An Enhanced Lightweight Network for Road Damage Detection Based on Deep Learning
Abstract
:1. Introduction
- A novel and enhanced lightweight network, E-EfficientDet, is proposed, and its performance can be evaluated by the road damage dataset published by the Global Road Damage Detection Challenge 2020. The experimental results can verify the effectiveness of the method proposed in this paper.
- An asymmetric convolution (ABC) is introduced, and a FEEM is designed to increase the receptive field and improve the feature representation capability of the network, which can consequently extract richer multi-scale feature information.
- Based on the idea of semi-dense connectivity, a feature pyramid module is proposed that is more suitable for road surface damage detection and more effectively incorporates multi-scale contextual semantic information.
2. Materials and Methods
2.1. Asymmetric Convolutional Block (ACB)
2.2. Feature Extraction Enhancement Module (FEEM)
2.3. A Feature Pyramid Module More Suitable for Road Surface Damage Detection
2.4. Compound Scaling
2.5. Loss Function
3. Results
3.1. Datasets and Evaluation Metrics
3.2. Implementation Details
3.3. Ablation Studies
3.4. Comparison Experiments
3.5. Visual Analysis Results of Different Models
4. Conclusions
Author Contributions
Funding
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Oliveira, H.; Correia, P.L. CrackIT—An image processing toolbox for crack detection and characterization. In Proceedings of the IEEE International Conference on Image Processing, Paris, France, 27–30 October 2014; pp. 798–802. [Google Scholar]
- Cai, Y.; Zhang, Y. Research on pavement crack recognition methods based on image processing. In Proceedings of the Third International Conference on Digital Image Processing, Chengdu, China, 8 July 2011. [Google Scholar]
- Chambon, S.; Moliard, J. Automatic Road Pavement Assessment with Image Processing: Review and Comparison. Int. J. Geophys. 2011, 2011, 989354. [Google Scholar] [CrossRef] [Green Version]
- Subirats, P.; Dumoulin, J.; Legeay, V.; Barba, D. Automation of pavement surface crack detection using the continuous wavelet transform. In Proceedings of the International Conference on Image Processing, Atlanta, GA, USA, 8–11 October 2006; pp. 3037–3040. [Google Scholar]
- Sun, L.; Qian, Z.D. Multi-scale wavelet transform filtering of non-uniform pavement surface image background for automated pavement distress identification. Measurement 2016, 86, 26–40. [Google Scholar] [CrossRef] [Green Version]
- Kamaliardakani, M.; Sun, L.; Ardakani, M.K. Sealed-crack detection algorithm using heuristic thresholding approach. J. Comput. Civil. Eng. 2014, 30, 04014110. [Google Scholar] [CrossRef]
- He, Y.; Qiu, H. A method of cracks image segmentation based on the means of multiple thresholds. J. Commun. Comput. 2012, 9, 1147–1151. [Google Scholar]
- Girshick, R.; Donahue, J.; Darrell, T.; Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 24–27 June 2014; pp. 580–587. [Google Scholar]
- Ren, S.; He, K.; Girshick, R.; Sun, J. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE. T. Pattern. Anal. 2017, 39, 1137–1149. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Dai, J.; Li, Y.; He, K.; Sun, J. R-FCN: Object detection via region-based fully convolutional networks. In Advances in Neural Information Processing Systems; Curran Associates Inc.: San Francisco, CA, USA, 2016; pp. 379–387. [Google Scholar]
- 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]
- Xu, X.; Zhao, M.; Shi, P.; Ren, R.; He, X.; Wei, X.; Yang, H. Crack Detection and Comparison Study Based on Faster R-CNN and Mask R-CNN. Sensors 2022, 22, 1215. [Google Scholar] [CrossRef]
- He, Y.; Jin, Z.; Zhang, J.; Teng, S.; Chen, G.; Sun, X.; Cui, F. Pavement Surface Defect Detection Using Mask Region-Based Convolutional Neural Networks and Transfer Learning. Appl. Sci. 2022, 12, 7364. [Google Scholar] [CrossRef]
- Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.Y.; Berg, A.C. SSD: Single shot multibox detector. In Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands, 8–16 October 2016; Springer: Berlin, Germany, 2016; pp. 21–37. [Google Scholar]
- Redmon, J.; Divvala, S.; Girshick, R.; Farhadi, A. You only look once: Unified, real-time object detection. In Proceedings of the Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 779–788. [Google Scholar]
- Redmon, J.; Farhadi, A. YOLO9000: Better, faster, stronger. In Proceedings of the Conference on ComputerVision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 7263–7271. [Google Scholar]
- Redmon, J.; Farhadi, A. Yolov3: An incremental improvement. arXiv 2018, arXiv:1804.02767. [Google Scholar]
- Lin, T.Y.; Goyal, P.; Girshick, R.; He, K.; Dollár, P. Focal loss for dense object detection. In Proceedings of the International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2980–2988. [Google Scholar]
- Lu, G.; He, X.; Wang, Q.; Shao, F.; Wang, J.; Jiang, Q. Bridge crack detection based on improved single shot multi-box detector. PLoS ONE 2022, 17, e0275538. [Google Scholar] [CrossRef]
- Suong, L.K.; Jangwoo, K. Detection of potholes using a deep convolutional neural network. J. Univers. Comput. Sci. 2018, 24, 244–1257. [Google Scholar]
- Cao, M.T.; Tran, Q.V.; Nguyen, N.M.; Chang, K.T. Survey on performance of deep learning models for detecting road damages using multiple dashcam image resources. Adv. Eng. Inform. 2020, 46, 101182. [Google Scholar] [CrossRef]
- Qu, Z.; Cao, C.; Liu, L.; Zhou, D.Y. A Deeply Supervised Convolutional Neural Network for Pavement Crack Detection with Multiscale Feature Fusion. IEEE Trans. Neural Netw. Learn. Syst. 2021, 33, 4890–4899. [Google Scholar] [CrossRef] [PubMed]
- Qu, Z.; Wang, C.Y.; Wang, S.Y.; Ju, R.F. A Method of Hierarchical Feature Fusion and Connected Attention Architecture for Pavement Crack Detection. IEEE Trans. Intell. Transp. 2022, 23, 16038–16047. [Google Scholar] [CrossRef]
- Wang, W.; Su, C. Deep Learning-Based Real-Time Crack Segmentation for Pavement Images. KSCE. J. Civ. Eng. 2021, 25, 4495–4506. [Google Scholar] [CrossRef]
- Guo, G.; Zhang, Z. Road damage detection algorithm for improved YOLOv5. Sci. Rep. 2022, 12, 15523. [Google Scholar] [CrossRef]
- Yu, Z.; Shen, Y.; Shen, C. A real-time detection approach for bridge cracks based on YOLOv4-FPM. Autom. Construct. 2021, 122, 103514. [Google Scholar] [CrossRef]
- Tan, M.; Pang, R.; Le, Q.V. Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 10778–10787. [Google Scholar]
- Ding, X.; Guo, Y.; Ding, G.; Han, J.G. ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea, 27 October–2 November 2019; pp. 1911–1920. [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. 2018, 40, 838–848. [Google Scholar] [CrossRef] [Green Version]
- Zhang, L.; Zhang, L.; Zhu, W. Target Detection Based on Edge-Aware and Cross-Coupling Attention for SAR Images. IEEE Geosci. Remote Sens. Lett. 2022, 19, 4501805. [Google Scholar] [CrossRef]
- Mandal, V.; Mussah, A.R.; Adu-Gyamfi, Y. Deep Learning Frameworks for Pavement Distress Classification: A Comparative Analysis. In Proceedings of the IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA, 10–13 December 2020; pp. 5577–5583. [Google Scholar]
- Arya, D.; Maeda, H.; Ghosh, S.K.; Toshniwal, D.; Mraz, A.; Kashiyama, T.; Sekimoto, Y. Transfer Learning-based Road Damage Detection for Multiple Countries. arXiv 2020, arXiv:2008.13101. [Google Scholar]
- Naddaf-Sh, S.; Naddaf-Sh, M.M.; Kashanipour, A.R.; Zargarzadeh, H. An Efficient and Scalable Deep Learning Approach for Road Damage Detection. In Proceedings of the IEEE International Conference on Big Data (Big Data), Atlanta, GA, USA, 10–13 December 2020; pp. 5602–5608. [Google Scholar]
- Kingma, D.; Ba, J. Adam: A Method for Stochastic Optimization. arXiv 2014, arXiv:1412.6980. [Google Scholar]
- Bochkovskiy, A.; Wang, C.-Y.; Liao, H.-Y.M. Yolov4: Optimal speed and accuracy of object detection. arXiv 2020, arXiv:2004.10934. [Google Scholar]
- YOLOv5 SOTA Realtime Instance Segmentation. Available online: https://github.com/ultralytics/yolov5 (accessed on 22 November 2022).
- Wang, C.-Y.; Bochkovskiy, A.; Liao, H.-Y.M. YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. arXiv 2022, arXiv:2207.02696. [Google Scholar]
Model | Input Size | Backbone Network | LC-BiFPN | Box/Class #Layers | |
---|---|---|---|---|---|
#Channels | #Layers | ||||
E-EfficientDet-D0 ( = 0) | 512 × 512 | EfficientNet-B0 | 64 | 3 | 3 |
E-EfficientDet-D1 ( = 1) | 640 × 640 | EfficientNet-B1 | 88 | 4 | 3 |
E-EfficientDet-D2 ( = 2) | 768 × 768 | EfficientNet-B2 | 112 | 5 | 3 |
Train | Validation | Test | Total |
---|---|---|---|
8505 | 945 | 1050 | 10,500 |
Model | D00 | D20 | D40 | mAP | F1-Score |
---|---|---|---|---|---|
EfficientNet-B0 + BiFPN | 33.89 | 67.39 | 50.85 | 50.71 | 46.00 |
EfficientNet-B0 + FPN-A | 32.97 | 68.23 | 50.42 | 50.54 | 44.67 |
EfficientNet-B0 + FPN-B | 34.02 | 69.86 | 51.66 | 51.85 | 46.00 |
EfficientNet-B0 + FPN-C | 34.49 | 69.28 | 50.88 | 51.55 | 47.33 |
EfficientNet-B0 + LC-BiFPN | 35.05 | 70.61 | 51.32 | 52.33 | 46.67 |
EfficientNet-B0 + LC-BiFPN + FEEM | 35.65 | 70.93 | 52.79 | 53.12 | 47.33 |
Model | D00 | D20 | D40 | mAP | F1-Score | FPS | Model Size |
---|---|---|---|---|---|---|---|
Faster R-CNN | 38.61 | 66.98 | 41.38 | 48.99 | 41.00 | 10.68 | 108.20 |
YOLOv3 | 42.97 | 61.86 | 51.56 | 52.23 | 37.33 | 39.48 | 235.02 |
YOLOv4 | 45.55 | 67.55 | 52.99 | 55.36 | 52.33 | 35.09 | 244.34 |
SSD | 36.84 | 65.06 | 50.39 | 50.76 | 42.33 | 41.56 | 91.62 |
RetinaNet | 33.68 | 67.74 | 58.29 | 53.24 | 51.67 | 24.38 | 139.02 |
EfficientDet-D0 | 33.89 | 67.39 | 50.85 | 50.71 | 46.00 | 28.44 | 14.95 |
YOLOv5s | 42.52 | 61.77 | 50.59 | 51.63 | 35.33 | 62.54 | 27.11 |
MobileNetv2-YOLOv4 | 41.07 | 63.53 | 49.33 | 51.31 | 43.33 | 56.50 | 46.49 |
MobileNetv3-YOLOv4 | 38.48 | 61.86 | 54.19 | 51.51 | 44.00 | 45.52 | 53.17 |
YOLOv4-tiny | 39.87 | 57.77 | 44.59 | 47.41 | 42.33 | 135.31 | 22.47 |
YOLOv7-tiny | 39.87 | 60.88 | 53.26 | 51.34 | 33.00 | 102.34 | 23.09 |
E-EfficientDet-D0 (Ours) | 35.65 | 70.93 | 52.79 | 53.12 | 47.33 | 27.08 | 32.31 |
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. |
© 2023 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
Luo, H.; Li, C.; Wu, M.; Cai, L. An Enhanced Lightweight Network for Road Damage Detection Based on Deep Learning. Electronics 2023, 12, 2583. https://doi.org/10.3390/electronics12122583
Luo H, Li C, Wu M, Cai L. An Enhanced Lightweight Network for Road Damage Detection Based on Deep Learning. Electronics. 2023; 12(12):2583. https://doi.org/10.3390/electronics12122583
Chicago/Turabian StyleLuo, Hui, Chenbiao Li, Mingquan Wu, and Lianming Cai. 2023. "An Enhanced Lightweight Network for Road Damage Detection Based on Deep Learning" Electronics 12, no. 12: 2583. https://doi.org/10.3390/electronics12122583