TY - GEN
T1 - Performance Evaluation of YOLO-Based Deep Learning Models for Real-Time Armour Unit Detection with Image Pre-processing Method
AU - Pratama, Firmansyah Putra
AU - Pratama, Alfan Rizaldy
AU - Sari, Dewi Mutiara
AU - Marta, Bayu Sandi
AU - Dwito Armono, R. Haryo
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Breakwater construction in Indonesia still relies on divers to direct the placement of rock armour units, which is risky and time-constrained. This research aims to replace the diver's task with a deep learning-based vision system using YOLO-based deep learning models. The system utilizes image pre-processing technology by applying histogram equalization (HE) techniques to improve image quality before the detection process. This research evaluates the performance of the YOLO-based deep learning models in detecting armour units in real-time with a focus on various environmental conditions, which are clear and murky water. The analysis reveals clear water consistently supports higher average frame rates (FPS) compared to murky water, maintaining efficient frame processing across all models. In murky water, histogram equalization significantly enhances detection accuracy from 60% to 80% for YOLOv4-tiny and YOLOv7-tiny, demonstrating its effectiveness in challenging conditions. Notably, accuracy remains at 100% for all models in clear water, underscoring their robust performance under optimal visibility conditions.
AB - Breakwater construction in Indonesia still relies on divers to direct the placement of rock armour units, which is risky and time-constrained. This research aims to replace the diver's task with a deep learning-based vision system using YOLO-based deep learning models. The system utilizes image pre-processing technology by applying histogram equalization (HE) techniques to improve image quality before the detection process. This research evaluates the performance of the YOLO-based deep learning models in detecting armour units in real-time with a focus on various environmental conditions, which are clear and murky water. The analysis reveals clear water consistently supports higher average frame rates (FPS) compared to murky water, maintaining efficient frame processing across all models. In murky water, histogram equalization significantly enhances detection accuracy from 60% to 80% for YOLOv4-tiny and YOLOv7-tiny, demonstrating its effectiveness in challenging conditions. Notably, accuracy remains at 100% for all models in clear water, underscoring their robust performance under optimal visibility conditions.
KW - armour units
KW - breakwater
KW - deep learning
KW - image pre-processing
KW - real-time detection
UR - http://www.scopus.com/inward/record.url?scp=85204991146&partnerID=8YFLogxK
U2 - 10.1109/IES63037.2024.10665816
DO - 10.1109/IES63037.2024.10665816
M3 - Conference contribution
AN - SCOPUS:85204991146
T3 - 2024 International Electronics Symposium: Shaping the Future: Society 5.0 and Beyond, IES 2024 - Proceeding
SP - 541
EP - 546
BT - 2024 International Electronics Symposium
A2 - Yunanto, Andhik Ampuh
A2 - Ramadhani, Afifah Dwi
A2 - Prayogi, Yanuar Risah
A2 - Putra, Putu Agus Mahadi
A2 - Rahmawati, Weny Mistarika
A2 - Rusli, Muhammad Rizani
A2 - Humaira, Fitrah Maharani
A2 - Nadziroh, Faridatun
A2 - Sa'adah, Nihayatus
A2 - Muna, Nailul
A2 - Rizki, Aris Bahari
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 26th International Electronics Symposium, IES 2024
Y2 - 6 August 2024 through 8 August 2024
ER -