Applications of mathematical morphology operators in civil infrastructures

• Published in: Earth science informatics 2024-10, Vol.17 (5), p.4027-4033
• Main Authors: Abrudan, Dumitru, Drăgulinescu, Ana-Maria, Vizireanu, Nicolae
• Format: Article
• Language: English
• Subjects: Cracks; Data collection; Datasets; Drone aircraft; Earth and Environmental Science; Earth Sciences; Earth System Sciences; Flaw detection; Image acquisition; Image filters; Image processing; Information Systems Applications (incl.Internet); Infrastructure; Manpower; Mathematical morphology; Morphology; Neural networks; Ontology; Operators (mathematics); Simulation and Modeling; Space Exploration and Astronautics; Space Sciences (including Extraterrestrial Physics; Unmanned aircraft
• ISSN: 1865-0473; 1865-0481
• DOI: 10.1007/s12145-024-01379-3

Civil infrastructures require a permanent attention and maintenance from the moment of commissioning to moment of demolition. One important aspect which is mandatory to be taken into consideration is crack detection. Cracks can appear during the lifetime of the civil infrastructure and require specialized personal for assessment. Depending of the civil infrastructure, this operation can require specialized skills (such as climbing). To overcome this issue with regards to specialized manpower, image processing is used. Nowadays, images can be easily acquired using an unmanned aircraft vehicle system known also as a drone. The main advantages of a drone for civil infrastructure image acquisition are: i) it can be operated at different heights, ii) rapid data collection, iii) cost and time savings, iv) user-friendly interface.The main purpose of our paper resides in improving the accuracy of the pre-trained neural networks when noisy images are used in civil works. Throughout our research, we used a dataset which contains three classes of images: with cracks, without cracks and with noise. To remove the noise presented in images mathematical morphology operators (MMO) are used. Our results reveal that using opening operator filter on a dataset of images which present civil infrastructure cracks outperform the results obtained using only pre-trained neural networks. In addition, the computation time is reduced.