A methodology framework for retrieval of concrete surface crack′s image properties based on hybrid model
Optik(2019)
摘要
Regular concrete surface crack inspection is critical since cracks are one of the earliest signs of deteriorating in concrete structures. With recent digital imaging and processing techniques, computer vision-based inspection shows huge potential in this field. A novel image processing framework for automatically retrieving multiple crack properties from concrete surface images is proposed. The framework includes (1) a crack extraction algorithm which combines edge detecting and seed growing; (2) a skeleton optimizing method which contains short branch deleting and polyline approximation algorithm; (3) a hybrid crack model which classifies crack segments into disc-shaped and bar-shaped parts based on their skeleton topological information, and (4) a triad labelling method that indicates the interrelationships between different cracks. Contrast experiments showed that the proposed segmentation method can extract more complete crack segments. Real image experiments indicated that the framework is effective and helpful for subsequent concrete structure health assessment.
更多查看译文
关键词
Crack detection,Image analysis,Feature extraction,Concrete,Hybrid model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络