Evaluating the Impact of Feature Extraction and Clustering Techniques in Highway Guardrail Classification
Abstract
This paper presents an approach for the detection of highway guardrails using camera-based systems and advanced machine learning techniques. The proposed methodology combines feature extraction with Convolutional Neural Networks (CNN), specifically MobileNetV2, ResNet18, and VGG16, and clustering algorithms applied to these features. The effectiveness of the models is evaluated through clustering and classification metrics, with a particular emphasis on using the Gaussian Mixture Model (GMM) for forming more cohesive and well-separated clusters compared to K-means. The results indicate that the combination of ResNet18 with GMM provides high accuracy in distinguishing between concrete and metal guardrails, outperforming other tested combinations. This study contributes to the advancement of automatic guardrail detection on highways, providing insights for applications in road asset management.
Keywords:
Clustering, Representation Learning, Object Detection, Road Management
References
J. Wang, T. Zhang, Y. Cheng, and N. Al-Nabhan, “Deep learning for object detection: A survey,” Computer Systems Science and Engineering, vol. 38, no. 2, pp. 165–182, 2021.
Y. Pu, J. Sun, N. Tang, and Z. Xu, “Deep expectation-maximization network for unsupervised image segmentation and clustering,” Image and Vision Computing, vol. 135, p. 104717, 2023. DOI: 10.1016/j.imavis.2023.104717
G. H. F. M. Oliveira, L. L. Minku, and A. L. I. Oliveira, “Tackling virtual and real concept drifts: An adaptive gaussian mixture model approach,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 2, pp. 2048–2060, 2023.
N. Gumaelius, “Guardrail detection for landmark-based localization,” 2022.
A. Saxena, M. Prasad, A. Gupta, N. Bharill, O. P. Patel, A. Tiwari, M. J. Er, W. Ding, and C.-T. Lin, “A review of clustering techniques and developments,” Neurocomputing, vol. 267, pp. 664–681, Dec. 2017. DOI: 10.1016/j.neucom.2017.06.053
H. Huang, C. Wang, X. Wei, and Y. Zhou, “Deep image clustering: A survey,” Neurocomputing, vol. 599, p. 128101, 2024. DOI: 10.1016/j.neucom.2024.128101
F. Tian, B. Gao, Q. Cui, E. Chen, and T.-Y. Liu, “Learning deep representations for graph clustering,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 28, no. 1, Jun. 2014. DOI: 10.1609/aaai.v28i1.8916
A. Coates and A. Y. Ng, Learning Feature Representations with K-Means. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012, pp. 561–580.
C. Lang, A. Braun, L. Schillingmann, and A. Valada, On Hyperbolic Embeddings in Object Detection. Springer International Publishing, 2022, pp. 462–476.
H. Zhu and B. Guo, “A beam guardrail detection algorithm using lidar for intelligent vehicle,” in 2018 IEEE 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), 2018, pp. 1398–1402.
T. Kim and B. Song, “Detection and tracking of road barrier based on radar and vision sensor fusion,” Journal of Sensors, vol. 2016, pp. 1–8, 2016.
H. Zhu, F. Chen, and B. Guo, “Joint beam guardrail detection and tracking by lidar for real-time applications,” in 2019 Chinese Automation Congress (CAC). IEEE, Nov. 2019.
A. Elamin and A. El-Rabbany, “UAV-based image and lidar fusion for pavement crack segmentation,” Sensors, vol. 23, no. 23, 2023.
G. Jocher, A. Chaurasia, J. Qiu, C. Fang et al., “YOLOv8n: A light-weight object detection model,” Ultralytics Documentation, 2023. Available at [link].
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2015.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” 2019.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2015.
A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpft, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, “PyTorch: An imperative style, high-performance deep learning library,” 2019.
K. Gonzalez and S. Misra, “Unsupervised learning monitors the carbon-dioxide plume in the subsurface carbon storage reservoir,” Expert Systems with Applications, vol. 201, p. 117216, 2022.
M. E. Ferrão, P. Prata, and P. Fazendeiro, “Utility-driven assessment of anonymized data via clustering,” Scientific Data, vol. 9, no. 1, Jul. 2022.
C. C. Rakowski and T. Bourlai, “On enhancing crack semantic segmentation using StyleGAN and Brownian bridge diffusion,” IEEE Access, vol. 12, pp. 34 769–34 784, 2024.
Z. Xie, Z. Zhang, Y. Cao, Y. Lin, J. Bao, Z. Yao, Q. Dai, and H. Hu, “SimMIM: A simple framework for masked image modeling,” 2022.
H. Jin, Z. Lan, and X. He, “On highway guardrail detection algorithm based on Mask R-CNN in complex environments,” in 2021 7th International Conference on Systems and Informatics (ICSAI), 2021, pp. 1–6.
Y. Pu, J. Sun, N. Tang, and Z. Xu, “Deep expectation-maximization network for unsupervised image segmentation and clustering,” Image and Vision Computing, vol. 135, p. 104717, 2023. DOI: 10.1016/j.imavis.2023.104717
G. H. F. M. Oliveira, L. L. Minku, and A. L. I. Oliveira, “Tackling virtual and real concept drifts: An adaptive gaussian mixture model approach,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 2, pp. 2048–2060, 2023.
N. Gumaelius, “Guardrail detection for landmark-based localization,” 2022.
A. Saxena, M. Prasad, A. Gupta, N. Bharill, O. P. Patel, A. Tiwari, M. J. Er, W. Ding, and C.-T. Lin, “A review of clustering techniques and developments,” Neurocomputing, vol. 267, pp. 664–681, Dec. 2017. DOI: 10.1016/j.neucom.2017.06.053
H. Huang, C. Wang, X. Wei, and Y. Zhou, “Deep image clustering: A survey,” Neurocomputing, vol. 599, p. 128101, 2024. DOI: 10.1016/j.neucom.2024.128101
F. Tian, B. Gao, Q. Cui, E. Chen, and T.-Y. Liu, “Learning deep representations for graph clustering,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 28, no. 1, Jun. 2014. DOI: 10.1609/aaai.v28i1.8916
A. Coates and A. Y. Ng, Learning Feature Representations with K-Means. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012, pp. 561–580.
C. Lang, A. Braun, L. Schillingmann, and A. Valada, On Hyperbolic Embeddings in Object Detection. Springer International Publishing, 2022, pp. 462–476.
H. Zhu and B. Guo, “A beam guardrail detection algorithm using lidar for intelligent vehicle,” in 2018 IEEE 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), 2018, pp. 1398–1402.
T. Kim and B. Song, “Detection and tracking of road barrier based on radar and vision sensor fusion,” Journal of Sensors, vol. 2016, pp. 1–8, 2016.
H. Zhu, F. Chen, and B. Guo, “Joint beam guardrail detection and tracking by lidar for real-time applications,” in 2019 Chinese Automation Congress (CAC). IEEE, Nov. 2019.
A. Elamin and A. El-Rabbany, “UAV-based image and lidar fusion for pavement crack segmentation,” Sensors, vol. 23, no. 23, 2023.
G. Jocher, A. Chaurasia, J. Qiu, C. Fang et al., “YOLOv8n: A light-weight object detection model,” Ultralytics Documentation, 2023. Available at [link].
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 2015.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” 2019.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” 2015.
A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpft, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, and S. Chintala, “PyTorch: An imperative style, high-performance deep learning library,” 2019.
K. Gonzalez and S. Misra, “Unsupervised learning monitors the carbon-dioxide plume in the subsurface carbon storage reservoir,” Expert Systems with Applications, vol. 201, p. 117216, 2022.
M. E. Ferrão, P. Prata, and P. Fazendeiro, “Utility-driven assessment of anonymized data via clustering,” Scientific Data, vol. 9, no. 1, Jul. 2022.
C. C. Rakowski and T. Bourlai, “On enhancing crack semantic segmentation using StyleGAN and Brownian bridge diffusion,” IEEE Access, vol. 12, pp. 34 769–34 784, 2024.
Z. Xie, Z. Zhang, Y. Cao, Y. Lin, J. Bao, Z. Yao, Q. Dai, and H. Hu, “SimMIM: A simple framework for masked image modeling,” 2022.
H. Jin, Z. Lan, and X. He, “On highway guardrail detection algorithm based on Mask R-CNN in complex environments,” in 2021 7th International Conference on Systems and Informatics (ICSAI), 2021, pp. 1–6.
Published
2024-11-06
How to Cite
MONTEIRO, Luis Flávio Ferreira; BARBOSA, Gabriely; SILVA, Julio Cezar Soares; VENTURA, Thiago Meirelles; TEIXEIRA, Raoni Florentino da Silva.
Evaluating the Impact of Feature Extraction and Clustering Techniques in Highway Guardrail Classification. In: WORKSHOP ON INFORMATION SYSTEMS (WSIS), 15. , 2024, Rio Paranaíba/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 21-27.
DOI: https://doi.org/10.5753/wsis.2024.33667.
