estimations with a high degree of accuracy under various operational conditions. This implementation not only enhances traffic surveillance efficiency but also presents solutions for traffic research and other security applications.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Deep Learning, Drone, Kecepatan Kendaraan, Pendeteksian Objek, Pemantauan Lalu Lintas, Deep Learning, Drone, Vehicle Speed, Object Detection, Traffic Monitoring
Subjects:	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 T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5105.888 Web sites--Design. Web site development.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User:	Moh. Iqbal Fatchurozi
Date Deposited:	19 Jul 2024 14:04
Last Modified:	19 Jul 2024 14:04
URI:	http://repository.its.ac.id/id/eprint/108537

Actions (login required)

View Item