IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Pemodelan Deteksi Kendaraan Untuk Identifikasi Kemacetan Lalu Lintas Menggunakan YOLOv8 Pada Data CCTV Kota Bogor

      Thumbnail
      View/Open
      Cover (425.9Kb)
      Fulltext (1.800Mb)
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      FB, MUH FARID
      Haryanto, Toto
      Ramdhani, Tosan Wiar
      Metadata
      Show full item record
      Abstract
      Kemacetan lalu lintas merupakan salah satu permasalahan utama di Kota Bogor yang memerlukan pemantauan secara real-time. Penelitian ini membangun model deteksi kendaraan berbasis YOLOv8s menggunakan 4.605 citra CCTV publik Kota Bogor dan dataset Roboflow. Tahapan penelitian meliputi anotasi empat kelas kendaraan (motor, mobil, truk, dan bus), pembagian dataset, pelatihan model baseline, hyperparameter tuning, dan implementasi Identifikasi kemacetan. Model baseline menghasilkan precision sebesar 0,900, recall sebesar 0,872, dan mAP50-95 sebesar 0,746. Konfigurasi hyperparameter terbaik diperoleh pada learning rate 0,01 dan weight decay 0,001 dengan peningkatan precision menjadi 0,903, recall menjadi 0,879, dan mAP50-95 menjadi 0,749. Meskipun peningkatan yang diperoleh relatif kecil, proses tuning mampu meningkatkan stabilitas dan kemampuan generalisasi model dalam mendeteksi kendaraan. Implementasi menggunakan Region of Interest (ROI), weighted score kendaraan, dan Hybrid Tracker berhasil melakukan deteksi secara real-time dan mengklasifikasikan kondisi lalu lintas menjadi tiga kategori, yaitu lancar, sedang, dan macet.
       
      Traffic congestion is one of the main problems in Bogor City that requires real-time monitoring. This study develops a YOLOv8s-based vehicle detection model using 4,605 images collected from public CCTV cameras in Bogor City and a Roboflow dataset. The research stages include annotation of four vehicle classes (motorcycle, car, truck, and bus), dataset splitting, baseline model training, hyperparameter tuning, and implementation of traffic congestion estimation. The baseline model achieved a precision of 0.900, recall of 0.872, and mAP50–95 of 0.746. The best hyperparameter configuration was obtained using a learning rate of 0.01 and weight decay of 0.001, which improved the precision to 0.903, recall to 0.879, and mAP50–95 to 0.749. Although the improvement was relatively small, the tuning process enhanced model stability and generalization capability. The implementation using a Region of Interest (ROI), weighted vehicle scoring, and a Hybrid Tracker successfully classified traffic conditions in real-time into three categories: smooth, medium, and heavy.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/177330
      Collections
      • UF - Computer Science [164]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository