Deteksi Penggunaan Helm Pada Pengendara Bermotor Berbasis Deep Learning

Hanafi, Yusuf Umar (2020) Deteksi Penggunaan Helm Pada Pengendara Bermotor Berbasis Deep Learning. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
07211640000006-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only

Download (19MB) | Request a copy

Abstract

Bedasarkan data dari Badan Pusat Statistik (BPS), jumlah korban meninggal dalam kejadian kecelakaan di Indonesia sebanyak 30.568 jiwa pada tahun 2017. Pertumbuhan jumlah korban jiwa setiap tahun terus bertambah dengan persentase 3,72% [1]. Tingginya jumlah korban meninggal dunia diikuti dengan tingginya jenis pelanggaran yang sering dilanggar salah satunya tidak menggunakan helm [2]. Maka dari itu, deteksi penggunaan helm pada pengendara bermotor penting untuk mengurangi jumlah pelanggaran tidak menggunakan helm guna mengantisipasi adanya korban jiwa saat kecelakaan lalu lintas. Sistem ini memanfaatkan kamera IP sebagai alat deteksi. Hasil tangkapan kamera digunakan untuk mendeteksi penggunaan helm menggunakan Deep Learning, yang kemudian mendeteksi pengendara bermotor yang tidak menggunakan helm. Dengan adanya sistem pendeteksi penggunaan helm pada pengendara bermotor, diharapkan dapat mendeteksi adanya pelanggaran tidak menggunakan helm yang nantinya akan dikembangkan lebih lanjut menjadi sistem e-Tilang. ============================================= Based on data from the Central Statistics Agency (BPS), the death rate in accidents in Indonesia was 30,568 in 2017. Growth in the number of deaths every year continues to increase with a percentage of 3.72% [1]. The high number of deaths was followed by high types of violations that were often violated, one of which was not wearing a helmet [2]. Therefore, detection of helmet use in motorized motorists is important to reduce the number of violations that do not use helmets to anticipate deaths during traffic accidents. This system uses IP cameras to capture. Camera footage is used to detect helmet use using Deep Learning, which then detects motorized motorists who don’t use helmets. With the presence of a helmet detection system for motorists, it is expected to detect violations that do not use helmets which will later be further developed into e-tilang systems.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: You Only Look Once (YOLO), Lalu Lintas, IP Camera, Traffic, IP Camera
Subjects: Q Science > QA Mathematics > QA336 Artificial Intelligence
T Technology > TE Highway engineering. Roads and pavements > TE228.3 Intelligent transportation systems.
T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL725.3 Traffic Control
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User: Yusuf Umar Hanafi
Date Deposited: 22 Aug 2020 04:21
Last Modified: 22 Aug 2020 04:21
URI: https://repository.its.ac.id/id/eprint/79184

Actions (login required)

View Item View Item