CorrDetector : A framework for structural corrosion detection from drone images using ensemble deep learning

Journal article


Forkan, Abdur Rahim Mohammad, Kang, Yong-Bin, Jayaraman, Prem Prakash, Liao, Kewen, Kaul, Rohit, Morgan, Graham, Ranjan, Rajiv and Sinha, Samir. (2022). CorrDetector : A framework for structural corrosion detection from drone images using ensemble deep learning. Expert Systems with Applications. 193, p. Article 116461. https://doi.org/10.1016/j.eswa.2021.116461
AuthorsForkan, Abdur Rahim Mohammad, Kang, Yong-Bin, Jayaraman, Prem Prakash, Liao, Kewen, Kaul, Rohit, Morgan, Graham, Ranjan, Rajiv and Sinha, Samir
Abstract

In this paper, we propose a new technique that applies automated image analysis in the area of structural corrosion monitoring and demonstrate improved efficacy compared to existing approaches. Structural corrosion monitoring is the initial step of the risk-based maintenance philosophy and depends on an engineer’s assessment regarding the risk of building failure balanced against the fiscal cost of maintenance. This introduces the opportunity for human error which is further complicated when restricted to assessment using drone captured images for those areas not reachable by humans due to many background noises. The importance of this problem has promoted an active research community aiming to support the engineer through the use of artificial intelligence (AI) image analysis for corrosion detection. In this paper, we advance this area of research with the development of a framework, CorrDetector. CorrDetector uses a novel ensemble deep learning approach underpinned by convolutional neural networks (CNNs) for structural identification and corrosion feature extraction. We provide an empirical evaluation using real-world images of a complicated structure (e.g. telecommunication tower) captured by drones, a typical scenario for engineers. Our study demonstrates that the ensemble approach of CorrDetector significantly outperforms the state-of-the-art in terms of classification accuracy.

Keywordscorrosion detection; object detection; deep learning; drone images; industrial structure; ensemble model; CNN
Year2022
JournalExpert Systems with Applications
Journal citation193, p. Article 116461
PublisherElsevier Ltd
ISSN0957-4174
Digital Object Identifier (DOI)https://doi.org/10.1016/j.eswa.2021.116461
Scopus EID2-s2.0-85123251903
Page range1-12
FunderRobonomics AI, Australia
Publisher's version
License
All rights reserved
File Access Level
Controlled
Output statusPublished
Publication dates
Online10 Jan 2022
Publication process dates
Accepted23 Dec 2021
Deposited16 May 2023
Permalink -

https://acuresearchbank.acu.edu.au/item/8z04w/corrdetector-a-framework-for-structural-corrosion-detection-from-drone-images-using-ensemble-deep-learning

Restricted files

Publisher's version

  • 1
    total views
  • 0
    total downloads
  • 0
    views this month
  • 0
    downloads this month
These values are for the period from 19th October 2020, when this repository was created.

Export as

Related outputs

CNN attention guidance for improved orthopedics radiographic fracture classification
Liao, Zhibin, Liao, Kewen, Shen, Haifeng, van Boxel, Marouska F, Prijs, Jasper, Jaarsma, Ruurd L., Doornberg, Job N., van den Hengel, Anton and Verjans, Johan W.. (2022). CNN attention guidance for improved orthopedics radiographic fracture classification. IEEE Journal of Biomedical and Health Informatics. 26(7), pp. 3139-3150. https://doi.org/10.1109/JBHI.2022.3152267
On finding maximum disjoint paths with different colors : Computational complexity and practical LP-based algorithms
Deng, Yunyun, Guo, Longkun, Liao, Kewen and Chen, Yi. (2021). On finding maximum disjoint paths with different colors : Computational complexity and practical LP-based algorithms. Theoretical Computer Science. 886, pp. 157-168. https://doi.org/10.1016/j.tcs.2021.08.009
Understanding the effects of real-time sentiment analysis and morale visualisation in backchannel systems : A case study
Wyeld, Theodor, Jiranantanagorn, Peerumporn, Shen, Haifeng, Liao, Kewen and Bednarz, Tomasz. (2021). Understanding the effects of real-time sentiment analysis and morale visualisation in backchannel systems : A case study. International Journal of Human-Computer Studies. 145, p. Article 102524. https://doi.org/10.1016/j.ijhcs.2020.102524
Human-AI interactive and continuous sensemaking : A case study of image classification using scribble attention maps
Shen, Haifeng, Liao, Kewen, Liao, Zhibin, Doornberg, Job, Qiao, Maoying, van den Hengel, Anton and Verjans, Johan W.. (2021). Human-AI interactive and continuous sensemaking : A case study of image classification using scribble attention maps. CHI Conference on Human Factors in Computing Systems. Virtual 08 - 13 May 2021 pp. 1-8 https://doi.org/10.1145/3411763.3451798
Inferring location types with geo-social-temporal pattern mining
Anwar, Tarique, Liao, Kewen, Goyal, Angelic, Sellis, Timos, Kayes, A. S. M. and Shen, Haifeng. (2020). Inferring location types with geo-social-temporal pattern mining. IEEE Access. 8, pp. 154789-154799. https://doi.org/10.1109/ACCESS.2020.3018997
Temporal betweenness centrality in dynamic graphs
Tsalouchidou, Ioanna, Baeza-Yates, Ricardo, Bonchi, Francesco, Liao, Kewen and Sellis, Timos. (2020). Temporal betweenness centrality in dynamic graphs. International Journal of Data Science and Analytics. 9(3), pp. 257 - 272. https://doi.org/10.1007/s41060-019-00189-x
Performance-aware cost-effective resource provisioning for future grid iot-cloud system
Li, Weiling, Liao, Kewen, He, Qiang and Xia, Yunni. (2019). Performance-aware cost-effective resource provisioning for future grid iot-cloud system. Journal of Energy Engineering. 145(5), pp. 2-13. https://doi.org/10.1061/(ASCE)EY.1943-7897.0000611
On effective and efficient graph edge labeling
Goonetilleke, Oshini, Koutra, Danai, Liao, Kewen and Sellis, Timos. (2019). On effective and efficient graph edge labeling. Distributed and Parallel Databases. 37(1), pp. 5-38. https://doi.org/10.1007/s10619-018-7234-4
Contextual community search over large social networks
Chen, Lu, Liu, Chengfei, Liao, Kewen, Li, Jianxin and Zhou, Rui. (2019). Contextual community search over large social networks. 35th International Conference on Data Engineering (ICDE). Macao, China: IEEE Computer Society. pp. 88 - 99 https://doi.org/10.1109/ICDE.2019.00017
Efficient algorithms for flexible sweep coverage in crowdsensing
Huang, Peihuang, Zhu, Wenxing, Liao, Kewen, Sellis, Timos, Yu, Zhiyong and Guo, Longkun. (2018). Efficient algorithms for flexible sweep coverage in crowdsensing. IEEE Access. 6, pp. 50055-50065. https://doi.org/10.1109/ACCESS.2018.2868931
Classification and annotation of open internet of things datastreams
Montori, Federico, Liao, Kewen, Jayaraman, Prem Prakash, Bononi, Luciano, Sellis, Timos and Georgakopoulos, Dimitrios. (2018). Classification and annotation of open internet of things datastreams. 19th International Conference, Web Information Systems Engineering, WISE 2018. Dubai, United Arab Emirates 12 2018 - 15 Nov 2019 Springer. pp. 209-224 https://doi.org/10.1007/978-3-030-02925-8_15
A fast algorithm for optimally finding partially disjoint shortest paths
Guo, Longkun, Deng, Yunyun, Liao, Kewen, He, Qiang, Sellis, Timos and Hu, Zheshan. (2018). A fast algorithm for optimally finding partially disjoint shortest paths. Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18), Stockholm, Sweden, July 13-19, 2018. Stockholm, Sweden: International Joint Conferences on Artificial Intelligence. pp. 1456 - 1462 https://doi.org/10.24963/ijcai.2018/202
A cost model for long-term compressed data retention
Liao, Kewen, Moffat, Alistair, Petri, Matthias and Wirth, Anthony. (2017). A cost model for long-term compressed data retention. 10th International Conference on Web Search and Data Mining. United States of America: Association for Computing Machinery. pp. 241 - 249 https://doi.org/10.1145/3018661.3018738
Edge labeling schemes for graph data
Goonetilleke, Oshini, Koutra, Danai, Sellis, Timos and Liao, Kewen. (2017). Edge labeling schemes for graph data. 29th International Conference on Scientific and Statistical Database Management. United States of America: Association for Computing Machinery. pp. 1 - 12 https://doi.org/10.1145/3085504.3085516
Effective construction of relative Lempel-Ziv dictionaries
Liao, Kewen, Petri, Matthias, Moffat, Alistair and Wirth, Anthony. (2016). Effective construction of relative Lempel-Ziv dictionaries. WWW '16: 25th International World Wide Web Conference. Switzerland: Association for Computing Machinery. pp. 807 - 816 https://doi.org/10.1145/2872427.2883042
Improved approximation algorithms for constrained fault-tolerant resource allocation
Liao, Kewen, Shen, Hong and Guo, Longkun. (2015). Improved approximation algorithms for constrained fault-tolerant resource allocation. Theoretical Computer Science. 590, pp. 118-128. https://doi.org/10.1016/j.tcs.2015.02.029
Improved approximation algorithms for computing k disjoint paths subject to two constraints
Guo, Longkun, Shen, Hong and Liao, Kewen. (2015). Improved approximation algorithms for computing k disjoint paths subject to two constraints. Journal of Combinatorial Optimization. 29(1), pp. 153-164. https://doi.org/10.1007/s10878-013-9693-x
Brief announcement : Efficient approximation algorithms for computing k disjoint restricted shortest paths
Guo, Longkun, Liao, Kewen, Shen, Hong and Li, Peng. (2015). Brief announcement : Efficient approximation algorithms for computing k disjoint restricted shortest paths. 27th ACM Symposium on Parallelism in Algorithms and Architectures. Portland, Oregon, United States of America 13 - 15 Jun 2015 Association for Computing Machinery. pp. 62–64 https://doi.org/10.1145/2755573.2755608
LP-based approximation algorithms for reliable resource allocation
Liao, Kewen and Shen, Hong. (2014). LP-based approximation algorithms for reliable resource allocation. The Computer Journal. 57(1), pp. 154-164. https://doi.org/10.1093/comjnl/bxs164
On the shallow-light Steiner tree problem
Guo, Longkun, Liao, Kewen and Shen, Hong. (2014). On the shallow-light Steiner tree problem. 15th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT 2014). Hong Kong, China 09 - 14 Dec 2014 IEEE Computer Society. pp. 56-60 https://doi.org/10.1109/PDCAT.2014.17
Effect of off-zenith observations on reducing the impact of precipitation on ground-based microwave radiometer measurement accuracy
Xu, Guirong, Stick Ware, Randolph, Zhang, Wengang, Feng, Guangliu, Liao, Kewen and Liu, Yibing. (2014). Effect of off-zenith observations on reducing the impact of precipitation on ground-based microwave radiometer measurement accuracy. Atmospheric Research. 140-141, pp. 85 - 94. https://doi.org/10.1016/j.atmosres.2014.01.021