Skip to main content
SpringerLink
Log in

A feasible region detection method for vehicles in unstructured environments based on PSMNet and improved RANSAC

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Feasible region detection is a critical problem in the field of intelligent driving. To solve the problem that the feasible region of vehicles is difficult to identify in the unstructured environment, a detection method based on the improved Random Sample Consensus (RANSAC) algorithm and Pyramidal Stereo Matching Network (PSMNet) is proposed in this paper. To overcome the influence of the complex environment and weather on the detection results, the 3D point cloud of the detection region is established to restore the actual scene. In contrast to the traditional stereo matching algorithm, the disparity map is obtained by the deep learning method PSMNet. Therefore, the 3D reconstruction of the detection region can be realized more accurately. Subsequently, the method of point cloud selection in RANSAC is redefined by constructing the k-dimensional tree (kd-tree) and using radius space density. Finally, the detection results of the feasible region are obtained by the improved RANSAC. It is tested in a variety of scenarios in complex environments and weather. The results demonstrate the high environmental adaptability and stability of the detection method. And compared with another method Segformer, the comparison results indicate that the method is effective in detecting road scenes under multiple weather conditions.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

References

  1. Alvarez J, Lopez A, Baldrich R (2008) Illuminant-invariant model-based road segmentation. IEEE Intell Veh Symp 2008:952–957. https://doi.org/10.1109/IVS.2008.4621283

    Article  Google Scholar 

  2. Baheti B, Innani S, Gajre S, Talbar S (2020) Semantic scene segmentation in unstructured environment with modified DeepLabV3+. Pattern Recogn Lett 138:223–229. https://doi.org/10.1016/j.patrec.2020.07.029

    Article  Google Scholar 

  3. Bellone M, Messina A, Reina G (2013) A New Approach for Terrain Analysis in Mobile Robot Applications. 2013 IEEE International Conference on Mechatronics (ICM). 225–230. https://doi.org/10.1109/ICMECH.2013.6518540

  4. Bento L, Nunes U, Moita F, Surrecio A (2005) Sensor fusion for precise autonomous vehicle navigation in outdoor semi-structured environments. IEEE Intell Transport Syst Conf (ITSC) 2005:245–250. https://doi.org/10.1109/ITSC.2005.1520055

    Article  Google Scholar 

  5. Chang J, Chen Y (2018) Pyramid stereo matching network. IEEE/CVF Conf Comput Vis Patt Recognit (CVPR) 2018:5410–5418. https://doi.org/10.1109/CVPR.2018.00567

    Article  Google Scholar 

  6. Chen L, Li Q, Li M, Zhang L, Mao Q (2012) Design of a Multi-Sensor Cooperation Travel Environment Perception System for autonomous vehicle. Sens 12:12386–12404. https://doi.org/10.3390/s120912386

    Article  Google Scholar 

  7. Chen A, Gao C, He B, Kim Y, Yarlagadda P (2014) Image Stereo Correspondence Method for Stereo Vision. Sens Meas Intell Mater II, Pts 1 and 2. 475–476:337–41. https://doi.org/10.4028/www.scientific.net/AMM.475-476.337

  8. Chen C, Xiong G, Zhu S, Xu B (2019) Outdoor 3D Environment Reconstruction based on Multi-sensor Fusion for Remote Control. 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC). 1753–7. https://doi.org/10.1109/ITAIC.2019.8785774

  9. Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R et al (2016) The Cityscapes dataset for semantic urban scene understanding. IEEE Conf Comput Vis Pattern Recog (CVPR) 2016:3213–3223. https://doi.org/10.1109/CVPR.2016.350

    Article  Google Scholar 

  10. Gao ZF, Zhang HY, Dong SZ, Sun SH, Wang X, Yang G et al (2020) Salient object detection in the distributed cloud-edge intelligent network. IEEE Netw 34:216–224

    Article  Google Scholar 

  11. Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? The KITTI vision benchmark suite. IEEE Conf Comput Vis Pattern Recogn 2012:3354–3361. https://doi.org/10.1109/CVPR.2012.6248074

    Article  Google Scholar 

  12. Girisha S, Pai MMM, Verma U, Pai RM (2019) Performance analysis of semantic segmentation algorithms for finely annotated new UAV aerial video dataset (ManipalUAVid). IEEE Access 7:136239–136253

    Article  Google Scholar 

  13. Han B, Zhang K, Yu X, Kwon E, Ou J (2011) Nickel particle-based self-sensing pavement for vehicle detection. Measurement. 44:1645–1650. https://doi.org/10.1016/j.measurement.2011.06.014

    Article  Google Scholar 

  14. He P, Gao F, Yarlagadda P (2014) Research on stereo matching algorithm in intelligent vehicle application. Adv Mechatronics Control Eng III(678):35–38. https://doi.org/10.4028/www.scientific.net/AMM.678.35

    Article  Google Scholar 

  15. Jebamikyous HH, Kashef R (2022) Autonomous vehicles perception (AVP) using deep learning: modeling, assessment, and challenges. IEEE Access 10:10523–10535

    Article  Google Scholar 

  16. Kendall A, Martirosyan H, Dasgupta S, Henry P, Kennedy R, Bachrach A et al (2017) End-to-end learning of geometry and context for deep stereo regression. IEEE Int Conf Comput Vis (ICCV) 2017:66–75. https://doi.org/10.1109/ICCV.2017.17

    Article  Google Scholar 

  17. Li Y, Tong G, Sun A, Ding W (2018) Road extraction algorithm based on intrinsic image and vanishing point for unstructured road image. Robot Auton Syst 109:86–96. https://doi.org/10.1016/j.robot.2018.08.011

    Article  Google Scholar 

  18. Li J, Wang H, Zhang L, Wang Z, Wang M (2019) The research of random sample consensus matching algorithm in PCA-SIFT stereo matching method. Chin Control Decis Conf (CCDC) 2019:3338–3341. https://doi.org/10.1109/CCDC.2019.8833239

    Article  Google Scholar 

  19. Magrini M, Moroni D, Palazzese G, Pieri G, Leone G, Salvetti O (2015) Computer Vision on Embedded Sensors for Traffic Flow Monitoring. 2015 IEEE 18th International Conference on Intelligent Transportation Systems. 161–6. https://doi.org/10.1109/ITSC.2015.35

  20. Melo J, Naftel A, Bernardino A, Santos-Victor J (2006) Detection and classification of highway lanes using vehicle motion trajectories. IEEE Trans Intell Transp Syst 7:188–200. https://doi.org/10.1109/TITS.2006.874706

    Article  Google Scholar 

  21. Niskanen I, Immonen M, Hallman L, Yamamuchi G, Mikkonen M, Hashimoto T et al (2021) Time-of-flight sensor for getting shape model of automobiles toward digital 3D imaging approach of autonomous driving. Autom Constr:121. https://doi.org/10.1016/j.autcon.2020.103429

  22. Pang J, Sun W, Ren J, Yang C, Yan Q (2017) Cascade residual learning: a two-stage convolutional neural network for stereo matching. IEEE Int Conf Comput Vis Workshops (ICCVW) 2017:878–886. https://doi.org/10.1109/ICCVW.2017.108

    Article  Google Scholar 

  23. Scharstein D, Szeliski R (2002) A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int J Comput Vis 47:7–42. https://doi.org/10.1023/A:1014573219977

    Article  MATH  Google Scholar 

  24. Sun L, Zhao C, Yan Z, Liu PC, Duckett T, Stolkin R (2019) A novel weakly-supervised approach for RGB-D-based nuclear waste object detection. IEEE Sensors J 19:3487–3500

    Article  Google Scholar 

  25. Varma G, Subramanian A, Namboodiri A, Chandraker M, Jawahar C (2019) IDD: a dataset for exploring problems of autonomous navigation in unconstrained environments. IEEE Winter Conf Appl Comput Vis (WACV) 2019:1743–1751. https://doi.org/10.1109/WACV.2019.00190

    Article  Google Scholar 

  26. Wang L, Chen F, Yin H (2016) Detecting and tracking vehicles in traffic by unmanned aerial vehicles. Autom Constr 72:294–308. https://doi.org/10.1016/j.autcon.2016.05.008

    Article  Google Scholar 

  27. Xie E, Wang W, Yu Z, Anandkumar A, Alvarez JM, Luo P (2021) SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers. https://doi.org/10.48550/arXiv.2105.15203

  28. Xu H, Zhang J (2020) AANet: adaptive aggregation network for efficient stereo matching. IEEE/CVF Conf Comput Vis Pattern Recognit (CVPR) 2020:1956–1965. https://doi.org/10.1109/CVPR42600.2020.00203

    Article  Google Scholar 

  29. Yang KL, Wang KW, Hu WJ, Bai J (2016) Expanding the detection of traversable area with RealSense for the visually impaired. Sens 16:ARTN 1954. https://doi.org/10.3390/s16111954

    Article  Google Scholar 

  30. Yang GR, Song X, Huang CQ, Deng ZD, Shi JP, Zhou BL (2019) DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (Cvpr 2019). :899–908. https://doi.org/10.1109/Cvpr.2019.00099

  31. Zhang Z (2000) A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell 22:1330–1334. https://doi.org/10.1109/34.888718

    Article  Google Scholar 

  32. Zhang Z (2019) Acquisition and Preprocessing of Face Recognition Data. 2018 4th International Conference on Environmental Science and Material Application. 252. https://doi.org/10.1088/1755-1315/252/4/042089

  33. Zhang Z, Hu M, Wang Y, Sun Z, Lai J, Chen X et al (2011) A survey of advances in biometric gait recognition. Biom Recog 7098:150–158. https://doi.org/10.1007/978-3-642-25449-9_19

    Article  Google Scholar 

  34. Zhao D, Wang L, Li Y, Du M (2018) Extraction of preview elevation of road based on 3D sensor. Meas 127:104–114. https://doi.org/10.1016/j.measurement.2018.05.062

    Article  Google Scholar 

  35. Zhou T, Chen Y (2018) Remote Sensing Images Recognition by Deep Convolutional Neural Networks. 2018 3rd International Conference on Robotics and Automation Engineering (ICRAE). 202–5. https://doi.org/10.1109/ICRAE.2018.8586678

Download references

Acknowledgments

The authors gratefully acknowledged the National Natural Science Foundation of China (grant number 51775225) and the Graduate Innovation Fund of Jilin University (grant number 101832020CX111) for the financial support of these studies.

Author information

Author notes

  1. Jianbo Guo, Guoqiang Wang, Wei Guan, Zeren Chen and Zhengbin Liu contributed equally to this work.

Authors and Affiliations

  1. School of Mechanical and Aerospace Engineering, Jilin University, Changchun, 130025, People’s Republic of China

    Jianbo Guo, Guoqiang Wang, Wei Guan & Zhengbin Liu

  2. College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, 030024, Taiyuan, People’s Republic of China

    Zeren Chen

Authors
  1. Jianbo Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guoqiang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wei Guan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zeren Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhengbin Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Jianbo Guo: Methodology, Software, Writing - Original Draft. Guoqiang Wang: Conceptualization, Supervision. Wei Guan: Investigation, Software. Zeren Chen: Writing- Reviewing and Editing. Zhengbin Liu: Investigation.

Corresponding author

Correspondence to Guoqiang Wang.

Ethics declarations

Competing interests

All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Guo, J., Wang, G., Guan, W. et al. A feasible region detection method for vehicles in unstructured environments based on PSMNet and improved RANSAC. Multimed Tools Appl 82, 43967–43989 (2023). https://doi.org/10.1007/s11042-023-15412-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-15412-y

Keywords

Search

Navigation