EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ICDW-YOLO: An Efficient Timber Construction Crack Detection Algorithm

Jieyang Zhou iD, Jing Ning iD, Zhiyang Xiang iD, Pengfei Yin iD

Sensors · 03.07.2024 · 24 (13) · 4333

DOI: 10.3390/s24134333 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 03.07.2024. Verfasst von Jieyang Zhou und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Engineering, Jishou University, Jishou 416000, China. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jishou University, Hunan Student's innovation and entrepreneurship training program, Jishou University Introduced Personnel and Returned Doctoral Research Funding Project: Key Technologies on Collaborative Information Retrieval for Big Data.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A robust wood material crack detection algorithm, sensitive to small targets, is indispensable for production and building protection. However, the precise identification and localization of cracks in wooden materials present challenges owing to significant scale variations among cracks and the irregular quality of existing data. In response, we propose a crack detection algorithm tailored to wooden materials, leveraging advancements in the YOLOv8 model, named ICDW-YOLO (improved crack detection for wooden material-YOLO). The ICDW-YOLO model introduces novel designs for the neck network and layer structure, along with an anchor algorithm, which features a dual-layer attention mechanism and dynamic gradient gain characteristics to optimize and enhance the original model. Initially, a new layer structure was crafted using GSConv and GS bottleneck, improving the model’s recognition accuracy by maximizing the preservation of hidden channel connections. Subsequently, enhancements to the network are achieved through the gather–distribute mechanism, aimed at augmenting the fusion capability of multi-scale features and introducing a higher-resolution input layer to enhance small target recognition. Empirical results obtained from a customized wooden material crack detection dataset demonstrate the efficacy of the proposed ICDW-YOLO algorithm in effectively detecting targets. Without significant augmentation in model complexity, the mAP50–95 metric attains 79.018%, marking a 1.869% improvement over YOLOv8. Further validation of our algorithm’s effectiveness is conducted through experiments on fire and smoke detection datasets, aerial remote sensing image datasets, and the coco128 dataset. The results showcase that ICDW-YOLO achieves a mAP50 of 69.226% and a mAP50–95 of 44.210%, indicating robust generalization and competitiveness vis-à-vis state-of-the-art detectors.

Schlagwörter

Stichwörter der Autor:innen

crack detectionneural networkobject detection

Autor:innen und Institutionen

  • College of Computer Science and Engineering, Jishou University, Jishou 416000, China.
  • School of Communication and Electronic Engineering, Jishou University, Jishou 416000, China.

ORCID-Profile: Jieyang Zhou, Jing Ning, Zhiyang Xiang, Pengfei Yin

Förderung

  • Jishou University
  • Hunan Student's innovation and entrepreneurship training program
  • Jishou University Introduced Personnel and Returned Doctoral Research Funding Project: Key Technologies on Collaborative Information Retrieval for Big Data
  • Hunan Student’s Innovation and Entrepreneurship Training Program

Zitieren

APA

Zhou, J., Ning, J., Xiang, Z., & Yin, P. (2024). ICDW-YOLO: An Efficient Timber Construction Crack Detection Algorithm. Sensors, 24(13), 4333. https://doi.org/10.3390/s24134333

Vancouver

Zhou J, Ning J, Xiang Z, Yin P. ICDW-YOLO: An Efficient Timber Construction Crack Detection Algorithm. Sensors. 2024;24(13):4333. doi:10.3390/s24134333

BibTeX
@article{Zhou2024,
  author = {Zhou, Jieyang and Ning, Jing and Xiang, Zhiyang and Yin, Pengfei},
  title = {ICDW-YOLO: An Efficient Timber Construction Crack Detection Algorithm},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {13},
  pages = {4333},
  doi = {10.3390/s24134333}
}
Kostenlos starten →