Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection
Abstract
:1. Introduction
2. Related Work
- We propose an improved U-Net-based method for infrared image segmentation of aircraft skin water accumulation areas, which has not been previously reported.
- We enhance the model’s robustness and accuracy by introducing a channel and spatial attention mechanism to the network.
- We optimize the complexity of the model by replacing traditional convolutions with depthwise separable convolutions.
- We construct a dataset of infrared images for aircraft skin water accumulation areas and evaluate the performance of the proposed method through comparative experiments.
3. Methodology
3.1. Network Architecture
3.2. Convolutional Block Attention Module
3.3. Depthwise Separable Convolution
4. Experiment
4.1. Dataset Collection
4.2. Training Strategy
5. Evaluation Metrics
- Mean pixel accuracy (MPA): Calculates the average accuracy of pixel-wise classifications across all pixels in an image. The formula is defined as follows:
- Mean intersection over union (MIoU): Computes the average intersection-over-union values for each class, providing a measure of segmentation accuracy. The formula is defined as follows:
- Precision: Quantifies the ratio of correctly predicted positive instances to the total predicted positive instances, indicating the accuracy of positive predictions made by the model. The formula is defined as follows:
- Recall: Measures the ratio of correctly predicted positive instances to the total actual positive instances, reflecting the model’s ability to capture all relevant instances in the dataset. The formula is defined as follows:
- Dice coefficient: Quantifies the similarity between the predicted and ground truth segmentations by measuring the overlap between the two. The formula is defined as follows:
- Hausdorff Distance (HD): Measures the maximum distance between the predicted and ground truth boundaries, defined as follows:
- Cohen’s Kappa: Quantifies the overall agreement between the predicted labels and the ground truth, and is calculated as follows:
- Floating point operations per second (FLOPs): Measure of the computational complexity of a model, representing the total number of floating-point arithmetic operations.
- Parameters (Params): The number of model parameters, which measures the total quantity of trainable parameters in a neural network model.
- Inference time: Refers to the amount of time required to perform inference using a deep learning model, which can directly reflect the efficiency of the model operation.
6. Results Analysis
6.1. Segmentation Accuracy
6.2. Inference Speed
6.3. Ablation Study
7. Discussion
8. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Meng, D.; Boer, W.; Juan, X.; Kasule, A.N.; Hongfu, Z. Visual inspection of aircraft skin: Automated pixel-level defect detection by instance segmentation. Chin. J. Aeronaut. 2022, 35, 254–264. [Google Scholar]
- Alemour, B.; Badran, O.; Hassan, M.R. A review of using conductive composite materials in solving lightening strike and ice accumulation problems in aviation. J. Aerosp. Technol. Manag. 2019, 11, e1919. [Google Scholar] [CrossRef]
- Wei, K.; Yang, Y.; Zuo, H.; Zhong, D. A review on ice detection technology and ice elimination technology for wind turbine. Wind Energy 2020, 23, 433–457. [Google Scholar] [CrossRef]
- Chulkov, A.; Vavilov, V.; Moskovchenko, A.; Pan, Y.Y. Quantitative evaluation of water content in composite honeycomb structures by using one-sided IR thermography: Is there any promise? In Proceedings of the Thermosense: Thermal Infrared Applications XXXIX, Anaheim, CA, USA, 9–13 April 2017; SPIE: St Bellingham, WA, USA, 2017; Volume 10214, pp. 213–220. [Google Scholar]
- Minaee, S.; Boykov, Y.; Porikli, F.; Plaza, A.; Kehtarnavaz, N.; Terzopoulos, D. Image segmentation using deep learning: A survey. IEEE Trans. Pattern Anal. Mach. Intell. 2021, 44, 3523–3542. [Google Scholar] [CrossRef] [PubMed]
- Zaidi, S.S.A.; Ansari, M.S.; Aslam, A.; Kanwal, N.; Asghar, M.; Lee, B. A survey of modern deep learning based object detection models. Digit. Signal Process. 2022, 126, 103514. [Google Scholar] [CrossRef]
- Roy, A.M.; Bhaduri, J. DenseSPH-YOLOv5: An automated damage detection model based on DenseNet and Swin-Transformer prediction head-enabled YOLOv5 with attention mechanism. Adv. Eng. Inform. 2023, 56, 102007. [Google Scholar] [CrossRef]
- Wang, R.; Lei, T.; Cui, R.; Zhang, B.; Meng, H.; Nandi, A.K. Medical image segmentation using deep learning: A survey. IET Image Process. 2022, 16, 1243–1267. [Google Scholar] [CrossRef]
- Lin, A.; Chen, B.; Xu, J.; Zhang, Z.; Lu, G.; Zhang, D. Ds-transunet: Dual swin transformer u-net for medical image segmentation. IEEE Trans. Instrum. Meas. 2022, 71, 1–15. [Google Scholar] [CrossRef]
- Aboelenein, N.M.; Piao, S.; Noor, A.; Ahmed, P.N. MIRAU-Net: An improved neural network based on U-Net for gliomas segmentation. Signal Process. Image Commun. 2022, 101, 116553. [Google Scholar] [CrossRef]
- Abadi, A.D.; Gu, Y.; Goncharenko, I.; Kamijo, S. Detection of Cyclist’s Crossing Intention based on Posture Estimation for Autonomous Driving. IEEE Sens. J. 2023, 23, 11274–11284. [Google Scholar] [CrossRef]
- Nahavandi, S.; Alizadehsani, R.; Nahavandi, D.; Mohamed, S.; Mohajer, N.; Rokonuzzaman, M.; Hossain, I. A Comprehensive Review on Autonomous Navigation. arXiv 2022, arXiv:2212.12808. [Google Scholar]
- Liu, H. Image Segmentation Techniques for Intelligent Monitoring of Putonghua Examinations. Adv. Math. Phys. 2022, 2022, 4302666. [Google Scholar] [CrossRef]
- Kazakeviciute-Januskeviciene, G.; Janusonis, E.; Bausys, R. Evaluation of the segmentation of remote sensing images. In Proceedings of the 2021 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream), Vilnius, Lithuania, 22 April 2021; IEEE: Piscataway, NJ, USA, 2021; pp. 1–7. [Google Scholar]
- Liang, C.; Zhang, Y. Multi Object Infrared Image Segmentation Based on Multi-level Feature Fusion. In Proceedings of the International Conference on Computer Science, Engineering and Education Applications, Warsaw, Poland, 17–19 March 2023; Springer: Berlin/Heidelberg, Germany, 2023; pp. 26–36. [Google Scholar]
- Otsu, N. A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 1979, 9, 62–66. [Google Scholar] [CrossRef]
- Arbelaez, P.; Maire, M.; Fowlkes, C.; Malik, J. Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2010, 33, 898–916. [Google Scholar] [CrossRef] [PubMed]
- Nock, R.; Nielsen, F. Statistical region merging. IEEE Trans. Pattern Anal. Mach. Intell. 2004, 26, 1452–1458. [Google Scholar] [CrossRef]
- Najman, L.; Schmitt, M. Watershed of a continuous function. Signal Process. 1994, 38, 99–112. [Google Scholar] [CrossRef]
- Neves, S.; Da Silva, E.; Mendonca, G. Wavelet-watershed automatic infrared image segmentation method. Electron. Lett. 2003, 39, 903–904. [Google Scholar] [CrossRef]
- Zhou, S.; Yang, P.; Xie, W. Infrared image segmentation based on Otsu and genetic algorithm. In Proceedings of the 2011 International Conference on Multimedia Technology, Hangzhou, China, 26–28 July 2011; IEEE: Piscataway, NJ, USA, 2011; pp. 5421–5424. [Google Scholar]
- Cui, L.L.; Lai, H.; Tang, Y.W.; Qi, M.J. Application of petrochemical heat equipments’ state inspection based on the edge detection of infrared image segmentation. Appl. Mech. Mater. 2013, 303, 970–974. [Google Scholar] [CrossRef]
- Zhang, R.; Zhu, S.; Zhou, Q. A novel gradient vector flow snake model based on convex function for infrared image segmentation. Sensors 2016, 16, 1756. [Google Scholar] [CrossRef]
- Liu, S.T.; Wang, Z.; Wang, Z. Fast infrared image segmentation method based on 2D OTSU and particle swarm optimization. In Proceedings of the Third International Workshop on Pattern Recognition, Jinan, China, 19–21 May 2018; SPIE: St Bellingham, WA, USA, 2018; Volume 10828, pp. 94–100. [Google Scholar]
- Dargan, S.; Kumar, M.; Ayyagari, M.R.; Kumar, G. A survey of deep learning and its applications: A new paradigm to machine learning. Arch. Comput. Methods Eng. 2020, 27, 1071–1092. [Google Scholar] [CrossRef]
- Rafique, A.A.; Ghadi, Y.Y.; Alsuhibany, S.A.; Chelloug, S.A.; Jalal, A.; Park, J. CNN Based Multi-Object Segmentation and Feature Fusion for Scene Recognition. Comput. Mater. Contin. 2022, 73, 4657–4675. [Google Scholar]
- Long, J.; Shelhamer, E.; Darrell, T. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, 7–12 June 2015; pp. 3431–3440. [Google Scholar]
- Ronneberger, O.; Fischer, P.; Brox, T. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015, Proceedings of the 18th International Conference, Munich, Germany, 5–9 October 2015, Proceedings, Part III 18; Springer: Berlin/Heidelberg, Germany, 2015; pp. 234–241. [Google Scholar]
- Paszke, A.; Chaurasia, A.; Kim, S.; Culurciello, E. Enet: A deep neural network architecture for real-time semantic segmentation. arXiv 2016, arXiv:1606.02147. [Google Scholar]
- Chen, L.C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A.L. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 40, 834–848. [Google Scholar] [CrossRef]
- He, K.; Gkioxari, G.; Dollár, P.; Girshick, R. Mask r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2961–2969. [Google Scholar]
- Zhao, H.; Shi, J.; Qi, X.; Wang, X.; Jia, J. Pyramid scene parsing network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 2881–2890. [Google Scholar]
- Wang, J.; Sun, K.; Cheng, T.; Jiang, B.; Deng, C.; Zhao, Y.; Liu, D.; Mu, Y.; Tan, M.; Wang, X.; et al. Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 2020, 43, 3349–3364. [Google Scholar] [CrossRef]
- Zhang, H.; Hong, X.; Zhou, S.; Wang, Q. Infrared image segmentation for photovoltaic panels based on Res-UNet. In Proceedings of the Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Xi’an, China, 8–11 November 2019; Springer: Berlin/Heidelberg, Germany, 2019; pp. 611–622. [Google Scholar]
- Nan, J.; Bo, L. A lightweight real-time infrared image instance segmentation algorithm based on tiny YOLO. In Proceedings of the Seventh Symposium on Novel Photoelectronic Detection Technology and Applications, Kunming, China, 5–7 November 2020; SPIE: St Bellingham, WA, USA, 2021; Volume 11763, pp. 1098–1107. [Google Scholar]
- Chen, S.; Xu, X.; Yang, N.; Chen, X.; Du, F.; Ding, S.; Gao, W. R-Net: A novel fully convolutional network–based infrared image segmentation method for intelligent human behavior analysis. Infrared Phys. Technol. 2022, 123, 104164. [Google Scholar] [CrossRef]
- Yu, J.; He, Y.; Liu, H.; Zhang, F.; Li, J.; Sun, G.; Zhang, X.; Yang, R.; Wang, P.; Wang, H. An improved U-Net model for infrared image segmentation of wind turbine blade. IEEE Sens. J. 2022, 23, 1318–1327. [Google Scholar] [CrossRef]
- Zhao, X.; Dai, J.; Li, L.p.; Su, Z.; Ma, X.f. Deep learning-based laser and infrared composite imaging for armor target identification and segmentation in complex battlefield environments. Infrared Phys. Technol. 2023, 132, 104725. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 770–778. [Google Scholar]
- Nair, V.; Hinton, G.E. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel, 21–24 June 2010; pp. 807–814. [Google Scholar]
- Liu, F.; Ren, X.; Zhang, Z.; Sun, X.; Zou, Y. Rethinking skip connection with layer normalization. In Proceedings of the 28th International Conference on Computational Linguistics, Barcelona, Spain, 8–13 December 2020; pp. 3586–3598. [Google Scholar]
- Choromanski, K.; Likhosherstov, V.; Dohan, D.; Song, X.; Gane, A.; Sarlos, T.; Hawkins, P.; Davis, J.; Mohiuddin, A.; Kaiser, L.; et al. Rethinking attention with performers. arXiv 2020, arXiv:2009.14794. [Google Scholar]
- Guo, M.H.; Xu, T.X.; Liu, J.J.; Liu, Z.N.; Jiang, P.T.; Mu, T.J.; Zhang, S.H.; Martin, R.R.; Cheng, M.M.; Hu, S.M. Attention mechanisms in computer vision: A survey. Comput. Vis. Media 2022, 8, 331–368. [Google Scholar] [CrossRef]
- Woo, S.; Park, J.; Lee, J.Y.; Kweon, I.S. Cbam: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 3–19. [Google Scholar]
- Chollet, F. Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 1251–1258. [Google Scholar]
- Howard, A.G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv 2017, arXiv:1704.04861. [Google Scholar]
- Yi-de, M.; Qing, L.; Zhi-Bai, Q. Automated image segmentation using improved PCNN model based on cross-entropy. In Proceedings of the 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, Hong Kong, China, 20–22 October 2004; IEEE: Piscataway, NJ, USA, 2004; pp. 743–746. [Google Scholar]
- Wang, Z.; Wang, E.; Zhu, Y. Image segmentation evaluation: A survey of methods. Artif. Intell. Rev. 2020, 53, 5637–5674. [Google Scholar] [CrossRef]
- Powers, D.M. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv 2020, arXiv:2010.16061. [Google Scholar]
Confusion Matrix | Predicted | ||
---|---|---|---|
Positive | Negative | ||
Ground Truth | Positive | TP | FN |
Negative | FP | TN |
Model | MPA | MIoU | Precision | Recall | Dice | HD | |
---|---|---|---|---|---|---|---|
FCN | 91.52% | 84.38% | 99.19% | 98.57% | 98.88% | 23.44 | 0.81 |
U-Net | 97.56% | 89.42% | 99.86% | 98.64% | 99.24% | 17.99 | 0.91 |
DeepLabv3 | 96.84% | 85.43% | 99.75% | 97.90% | 98.81% | 9.66 | 0.87 |
PSPNet | 92.13% | 86.08% | 99.30% | 98.88% | 99.09% | 13.52 | 0.83 |
HRNet | 96.79% | 89.90% | 99.78% | 98.93% | 99.35% | 14.72 | 0.89 |
Proposed model | 97.97% | 92.68% | 99.81% | 99.27% | 99.54% | 10.81 | 0.93 |
Model | FLOPs | Params | Inference Time |
---|---|---|---|
FCN | 11.37 G | 15.25 M | 3.46 ms |
U-Net | 17.51 G | 13.40 M | 5.88 ms |
DeepLabv3 | 23.08 G | 39.63 M | 7.62 ms |
PSPNet | 28.42 G | 52.49 M | 10.27 ms |
HRNet | 13.20 G | 65.85 M | 42.98 ms |
Proposed model | 33.06 G | 35.07 M | 15.02 ms |
The bold indicates the best results in the table. |
Model | CBAM | DW | MIoU | MPA | Precision | Recall | HD | FLOPs | Params | Inference Time | |
---|---|---|---|---|---|---|---|---|---|---|---|
Res-UNet (Baseline) | 91.27% | 97.65% | 96.81% | 99.82% | 9.05 | 0.83 | 42.69 G | 57.16 M | 15.68 ms | ||
Res-UNet with CBAM | ✔ | 92.19% | 97.90% | 96.53% | 99.92% | 10.95 | 0.93 | 42.70 G | 57.34 M | 18.16 ms | |
Res-UNet with dw | ✔ | 91.43% | 97.20% | 96.61% | 99.92% | 10.81 | 0.92 | 33.11 G | 34.93 M | 9.54 ms | |
Proposed model | ✔ | ✔ | 92.68% | 97.97% | 99.81% | 99.27% | 10.81 | 0.93 | 33.06 G | 35.11 M | 15.02 ms |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Fei, H.; Zuo, H.; Wang, H.; Liu, Y.; Liu, Z.; Li, X. Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection. Aerospace 2024, 11, 961. https://doi.org/10.3390/aerospace11120961
Fei H, Zuo H, Wang H, Liu Y, Liu Z, Li X. Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection. Aerospace. 2024; 11(12):961. https://doi.org/10.3390/aerospace11120961
Chicago/Turabian StyleFei, Hang, Hongfu Zuo, Han Wang, Yan Liu, Zhenzhen Liu, and Xin Li. 2024. "Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection" Aerospace 11, no. 12: 961. https://doi.org/10.3390/aerospace11120961
APA StyleFei, H., Zuo, H., Wang, H., Liu, Y., Liu, Z., & Li, X. (2024). Deep Learning-Based Infrared Image Segmentation for Aircraft Honeycomb Water Ingress Detection. Aerospace, 11(12), 961. https://doi.org/10.3390/aerospace11120961