Skip to main content

VLDNet: Vision-based lane region detection network for intelligent vehicle system using semantic segmentation

Abstract

Detection of lane region under the road boundary is an imperative module for intelligent vehicle system. Lane markings provide separate regions on the road for the vehicles to avoid the possibility of accidents. Existing methods in lane detection have limited performance using various sensor-based approaches such as Radar and LiDAR and have high operational costs. To achieve a steady and optimal lane detection, the vision-based lane region detection scheme VLDNet is proposed which utilizes a encoder-decoder network using semantic segmentation architecture. In this direction, a hybrid model using UNet and ResNet has been adopted, where UNet is used as a segmentation model and ResNet-50 is used for down-sampling the image and identifying the required features. These identified features have been then applied into UNet for up-sampling and decoding the segments of the images. The publicly available KITTI dataset have been accessed for experiments and validation of the proposed network. The method outperforms the existing state-of-the-art methods in lane region detection. The network achieves better performance using standard evaluation measures such as accuracy of 98.87%, the precision of 98.24%, recall of 96.55%, frequency weighted IoU of 97.78%, and MaxF score of 97.77%.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

References

  1. 1.

    “Road traffic deaths, Global Health Observatory data repository by World Health Organization,”2020. https://apps.who.int/gho/data/node.main.A997

  2. 2.

    Dewangan DK and Sahu SP (2020) “Real Time Object Tracking for Intelligent Vehicle,” 2020 first international conference on power, control and computing technologies (ICPC2T), pp. 134-138, https://doi.org/10.1109/ICPC2T48082.2020.9071478.

  3. 3.

    Kiss G (2020) Manchurian artificial intelligence in autonomous vehicles. J Intell Fuzzy (Preprint):1-5

  4. 4.

    Sairam B, Agrawal A, Krishna G, Sahu SP (2020) Automated vehicle parking slot detection system using deep learning. In 2020 fourth international conference on computing methodologies and communication (ICCMC) Mar 11 (pp. 750-755). IEEE

  5. 5.

    Jung J, Bae SH (2018) Real-time road lane detection in urban areas using LiDAR data. Electronics 7(11):276

    Article  Google Scholar 

  6. 6.

    Xu F, Chen L, Lou J, Ren M (2019) A real-time road detection method based on reorganized lidar data. PloS one 14(4):e0215159

    Article  Google Scholar 

  7. 7.

    Wang Y, & Tsai Y (2018, May). A lane detection method based on 3D-LiDAR. In Fukuoka International Congress Center Fukuoka (pp. 1-10)

  8. 8.

    Kim DH (2020) Lane detection method with impulse radio ultra-wideband radar and metal lane reflectors. Sensors 20(1):324

    Article  Google Scholar 

  9. 9.

    Clarke D, Andre D, Zhang F (2016) Synthetic aperture radar for lane boundary detection in driver assistance systems. In2016 IEEE international conference on multisensor fusion and integration for intelligent systems (MFI) Sep 19 (pp. 238-243). IEEE

  10. 10.

    Felguera-Martín D, González-Partida JT, Almorox-González P, Burgos-García M (2012) Vehicular traffic surveillance and road lane detection using radar interferometry. IEEE Trans Vehicul Technol 61(3):959–70

    Article  Google Scholar 

  11. 11.

    Adam C, Schubert R, Mattern N, Wanielik G (2011) Probabilistic road estimation and lane association using radar detections. in14th international conference on information fusion Jul 5 (pp. 1-8). IEEE

  12. 12.

    Abbott E, Powell D (1999) Land-vehicle navigation using GPS. Proc IEEE 87(1):145–62

    Article  Google Scholar 

  13. 13.

    Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. Sep 4

  14. 14.

    Zhou W, Yu L, Zhou Y, Qiu W, Wu MW, Luo T (2018) Local and global feature learning for blind quality evaluation of screen content and natural scene images. IEEE Trans Imag Process 27(5):2086–95

    MathSciNet  Article  Google Scholar 

  15. 15.

    Huang G, Liu Z, Van Der Maaten L (2017) Weinberger KQ. Densely connected convolutional networks. InProceedings of the IEEE conference on computer vision and pattern recognition (pp. 4700-4708)

  16. 16.

    Dewangan DK, Sahu SP (2021) Deep learning-based speed bump detection model for intelligent vehicle system using raspberry Pi. IEEE Sens J 21(3):3570–3578

    Article  Google Scholar 

  17. 17.

    Dewangan DK, Sahu SP (2021) Driving behavior analysis of intelligent vehicle system for lane detection using vision-sensor. IEEE Sens J 21(5):6367–6375

    Article  Google Scholar 

  18. 18.

    Knoop VL, de Bakker PF, Tiberius CC, van Arem B (2017) Lane determination with GPS precise point positioning. IEEE Trans Intell Transp Syst 18(9):2503–13

    Article  Google Scholar 

  19. 19.

    Rabiee R, Zhong X, Yan Y, Tay WP (2018) LaIF: a lane-level self-positioning scheme for vehicles in GNSS-denied environments. IEEE Trans Intell Transp Syst 20(8):2944–61

    Article  Google Scholar 

  20. 20.

    Feng Z, Li M, Stolz M, Kunert M, Wiesbeck W (2018) Lane detection with a high-resolution automotive radar by introducing a new type of road marking. IEEE Trans Intell Transp Syst 20(7):2430–47

    Article  Google Scholar 

  21. 21.

    Ozgunalp U, Fan R, Ai X, Dahnoun N (2016) Multiple lane detection algorithm based on novel dense vanishing point estimation. IEEE TransIntell Transp Syst 18(3):621–32

    Article  Google Scholar 

  22. 22.

    Cui G, Wang J, Li J (2014) Robust multilane detection and tracking in urban scenarios based on LIDAR and mono-vision. IET Image Process 8(5):269–79

    Article  Google Scholar 

  23. 23.

    Shinzato PY, Wolf DF, Stiller C (2014) Road terrain detection: Avoiding common obstacle detection assumptions using sensor fusion. IEEE intelligent vehicles symposium proceedings 2014:687–692. https://doi.org/10.1109/IVS.2014.6856454

  24. 24.

    Chen L, Yang J and Kong H (2017)“Lidar-histogram for fast road and obstacle detection,” 2017 IEEE international conference on robotics and automation (ICRA), pp. 1343-1348, https://doi.org/10.1109/ICRA.2017.7989159.

  25. 25.

    Shinzato PY (2015) Estimation of obstacles and road area with sparse 3D points. Institute of Mathematics and Computer Science (ICMC)/University of Sao Paulo (USP)

  26. 26.

    Xiao L, Dai B, Liu D, Hu T, Wu T (2015) CRF based road detection with multi-sensor fusion. IEEE intelligent vehicles symposium (IV) 2015:192–198. https://doi.org/10.1109/IVS.2015.7225685

  27. 27.

    Xiao L, Wang R, Dai B, Fang Y, Liu D, Wu T (2018) Hybrid conditional random field based camera-LIDAR fusion for road detection. Inform Sci 432:543–558

    MathSciNet  Article  Google Scholar 

  28. 28.

    Ye YY, Hao XL, Chen HJ (2018) Lane detection method based on lane structural analysis and CNNs. IET Intell Transp Syst. 12(6):513–20

    Article  Google Scholar 

  29. 29.

    Zou Q, Jiang H, Dai Q, Yue Y, Chen L, Wang Q (2019) Robust lane detection from continuous driving scenes using deep neural networks. IEEE Trans Vehicul Technol 69(1):41–54

    Article  Google Scholar 

  30. 30.

    Fan R, Wang X, Hou Q, Liu H, Mu TJ (2019) SpinNet: spinning convolutional network for lane boundary detection. Comput Visual Media 5(4):417–28

    Article  Google Scholar 

  31. 31.

    Xiao D, Yang X, Li J, Islam M (2020) Attention deep neural network for lane marking detection. Knowledge-Based Syst 31:105584

    Article  Google Scholar 

  32. 32.

    Ma Y, Havyarimana V, Bai J, Xiao Z (2018) Vision-based lane detection and lane-marking model inference: a three-step deep learning approach. In2018 9th international symposium on parallel architectures, algorithms and programming (PAAP) Dec 26 (pp. 183-190). IEEE

  33. 33.

    Lyu Y, Bai L, Huang X (2019) Road segmentation using cnn and distributed lstm. In2019 IEEE International Symposium on Circuits and Systems (ISCAS) May 26 (pp. 1-5). IEEE

  34. 34.

    Sun JY, Kim SW, Lee SW, Kim YW, Ko SJ (2019)Reverse and boundary attention network for road segmentation. In Proceedings of the IEEE international conference on computer vision workshops (pp. 0-0)

  35. 35.

    Caltagirone L, Bellone M, Svensson L, Wahde M (2019) LIDAR-camera fusion for road detection using fully convolutional neural networks. Robot Autonom Syst 1(111):125–31

    Article  Google Scholar 

  36. 36.

    Chen Z, Chen Z. Rbnet: A deep neural network for unified road and road boundary detection. InInternational Conference on Neural Information Processing (2017) 14. Springer, Cham, pp 677–687

  37. 37.

    Han X, Lu J, Zhao C, You S, Li H (2018) Semisupervised and weakly supervised road detection based on generative adversarial networks. IEEE Signal Process Lett 25(4):551–5

    Article  Google Scholar 

  38. 38.

    Garnett N, Silberstein S, Oron S, Fetaya E, Verner U, Ayash A, Goldner V, Cohen R, Horn K, Levi D (2017) Real-time category-based and general obstacle detection for autonomous driving. InProceedings of the IEEE international conference on computer vision workshops (pp. 198-205)

  39. 39.

    Teichmann M, Weber M, Zoellner M, Cipolla R, Urtasun R (2018) Multinet: Real-time joint semantic reasoning for autonomous driving. In2018 IEEE Intelligent Vehicles Symposium (IV) Jun 26 (pp. 1013-1020). IEEE

  40. 40.

    Caltagirone L, Svensson L, Wahde M, Sanfridson M (2019) Lidar-Camera Co-Training for Semi-Supervised Road Detection. arXiv preprint arXiv:1911.12597. Nov 28

  41. 41.

    Van Gansbeke W, De Brabandere B, Neven D, Proesmans M, & Van Gool L (2019) End-to-end lane detection through differentiable least-squares fitting. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (pp. 0-0)

  42. 42.

    Hou Y, Ma Z, Liu C, & Loy CC (2019) Learning lightweight lane detection cnns by self attention distillation. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 1013-1021)

  43. 43.

    Li W, Qu F, Liu J, Sun F, Wang Y (2019) A lane detection network based on IBN and attention. Multimedia Tools and Applications 1–14

  44. 44.

    Ghafoorian M, Nugteren C, Baka N, Booij O, & Hofmann M (2018) El-gan: Embedding loss driven generative adversarial networks for lane detection. In proceedings of the european conference on computer vision (ECCV) Workshops (pp. 0-0)

  45. 45.

    Zhang, J., Xu, Y., Ni, B., & Duan, Z. (2018). Geometric constrained joint lane segmentation and lane boundary detection. In proceedings of the european conference on computer vision (ECCV) (pp. 486-502)

  46. 46.

    Chougule S, Koznek N, Ismail A, Adam G, Narayan V, & Schulze M (2018) Reliable multilane detection and classification by utilizing CNN as a regression network. In proceedings of the european conference on computer vision (ECCV) workshops (pp. 0-0)

  47. 47.

    Wang Z, Ren W, & Qiu Q (2018) Lanenet: Real-time lane detection networks for autonomous driving. arXiv preprint arXiv:1807.01726

  48. 48.

    Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: the kitti dataset. The Int J Robot Res 32(11):1231–7

    Article  Google Scholar 

  49. 49.

    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778)

  50. 50.

    He K, Zhang X, Ren S, Sun J, Identity mappings in deep residual networks. InEuropean conference on computer vision, (2016 Oct) 8. Springer, Cham, pp 630–645

  51. 51.

    Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. InProceedings of the IEEE conference on computer vision and pattern recognition (pp. 3431-3440)

  52. 52.

    Dewangan DK, Sahu SP (2021) RCNet: road classification convolutional neural networks for intelligent vehicle system. Intel Serv Robot 14:199–214. https://doi.org/10.1007/s11370-020-00343-6

    Article  Google Scholar 

  53. 53.

    Dewangan DK, Sahu SP (2021) PotNet: pothole detection for autonomous vehicle system using convolutional neural network. Electron Lett 57:53–56. https://doi.org/10.1049/ell2.12062

    Article  Google Scholar 

  54. 54.

    Padilla R, Netto SL, & da Silva EA (2020, July) A survey on performance metrics for object-detection algorithms. in 2020 international conference on systems, signals and image processing (IWSSIP) (pp. 237-242). IEEE

  55. 55.

    Srivastava RK, Greff K, & Schmidhuber J (2015) Highway networks. arXiv preprint arXiv:1505.00387

  56. 56.

    He K, & Sun J (2015) Convolutional neural networks at constrained time cost. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5353-5360)

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Deepak Kumar Dewangan.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Dewangan, D.K., Sahu, S.P., Sairam, B. et al. VLDNet: Vision-based lane region detection network for intelligent vehicle system using semantic segmentation. Computing (2021). https://doi.org/10.1007/s00607-021-00974-2

Download citation

Keywords

  • Intelligent Vehicle System
  • Artificial Intelligence
  • Lane Detection
  • Deep Learning
  • Computer Vision
  • Segmentation

Mathematics Subject Classification

  • 68T07