Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Optimizing YOLOv8 for Real-Time CCTV Surveillance: A Trade-off Between Speed and Accuracy

Jurnal Online Informatika · Vol. 8 No. 2 (2023) · hlm. 261–270

DOI
10.15575/join.v8i2.1196
ISSN
2527-9165, 2528-1682
Terbit
2023-12-28
Penerbit
Sunan Gunung Djati State Islamic University Bandung
Bahasa
en
Lisensi
creativecommons.org/licenses/by-nd/4.0/

Abstrak

Real-time video surveillance, especially CCTV systems, requires fast and accurate face detection. Object detection models with slow inference times are ineffective in real-time. This study addresses this challenge by improving the inference speed of the YOLOv8 model, a leading object detection framework known for its accuracy and speed. We focus on pruning the model's architecture, particularly the P5 head section, which detects larger objects. According to Bochkovskiy's 2020 research, this modification enhances the model's performance specifically for medium and small objects in CCTV footage. The standard YOLOv8 model and its modified version were compared for inference time, mean Average Precision (mAP), and model weight. The pruned YOLOv8 model cuts inference time by 15.56%, from 4.5 ms to 3.8 ms, and reduces model weight. The advantages mentioned above are offset by a 1.6% decrease in mean average precision. This research advances object detection technology by demonstrating architectural modifications' efficacy. These changes make the model faster and lighter, making it suitable for real-time surveillance. The accuracy trade-off is slight. The implications of these findings are crucial for implementing efficient object detection systems in CCTV surveillance. These findings also lay the groundwork for future research to improve such systems' speed-accuracy trade-off.

Kata kunci

Jaringan kolaborasi para penulis

35 penulis · 110 tautan kepenulisan bersama · 33 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Politeknik Negeri Bandung
  • Sunan Gunung Djati State Islamic University Bandung
  • Pukyong National University
  • Universitas Negeri Padang
  • Universitas Masoem
  • University of Birmingham
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Diena Rauda RamdaniaSunan Gunung Djati State Islamic University Bandung3
Nurjannah SyakraniPoliteknik Negeri Bandung2
Dimas KurniawanPoliteknik Negeri Bandung1
Wili Akbar NugrahaAfiliasi tidak diketahui1
Priyanto HidayatullahPoliteknik Negeri Bandung1
Lukmannul Hakim FirdausAfiliasi tidak diketahui1
Yayang Setia BudiAfiliasi tidak diketahui1
Fardan Al JihadAfiliasi tidak diketahui1
Trisna GelarAfiliasi tidak diketahui1
Djoko Cahyo Utomo LieharyaniAfiliasi tidak diketahui1
Sandi RahmadikaUniversitas Negeri Padang1
Vandha Pradwiyasma WidarthaPukyong National University1
Setiadi RachmatPoliteknik Negeri Bandung1
Nurul Dewi AuliaSunan Gunung Djati State Islamic University Bandung1
Zulfa Audina DwiSunan Gunung Djati State Islamic University Bandung1
Amelia Dewi AgustianiPoliteknik Negeri Bandung1
Salsabila Maharani PutriPoliteknik Negeri Bandung1
Jonner HutahaeanPoliteknik Negeri Bandung1
Muhammad Riza AlifiPoliteknik Negeri Bandung1
Ade HodijahPoliteknik Negeri Bandung1
Undang SyaripudinSunan Gunung Djati State Islamic University Bandung1
Indah Sri LestariSunan Gunung Djati State Islamic University Bandung1
Mimin MintarsihUniversitas Masoem1
Jumadi Jumadi JumadiSunan Gunung Djati State Islamic University Bandung1
Indri NurfianiSunan Gunung Djati State Islamic University Bandung1
Alfin Yogi SetyawanSunan Gunung Djati State Islamic University Bandung1
Gina Giftia Azmiana DelilahSunan Gunung Djati State Islamic University Bandung1
Ichsan BudimanUniversity of Birmingham1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S4210216628, pertama di-harvest 21 Nov 2026, terakhir terlihat 21 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Optimizing YOLOv8 for Real-Time CCTV Surveillance: A Trade-off Between Speed and Accuracy</dc:title><dc:creator>Muhammad Rizqi Sholahuddin</dc:creator><dc:creator>Maisevli Harika</dc:creator><dc:creator>Iwan Awaludin</dc:creator><dc:creator>Yunita Citra Dewi</dc:creator><dc:creator>Fachri Dhia Fauzan</dc:creator><dc:creator>Bima Putra Sudimulya</dc:creator><dc:creator>Vandha Pradiyasma Widarta</dc:creator><dc:subject>YOLOv8</dc:subject><dc:subject>CCTV surveillance</dc:subject><dc:subject>real-time video surveillance</dc:subject><dc:subject>face detection</dc:subject><dc:subject>object detection</dc:subject><dc:subject>model pruning</dc:subject><dc:subject>inference speed</dc:subject><dc:subject>speed-accuracy trade-off</dc:subject><dc:subject>small object detection</dc:subject><dc:description xml:lang="en">Real-time video surveillance, especially CCTV systems, requires fast and accurate face detection. Object detection models with slow inference times are ineffective in real-time. This study addresses this challenge by improving the inference speed of the YOLOv8 model, a leading object detection framework known for its accuracy and speed. We focus on pruning the model's architecture, particularly the P5 head section, which detects larger objects. According to Bochkovskiy's 2020 research, this modification enhances the model's performance specifically for medium and small objects in CCTV footage. The standard YOLOv8 model and its modified version were compared for inference time, mean Average Precision (mAP), and model weight. The pruned YOLOv8 model cuts inference time by 15.56%, from 4.5 ms to 3.8 ms, and reduces model weight. The advantages mentioned above are offset by a 1.6% decrease in mean average precision. This research advances object detection technology by demonstrating architectural modifications' efficacy. These changes make the model faster and lighter, making it suitable for real-time surveillance. The accuracy trade-off is slight. The implications of these findings are crucial for implementing efficient object detection systems in CCTV surveillance. These findings also lay the groundwork for future research to improve such systems' speed-accuracy trade-off.</dc:description><dc:publisher>Sunan Gunung Djati State Islamic University Bandung</dc:publisher><dc:date>2023-12-28</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.15575/join.v8i2.1196</dc:identifier><dc:identifier>10.15575/join.v8i2.1196</dc:identifier><dc:source>Jurnal Online Informatika; Vol 8 No 2 (2023); 261-270</dc:source><dc:source>2527-9165</dc:source><dc:source>2528-1682</dc:source><dc:language>en</dc:language><dc:relation>https://join.if.uinsgd.ac.id/index.php/join/article/download/1196/296</dc:relation><dc:rights>https://creativecommons.org/licenses/by-nd/4.0/</dc:rights></oai_dc:dc>