Robust Stereo Matching for Driver Assistance Systems Under Adverse Driving Conditions

Authors

Vinh Dinh Nguyen
FPT University, Can Tho Campus, Vietnam
Nhan Huu Tran
DOI: https://doi.org/10.52549/.v13i4.6686
Download PDF
Published: 21-12-2025 • Issue: Vol. 13 No. 4: December 2025 • Section: Regular paper

Abstract

Deep stereo networks perform effectively when both training and testing data come from the same domain. However, their accuracy tends to drop significantly in efficiency-focused target scenarios due to domain shifts between training and testing datasets. These shifts often arise from differences in factors such as color, lighting, contrast, and texture. Additionally, the architecture of deep networks generally results in processing times that are unsuitable for real-time applications. To address these issues, this paper proposes a lightweight and robust stereo matching approach tailored for diverse driving environments. It leverages attention mechanisms for feature extraction and uses evolutionary algorithms for optimizing parameters. The method outperforms existing deep learning and traditional stereo matching techniques in terms of both processing speed and the percentage of bad pixels, as demonstrated on three challenging outdoor datasets: KITTI, HCI, and Driving Stereo. These results indicate that the proposed solution is highly effective for real-world applications where both precision and flexibility are essential.
Keywords: complex driving condition; adverse weather conditions; depth estimation; deep learning; stereo matching

References

H. Laga, L. V. Jospin, F. Boussaid, and M. Bennamoun, “A survey on deep learning techniques for stereo-based depth estimation,†IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 4, pp. 1738–1764, 2022. [Online]. Available: https://doi.org/10.1109/TPAMI.2020.3032602

F. Tosi, L. Bartolomei, and M. Poggi, “A survey on deep stereo matching in the twenties,†International Journal of Computer Vision, 2025. [Online]. Available: https://doi.org/10.1007/s11263-024-02331-0

J. Li, P. Wang, P. Xiong, T. Cai, Z. Yan, L. Yang, J. Liu, H. Fan, and S. Liu, “Practical stereo matching via cascaded recurrent network with adaptive correlation,†in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 16 242–16 251. [Online]. Available: https://doi.org/10.1109/CVPR52688.2022.01578

W. Zhong, Y. Yuan, X. Ye, D. Zheng, and R. Xu, “Underwater stereo matching via unsupervised appearance and feature adaptation networks,†pp. 2295–2299, 2022. [Online]. Available: https://doi.org/10.1109/ICASSP43922.2022.9746701

H. Dai, X. Zhang, Y. Zhao, H. Sun, and N. Zheng, “Adaptive disparity candidates prediction network for efficient real-time stereo matching,†IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 5, pp. 3099–3110, 2022. [Online]. Available: https://doi.org/10.1109/TCSVT.2021.3102109

X. Lai, Y. Zhang, and Z. Li, “An improved stereo matching algorithm based on joint similarity measure and adaptive weights,†Applied Sciences, vol. 13, no. 1, p. 514, 2023. [Online]. Available: https://doi.org/10.3390/app13010514

G. Xu, X. Wang, X. Ding, and X. Yang, “Iterative geometry encoding volume for stereo matching,†in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 21 919–21 928. [Online]. Available: https://doi.org/10.1109/CVPR52729.2023.02099

X. Wang, G. Xu, H. Jia, and X. Yang, “Selective-stereo: Adaptive frequency information selection for stereo matching,†in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2024, pp. 19 701–19 710. [Online]. Available: https://doi.org/10.1109/CVPR52733.2024.01863

K. Li, L. Wang, Y. Zhang, K. Xue, S. Zhou, and Y. Guo, “Los: Local structure-guided stereo matching,†in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 19 746–19 756. [Online]. Available: https://doi.org/10.1109/CVPR52733.2024.01867

Z. Cheng, J. Yang, and H. Li, “Stereo matching in time: 100+ fps video stereo matching for extended reality,†in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Waikoloa, HI, USA: IEEE, 2024, pp. 8704–8713. [Online]. Available: https: //doi.org/10.1109/WACV57701.2024.00852

X. Yue et al., “Semi-stereo: A universal stereo matching framework for imperfect data via semi-supervised learning,†in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Seattle, WA, USA: IEEE, 2024, pp. 646–655. [Online]. Available: https://doi.org/10.1109/CVPRW63382.2024.00069

O.-H. Kwon and E. Zell, “Image-coupled volume propagation for stereo matching,†in 2023 IEEE International Conference on Image Processing (ICIP). Kuala Lumpur, Malaysia: IEEE, 2023, pp. 2510–2514. [Online]. Available: https://doi.org/10.1109/ICIP49359.2023.10222247

J. Song, Q. Zhu, J. Lin, and M. Ghaffari, “BDIS: Bayesian Dense Inverse Searching Method for Real-Time Stereo Surgical Image Matching,†IEEE Transactions on Robotics, vol. 39, no. 2, pp. 1388–1406, Apr. 2023. [Online]. Available: https://doi.org/10.1109/TRO.2022.3215018

Z. Quan, B. Wu, and L. Luo, “An image stereo matching algorithm with multi-spectral attention mechanism,†Sensors, vol. 23, no. 19, p. 8179, 2023. [Online]. Available: https: //doi.org/10.3390/s23198179

Y. Zhang, M. Poggi, and S. Mattoccia, “Temporalstereo: Efficient spatial-temporal stereo matching network,†in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Detroit, MI, USA: IEEE, 2023, pp. 9528–9535. [Online]. Available: https: //doi.org/10.1109/IROS55552.2023.10341598

W. Gao, Y. Cai, Y. Akoudad, Y. Yang, and J. Chen, “Ma-stereo: Real-time stereo matching via multi-scale attention fusion and spatial error-aware refinement,†IEEE Robotics and Automation Letters, vol. 9, no. 11, pp. 9954–9961, Nov. 2024. [Online]. Available: https://doi.org/10.1109/LRA.2024.3468173

X. Ye, J. Li, H. Wang, H. Huang, and X. Zhang, “Efficient stereo matching leveraging deep local and context information,†IEEE Access, vol. 5, pp. 18 745–18 755, 2017. [Online]. Available: https://doi.org/10.1109/ACCESS.2017.2754318

B. Zhang, X. Wu, S. Liu, and W. Wan, “A fast stereo matching network based on multiscale feature fusion,†in 2024 IEEE 7th International Conference on Electronic Information and Communication Technology (ICEICT). Xi’an, China: IEEE, 2024, pp. 491–496. [Online]. Available: https://doi.org/10.1109/ICEICT61637.2024.10670969

X. Yang, L. He, Y. Zhao, H. Sang, Z. L. Yang, and X. J. Cheng, “Multi-attention network for stereo matching,†IEEE Access, vol. 8, pp. 113 371–113 382, 2020. [Online]. Available: https://doi.org/10.1109/ACCESS.2020.3003375

X. Wang, J. Yu, Z. Sun, J. Sun, and Y. Su, “Multi-scale graph neural network for global stereo matching,†Signal Processing: Image Communication, vol. 118, p. 117026, 2023. [Online]. Available: https://doi.org/10.1016/j.image.2023.117026

H. Xu and J. Zhang, “Aanet: Adaptive aggregation network for efficient stereo matching,†in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, WA, USA: IEEE, 2020, pp. 1956–1965. [Online]. Available: https://doi.org/10.1109/CVPR42600.2020.00203

X. Su, S. Liu, R. Li, Z. Bing, and A. Knoll, “Efficient stereo matching using swin transformer and multilevel feature consistency in autonomous mobile systems,†IEEE Transactions on Industrial Informatics, vol. 20, no. 5, pp. 7957–7965, May 2024. [Online]. Available: https://doi.org/10.1109/TII.2024.3367033

X. Yang, Y. Zhao, Z. Feng, H. Sang, Z. Zhang, G. Zhang, and L. He, “A light-weight stereo matching network based on multi-scale features fusion and robust disparity refinement,†IET Image Processing, vol. 17, pp. 1797–1811, 2023. [Online]. Available: https://doi.org/10.1049/ipr2.12756

J. Qi and L. Liu, “The stereo matching algorithm based on an improved adaptive support window,†IET Image Processing, vol. 16, no. 10, pp. 2803–2816, Oct 2022. [Online]. Available: https://doi.org/10.1049/ipr2.1234567

Y. Zhang, X. Li, and Z. Li, “Lidar-guided stereo matching with a spatial consistency constraint,†arXiv preprint arXiv:2202.09953, 2022. [Online]. Available: https://doi.org/10.48550/arXiv.2202.09953

S. Yang, H. Chen, and W. Chen, “Generalized stereo matching method based on iterative optimization of hierarchical graph structure consistency cost,†Remote Sensing, vol. 15, no. 9, p. 2369, 2023. [Online]. Available: https://doi.org/10.3390/rs15092369

W. Iqbal, J. A. Paffenholz, and M. Mehltretter, “Guiding deep learning with expert knowledge for dense stereo matching,†PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science, vol. 91, pp. 365–380, 2023. [Online]. Available: https://doi.org/10.1007/s41064-023-00252-0

H. Laga, L. V. Jospin, F. Boussaid, and M. Bennamoun, “A survey on deep learning techniques for stereo-based depth estimation,†IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 4, pp. 1738–1764, Apr. 2022. [Online]. Available: https://doi.org/10.1109/TPAMI.2020.3032602

G. Suh, J. Lim, S. Jeong, and T. Park, “A real-time design of stereo vision system using disparity calibration,†in 2024 Fifteenth International Conference on Ubiquitous and Future Networks (ICUFN). Budapest, Hungary: IEEE, 2024, pp. 532–537. [Online]. Available: https://doi.org/10.1109/ICUFN61752.2024.10625225

H. Wenbin and S. Kamata, “Unsupervised learning for stereo depth estimation using efficient correspondence matching,†in Proceedings of the 5th International Conference on Advanced Image Processing (ICAIP ’21). New York, NY, USA: ACM, 2022, pp. 30–34. [Online]. Available: https://doi.org/10.1145/3502827.3502828

K. Wegner and O. Stankiewicz, “Depth estimation using modified cost function for occlusion handling,†Signal, Image and Video Processing, vol. 13, pp. 1539–1547, 2019. [Online]. Available: https://doi.org/10.1007/s11760-019-01487-4

A. D. Pon, J. Ku, C. Li, and S. L. Waslander, “Object-centric stereo matching for 3d object detection,†in 2020 IEEE International Conference on Robotics and Automation (ICRA). Paris, France: IEEE, 2020, pp. 8383–8389. [Online]. Available: https://doi.org/10.1007/s11760-019-01487-4

S. Jeon and Y. S. Heo, “Efficient multi-scale stereo-matching network using adaptive cost volume filtering,†Sensors, vol. 22, no. 15, p. 5500, 2022. [Online]. Available: https://doi.org/10.3390/s22155500

E.-T. Baek and H. J. Yang, “Cost aggregation for stereo matching using total generalized variation with fusion tensor,†IEEE Access, vol. 7, pp. 134 505–134 513, 2019. [Online]. Available: https://doi.org/10.1109/ACCESS.2019.2941215

H. Liu et al., “Stereo matching algorithm based on two-phase adaptive optimization of adcensus and gradient fusion,†in 2021 IEEE International Conference on Real-time Computing and Robotics (RCAR). Xining, China: IEEE, 2021, pp. 726–731. [Online]. Available: https: //doi.org/10.1109/RCAR52367.2021.9517511

W. Chen, H. Chen, and S. Yang, “Self-supervised stereo matching method based on srwp and pcam for urban satellite images,†Remote Sensing, vol. 14, no. 7, p. 1636, 2022. [Online]. Available: https://doi.org/10.3390/rs14071636

B. Liu, K. Chen, S.-L. Peng, and M. Zhao, “Adaptive aggregate stereo matching network with depth map super-resolution,†Sensors, vol. 22, no. 12, p. 4548, 2022. [Online]. Available: https://doi.org/10.3390/s22124548

S. Meister, B. Jahne, and D. Kondermann, “A stereo camera system for the generation of real-world ¨ benchmark datasets with ground truth,†2011. [Online]. Available: https://doi.org/10.11588/heidok. 00011610

M. Jang, H. Yoon, S. Lee, J. Kang, and S. Lee, “A comparison and evaluation of stereo matching on active stereo images,†Sensors, vol. 22, no. 9, p. 3332, May 2022. [Online]. Available: https://doi.org/10.3390/s22093332

M. J. A. Dujaili, “Survey on facial expressions recognition: Databases, features, and classification schemes,†Multimedia Tools and Applications, vol. 83, pp. 7457–7478, 2024. [Online]. Available: https://doi.org/10.1007/s11042-023-15139-w

V. D. Nguyen, H. V. Nguyen, and J. W. Jeon, “Robust stereo data cost with a learning strategy,†IEEE Transactions on Intelligent Transportation Systems, vol. 18, no. 2, pp. 248–258, 2017. [Online]. Available: https://doi.org/10.1109/TITS.2016.2563661

V. D. Nguyen, T. T. Nguyen, D. D. Nguyen, S. J. Lee, and J. W. Jeon, “A fast evolutionary algorithm for real-time vehicle detection,†IEEE Transactions on Vehicular Technology, vol. 62, no. 6, pp. 2453–2468, Jul 2013. [Online]. Available: https://doi.org/10.1109/TVT.2013.224291

G. Yang, X. Song, C. Huang, Z. Deng, J. Shi, and B. Zhou, “Drivingstereo: A large-scale dataset for stereo matching in autonomous driving scenarios,†in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 899–908. [Online]. Available: https://doi.org/10.1109/CVPR.2019.00099

A. Geiger, P. Lenz, and R. Urtasun, “Are we ready for autonomous driving? the kitti vision benchmark suite,†in 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 3354–3361. [Online]. Available: https://doi.org/10.1109/CVPR.2012.6248074

C. Deng, D. Liu, H. Zhang, J. Li, and B. Shi, “Semi-global stereo matching algorithm based on multi-scale information fusion,†Applied Sciences, vol. 13, no. 2, p. 1027, Jan 2023. [Online]. Available: https://doi.org/10.3390/app13021027

I. Firmansyah, B. Setiadi, R. Indrawijaya, A. S. Satyawan, D. Kurniawan, and A. A. Waskita, “An efficient hardware implementation of fpga-based stereo matching using a single path sgm direction,†pp. 400–404, 2024. [Online]. Available: https://doi.org/10.1109/IC3INA64086.2024.10732374

V. Q. Dinh, P. H. Nguyen, and V. D. Nguyen, “Feature engineering and deep learning for stereo matching under adverse driving conditions,†IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 7, pp. 7855–7865, Jul 2022. [Online]. Available: https://doi.org/10.1109/TITS.2021.3073557

P.-A. Rousseau and S. Roy, “A permutation model for the self-supervised stereo matching problem,†pp. 122–131, 2022. [Online]. Available: https://doi.org/10.1109/CRV55824.2022.0002

X. Fan, S. Jeon, and B. Fidan, “Occlusion-aware self-supervised stereo matching with confidence guided raw disparity fusion,†in 2022 19th Conference on Robots and Vision (CRV), 2022, pp. 132–139. [Online]. Available: https://doi.org/10.1109/CRV55824.2022.00025

H. Morimitsu, X. Zhu, R. M. Cesar, X. Ji, and X.-C. Yin, “Rapidflow: Recurrent adaptable pyramids with iterative decoding for efficient optical flow estimation,†pp. 2946–2952, 2024. [Online]. Available: https://doi.org/10.1109/ICRA57147.2024.10610277

Author Biographies

Vinh Dinh Nguyen

How to Cite

[1]
V. D. Nguyen and N. H. Tran, “Robust Stereo Matching for Driver Assistance Systems Under Adverse Driving Conditions”, IJEEI, vol. 13, no. 4, pp. 1050–1064, Dec. 2025, doi: 10.52549/.v13i4.6686.