EUVIMEDEUVIMED entdecken
Crossref

Crack detection on concrete surfaces using the YOLOv8 quantization model

Binh Ngo Thanh, Minh Ngo Van, Linh Vu Ngoc, Dung Pham Tuan

Transport and Communications Science Journal · 19.03.2025 · 76 (4) · 489-503

DOI: 10.47869/tcsj.76.4.4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transport and Communications Science Journal, online erschienen am 19.03.2025. Verfasst von Binh Ngo Thanh und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The condition of concrete structures’ surfaces, most importantly the condition of cracks on the surface and their development over time, is an important and common criterion used to diagnose health conditions and determine their service life. Rapid collection, identification, and monitoring of concrete structures’ surfaces to assess the condition of bridge structures requires a fast-acting system that can meet the actual speed of the inspection process. This article introduces a YOLOv8 quantization model for rapid crack detection in concrete structures, leveraging GPU acceleration suitable for real-time video analysis during bridge inspections. The method incorporates histogram equalization and image enhancement to mitigate lighting issues and improve crack visibility. INT8 quantization reduces model size and accelerates processing while maintaining accuracy through dataset calibration. Converted to TensorRT and integrated into the inference pipeline for optimized GPU and memory management, the YOLOv8 quantization model achieves at least 30 FPS using full HD video footage. Field tests with NVIDIA GPUs demonstrated a 5x reduction in processing time, a 5x FPS increase, and a 6x improvement in GPU utilization, all while maintaining similar RAM usage. The quantum YOLOv8 model is optimized for NVIDIA GPUs, achieving a balance between accuracy and processing speed, allowing workers to analyze full HD videos in real-time at a rate of at least 30 FPS during field inspections

Zitieren

APA

Thanh, B. N., Van, M. N., Ngoc, L. V., & Tuan, D. P. (2025). Crack detection on concrete surfaces using the YOLOv8 quantization model. Transport and Communications Science Journal, 76(4), 489-503. https://doi.org/10.47869/tcsj.76.4.4

Vancouver

Thanh BN, Van MN, Ngoc LV, Tuan DP. Crack detection on concrete surfaces using the YOLOv8 quantization model. Transport and Communications Science Journal. 2025;76(4):489-503. doi:10.47869/tcsj.76.4.4

BibTeX
@article{Thanh2025,
  author = {Thanh, Binh Ngo and Van, Minh Ngo and Ngoc, Linh Vu and Tuan, Dung Pham},
  title = {Crack detection on concrete surfaces using the YOLOv8 quantization model},
  journal = {Transport and Communications Science Journal},
  year = {2025},
  volume = {76},
  number = {4},
  pages = {489--503},
  doi = {10.47869/tcsj.76.4.4}
}
Kostenlos starten →