A Novel Hybrid Feature Optimization Framework for Road Surface Identification with Vision Transformer and EGWO-SVM
Received: 25 November 2025 | Revised: 16 December 2025 and 4 January 2026 | Accepted: 6 January 2026 | Online: 15 January 2026
Corresponding author: Ramya Krishna Rajavolu
Abstract
Accurate identification of road surface conditions is essential for autonomous driving, Intelligent Transportation Systems (ITS), and driver-assist technologies. This paper proposes an integrated hybrid framework that combines multi-resolution texture decomposition, attention-based deep learning, handcrafted statistical descriptors, and evolutionary feature optimization. The approach begins by applying Stationary Wavelet Transform (SWT) to extract stable texture characteristics from road images. A Vision Transformer enhanced with Squeeze-and-Excitation (ViT-SE) blocks captures global spatial relationships, whereas Gray-Level Co-Occurrence Matrix (GLCM) descriptors contribute fine-grained statistical features. These complementary features are filtered using Mutual Information (MI) and optimized using Enhanced Grey Wolf Optimization (EGWO), enabling compact and discriminative feature selection. The optimized feature subset is classified using a Support Vector Machine (SVM). Experiments conducted on a multi-class road surface dataset demonstrate that the proposed SWT–ViT-SE–GLCM–MI–EGWO–SVM pipeline achieves 99.52% accuracy, outperforming state-of-the-art Convolutional Neural Network (CNN), Transformer, and hybrid models. The results confirm the synergy of multi-domain features and metaheuristic optimization in real-time road condition assessment applications.
Keywords:
road surface classification, Vision Transformer (ViT), Stationary Wavelet Transform (SWT), Gray-Level Co-Occurrence Matrix (GLCM), Mutual Information (MI), Enhanced Grey Wolf Optimization (EGWO), Support Vector Machine (SVM)Downloads
References
E. Asadi Shamsabadi, C. Xu, A. S. Rao, T. Nguyen, T. Ngo, and D. Dias-da-Costa, "Vision transformer-based autonomous crack detection on asphalt and concrete surfaces," Automation in Construction, vol. 140, Aug. 2022, Art. no. 104316. DOI: https://doi.org/10.1016/j.autcon.2022.104316
Y. Chen, X. Gu, Z. Liu, and J. Liang, "A Fast Inference Vision Transformer for Automatic Pavement Image Classification and Its Visual Interpretation Method," Remote Sensing, vol. 14, no. 8, Apr. 2022, Art. no. 1877. DOI: https://doi.org/10.3390/rs14081877
Y. Moroto, K. Maeda, R. Togo, T. Ogawa, and M. Haseyama, "Multimodal Transformer Model Using Time-Series Data to Classify Winter Road Surface Conditions," Sensors, vol. 24, no. 11, May 2024, Art. no. 3440. DOI: https://doi.org/10.3390/s24113440
R. R. Krishna and N. Jyothi, "Road Surface Condition Identification with Deep Neural Networks and SVM Classifier," Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 21998–22003, Apr. 2025. DOI: https://doi.org/10.48084/etasr.10166
R. Shi et al., "CNN‐Transformer for visual‐tactile fusion applied in road recognition of autonomous vehicles," Pattern Recognition Letters, vol. 166, pp. 200–208, Feb. 2023. DOI: https://doi.org/10.1016/j.patrec.2022.11.023
T. Chen, D. Jiang, and R. Li, "Swin Transformers Make Strong Contextual Encoders for VHR Image Road Extraction," in IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia, 2022, pp. 3019–3022. DOI: https://doi.org/10.1109/IGARSS46834.2022.9883628
J. Li, Y. Zhang, P. Yun, G. Zhou, Q. Chen, and R. Fan, "RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsing," IEEE Transactions on Intelligent Vehicles, vol. 9, no. 7, pp. 5163–5172, July 2024. DOI: https://doi.org/10.1109/TIV.2024.3388726
W. H. Abdulsalam, R. H. Ali, S. H. Jadooa, and S. S. Hussein, "Automated Glaucoma Detection Techniques: A Literature Review," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19891–19897, Feb. 2025. DOI: https://doi.org/10.48084/etasr.9316
T. E. Burghardt et al., "Visibility of various road markings for machine vision," Case Studies in Construction Materials, vol. 15, Dec. 2021, Art. no. e00579. DOI: https://doi.org/10.1016/j.cscm.2021.e00579
S. Marianingsih, W. Widodo, M. S. S. Pieter, E. V. Manullang, and H. Y. Nanlohy, "Machine Vision for the Various Road Surface Type Classification Based on Texture Feature," Journal of Mechanical Engineering Science and Technology, vol. 6, no. 1, pp. 40–47, July 2022. DOI: https://doi.org/10.17977/um016v6i12022p040
Robet, C. Juliandy, Andi, Hendri, J. Hendrik, and F. A. Tarigan, "Image Road Surface Classification Based on GLCM Feature Using LGBM Classifier," IOP Conference Series: Earth and Environmental Science, vol. 1083, no. 1, Sept. 2022, Art. no. 012006. DOI: https://doi.org/10.1088/1755-1315/1083/1/012006
J. K. Lee, B. K. Kim, H. Choi, and S. I. Chang, "Road-pavement classification by artificial neural network model based on tire-pavement noise and road-surface image," Applied Acoustics, vol. 225, Nov. 2024, Art. no. 110194. DOI: https://doi.org/10.1016/j.apacoust.2024.110194
I. Aslam and S. Mahfuz, "Transformer-Based Classification of Road Conditions Using Vehicular Sensor Data," Procedia Computer Science, vol. 257, pp. 444–451, Jan. 2025. DOI: https://doi.org/10.1016/j.procs.2025.03.058
S. Huang, H. Chen, L. Yan, X. Zou, B. Li, and Y. Bi, "A review of the progress in machine vision-based crack detection and identification technology for asphalt pavements," Digital Transportation and Safety, vol. 4, no. 1, pp. 65–79, Mar. 2025. DOI: https://doi.org/10.48130/dts-0025-0006
Y. Zhu, T. Cao, and Y. Yang, "A Transformer-Based Pavement Crack Segmentation Model with Local Perception and Auxiliary Convolution Layers," Electronics, vol. 14, no. 14, July 2025, Art. no. 2834. DOI: https://doi.org/10.3390/electronics14142834
S. Matarneh, F. Elghaish, D. J. Edwards, F. P. Rahimian, E. Abdellatef, and O. Ejohwomu, "Automatic crack classification on asphalt pavement surfaces using convolutional neural networks and transfer learning," Journal of Information Technology in Construction, vol. 29, no. 55, pp. 1239–1256, Dec. 2024. DOI: https://doi.org/10.36680/j.itcon.2024.055
M. R. Islam, B. Ahmed, M. A. Hossain, and M. P. Uddin, "Mutual Information-Driven Feature Reduction for Hyperspectral Image Classification," Sensors, vol. 23, no. 2, Jan. 2023, Art. no. 657. DOI: https://doi.org/10.3390/s23020657
G. Li, Y. Cui, and J. Su, "Adaptive mechanism-based grey wolf optimizer for feature selection in high-dimensional classification," Plos One, vol. 20, no. 5, May 2025, Art. no. e0318903. DOI: https://doi.org/10.1371/journal.pone.0318903
Y. Wang, Y. Yin, H. Zhao, J. Liu, C. Xu, and W. Dong, "Grey wolf optimizer with self-repulsion strategy for feature selection," Scientific Reports, vol. 15, no. 1, Apr. 2025, Art. no. 12807. DOI: https://doi.org/10.1038/s41598-025-97224-8
A. Dede et al., "Wavelet-Based Feature Extraction for Efficient High-Resolution Image Classification," Engineering Reports, vol. 7, no. 2, Feb. 2025, Art. no. e70027. DOI: https://doi.org/10.1002/eng2.70027
F. Li et al., "2D-wavelet based micro and macro texture analysis for asphalt pavement under snow or ice condition," Journal of Infrastructure Preservation and Resilience, vol. 2, no. 1, May 2021, Art. no. 14. DOI: https://doi.org/10.1186/s43065-021-00029-y
Q. Cui, Y. Li, H. Bian, J. Kong, and Y. Dong, "Visual defect recognition with stationary wavelet transform based neural networks," Digital Signal Processing, vol. 158, Mar. 2025, Art. no. 104947. DOI: https://doi.org/10.1016/j.dsp.2024.104947
Y. Xu, C. Zhang, and H. Li, "Transformer-based large vision model for universal structural damage segmentation," Automation in Construction, vol. 176, Aug. 2025, Art. no. 106256. DOI: https://doi.org/10.1016/j.autcon.2025.106256
T. Ahmed, N. Ejaz, and S. Choudhury, "Redefining Real-Time Road Quality Analysis With Vision Transformers on Edge Devices," IEEE Transactions on Artificial Intelligence, vol. 5, no. 10, pp. 4972–4983, Oct. 2024. DOI: https://doi.org/10.1109/TAI.2024.3394797
M. H. Daneshvari, E. Nourmohammadi, M. Ameri, and B. Mojaradi, "Efficient LBP-GLCM texture analysis for asphalt pavement raveling detection using eXtreme Gradient Boost," Construction and Building Materials, vol. 401, Oct. 2023, Art. no. 132731. DOI: https://doi.org/10.1016/j.conbuildmat.2023.132731
M. Yu, J. Xu, W. Liang, Y. Qiu, S. Bao, and L. Tang, "Improved multi-strategy adaptive Grey Wolf Optimization for practical engineering applications and high-dimensional problem solving," Artificial Intelligence Review, vol. 57, no. 10, Sept. 2024, Art. no. 277. DOI: https://doi.org/10.1007/s10462-024-10821-3
T. Zhao and Y. Wei, "A road surface image dataset with detailed annotations for driving assistance applications," Data in Brief, vol. 43, Aug. 2022, Art. no. 108483. DOI: https://doi.org/10.1016/j.dib.2022.108483
Downloads
How to Cite
License
Copyright (c) 2026 Ramya Krishna Rajavolu, Lakshmi Rajeswara Rao Langoju
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
