Abstract
Detection of road defects can be an extremely complicated task, given that it requires many trained human resources to overlook. Visual inspection tasks are starting to be performed by computer vision systems instead of people since such systems perform faster and deliver higher precision results. Recently, deep learning approaches showed a state-of-the-art solution in object detection and image segmentation. In this work, we present a pixel-wise road pavement defects detection method using the U-Net convolutional neural network. Instead of using a single deep neural network, we have aggregated several networks with different structures. We experimentally evaluated a different number of aggregation techniques (median, average and weighted average) to improve accuracy. The best-suggested configuration of a single network for road pavement cracks segmentation task has received up to 99.12%, and by aggregating six of them with averaging aggregation rule, the accuracy was improved up to 99.155%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
ImageNet Large Scale Visual Recognition Challenge (ILSVRC) Website, (2019), Available: http://image-net.org/challenges/LSVRC/. Accessed 22 Jan 2019 (Online)
A. Verikas, A. Lipnickas, K. Malmqvist, M. Bacauskiene, A. Gelzinis, Soft combination of neural classifiers: a comparative study. Pattern Recognit. Lett. 20(4), 429–444 (1999)
A. Verikas, A. Lipnickas, Fusing neural networks through space partitioning and fuzzy integration. Neural Process. Lett. 16(1), 53–65 (2002)
A. Verikas, A. Lipnickas, K.G. Malmqvist, Fusing neural networks through fuzzy integration, in Hybrid Methods in Pattern Recognition, World Scientific, 2002, May
Y. Shi, L. Cui, Z. Qi, F. Meng, Z. Chen, Automatic road crack detection using random structured forests. IEEE Trans. Intell. Transp. Syst. 17(12), 3434–3445 (2016)
L. Cui, Z. Qi, Z. Chen, F. Meng, Y. Shi, Pavement Distress Detection Using Random Decision Forests (Springer, Cham, 2015)
O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 9351, 234–241 (2015)
V. Zyuzin et al., Identification of the left ventricle endocardial border on two-dimensional ultrasound images using the convolutional neural network Unet, in Proceedings—2018 Ural Symposium Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT) 2018, pp. 76–78
X. Li, H. Chen, X. Qi, Q. Dou, C. W. Fu, P. A. Heng, H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes. IEEE Trans. Med. Imaging, vol. PP, no. 1, p. 1, 2018
V. Iglovikov, TernausNet : U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation, 2018
G. Huang, Y. Ma, Y. Yu, Vehicle segmentation from remote sensing images using the small object segmentation convolutional network, in 2017 4th International Conference on Systems and Informatics, ICSAI 2017, vol. 2018–January, no. Icsai, pp. 1292–1296, 2018
Z. Zhang, Q. Liu, Y. Wang, Road extraction by deep residual U-Net. IEEE Geosci. Remote Sens. Lett. 15(5), 749–753 (2018)
J.S. Winsuk Kim, Indoor Semantic segmentation for robot navigating on mobile, in 2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN), 2018, pp. 22–25
J. Akeret, C. Chang, A. Lucchi, A. Refregier, Radio frequency interference mitigation using deep convolutional neural networks. Astron. Comput. 18, 35–39 (2017)
L. Zhang, F. Yang, Y. Daniel Zhang, Y.J. Zhu, Road crack detection using deep convolutional neural network, in International Conference on Image Processing (ICIP), 2016, pp. 3708–3712
M.D. Jenkins, T.A. Carr, M.I. Iglesias, T. Buggy, G. Morison, A deep convolutional neural network for semantic pixel-wise segmentation of road and pavement surface cracks, in 2018 26th European Signal Processing Conference (EUSIPCO) (2018), pp. 2134–2138
T.A. Carr, M.D. Jenkins, M.I. Iglesias, T. Buggy, G. Morison, Road crack detection using a single stage detector based deep neural network, in EESMS 2018—Environ. Environmental, Energy, and Structural Monitoring Systems Proceedings, pp. 1–5, 2018
S. Wu, S. Zhong, Y. Liu, Deep residual learning for image steganalysis, Multimed. Tools Appl. 2017, pp. 1–17
H. Maeda, Y. Sekimoto, T. Seto, T. Kashiyama, H. Omata, Road damage detection using deep neural networks with images captured through a smartphone, 2018, pp. 4–6
J. Guo, S. Gould, Deep CNN Ensemble with Data Augmentation for Object Detection, 2015
G. Antipov, S.A. Berrani, J.L. Dugelay, Minimalistic CNN-based ensemble model for gender prediction from face images. Pattern Recognit. Lett. 70, 59–65 (2016)
R. Rasti, M. Teshnehlab, S.L. Phung, Breast cancer diagnosis in DCE-MRI using mixture ensemble of convolutional neural networks. Pattern Recognit. 72(November), 381–390 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Augustauskas, R., Lipnickas, A. (2020). Aggregation of Pixel-Wise U-Net Deep Neural Networks for Road Pavement Defects Detection. In: Nagar, A., Deep, K., Bansal, J., Das, K. (eds) Soft Computing for Problem Solving 2019 . Advances in Intelligent Systems and Computing, vol 1138. Springer, Singapore. https://doi.org/10.1007/978-981-15-3290-0_9
Download citation
DOI: https://doi.org/10.1007/978-981-15-3290-0_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3289-4
Online ISBN: 978-981-15-3290-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)