Twisting Pathway Understanding Inspired by Global Precedence Effect in a Field Environment

Luping Wang; Lijuan Chen; Yuan Feng; Shanshan Wang; Hui Wei

Abstract

Scene understanding is a core prerequisite for robots’ autonomous decision-making. However, real-world application faces challenges like understanding unknown, unstructured twisting paths in field environments. Traditional methods using 3D point clouds or multi-sensor fusion are energy-intensive and computationally expensive, making them laborious for resource-limited field robots. Inspired by the global precedence effect (GPE)—the phenomenon that humans perceive global stimuli preferentially, aiding understanding of multiple zigzag paths—we present a method using only a monocular camera to understand unstructured twisting paths. We extracted improved edge-based lines. Multiple curves were formed by grouping lines based on proximity and continuity, inspired by GPE. By analyzing curve orientations, twisted zigzag paths can be reshaped and twist direction estimated, providing decision basis for robot autonomous navigation. Unlike deep learning algorithms, our method is highly interpretable without prior training or camera internal parameters. It has low energy consumption and low investment, requiring no external equipment. Pure geometric reasoning contributes to robustness under lighting variations and various colors. Pixel-wise classification accuracy was compared with ground truth. Experimental results show the method successfully elucidates unstructured twisting paths, providing navigation-relevant scene interpretation in field environments.

References

1.
Amirkhiabani, G.; Lovegrove, W.J. Role of eccentricity and size in the global precedence effect. J. Exp. Psychol. Hum. Percept. Perform. 1996, 22, 1434–1447.
2.
Rezvani, Z.; Katanforoush, A.; Pouretemad, H. Global precedence changes by environment: A systematic review and meta-analysis on effect of perceptual field variables on global–local visual processing. Atten. Percept. Psychophys. 2020, 82, 2348–2359.
3.
Wang, L.; Wei, H. Avoiding non-Manhattan obstacles based on projection of spatial corners in indoor environment. IEEE/CAA J. Autom. Sin. 2020, 7, 1190–1200.
4.
Baheti, B.; Innani, S.; Gajre, S.S.; et al. Eff-UNet: A novel architecture for semantic segmentation in unstructured environment. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Seattle, WA, USA, 14–19 June 2020; pp. 1473–1481.
5.
Magerand, L.; Del Bue, A. Revisiting projective structure from motion: A robust and efficient incremental solution. IEEE Trans. Pattern Anal. Mach. Intell. 2020, 42, 430–443.
6.
Bescós, B.; Cadena, C.; Neira, J. Empty cities: A dynamic-object-invariant space for visual SLAM. IEEE Trans. Robot. 2021, 37, 433–451.
7.
Cavagna, A.; Melillo, S.; Parisi, L.; Ricci-Tersenghi, F. SpaRTA: Tracking across occlusions via partitioning of 3D clouds of points. IEEE Trans. Pattern Anal. Mach. Intell. 2021, 43, 1394–1403.
8.
Mahmoud, A.; Ehab, L.; Reda, M.; et al. Real-time lane detection based on line segment detection. In Proceedings of the 2018 New Generation of CAS (NGCAS), Valletta, Malta, 20–23 November 2018; pp. 57–61.
9.
Agrawal, S.; Deo, I.K.; Haldar, S.; et al. Off-road lane detection using superpixel clustering and RANSAC curve fitting. In Proceedings of the 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore, 18–21 November 2018; pp. 1942–1946.
10.
Ye, C.; Zhao, H.; Ma, L.; et al. Robust lane extraction from MLS point clouds towards HD maps especially in curve road. IEEE Trans. Intell. Transp. Syst. 2022, 23, 1505–1518.
11.
Merugu, K.; Adarsh, S. Multi lane detection, curve fitting and lane type classification. In Proceedings of the 2022 IEEE 19th India Council International Conference (INDICON), Kochi, India, 24–26 November 2022; pp. 1–6.
12.
Wang, L.; Wei, H. Recognizing slanted deck scenes by non-Manhattan spatial right angle projection. IEEE Intell. Syst. 2022, 37, 75–85.
13.
Viswanath, K.; Singh, K.; Jiang, P.; et al. OFFSEG: A semantic segmentation framework for off-road driving. In Proceedings of the 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), Lyon, France, 23–27 August 2021; pp. 354–359.
14.
Ding, L.; Sherony, R.; Mehler, B.; Reimer, B. Perceptual evaluation of driving scene segmentation. In Proceedings of the 2021 IEEE Intelligent Vehicles Symposium (IV), Nagoya, Japan, 11–17 July 2021; pp. 1444–1450.
15.
TAS500 Dataset url. Available online: https://mucar3.de/icpr2020-tas500/ (accessed on 17 July 2024).
16.
Shelhamer, E.; Long, J.; Darrell, T. Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 640–651.
17.
Badrinarayanan, V.; Kendall, A.; Cipolla, R. SegNet: A deep convolutional encoder–decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 2481–2495.
18.
Zhao, H.; Shi, J.; Qi, X.; et al. Pyramid scene parsing network. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 6230–6239.
19.
Chen, L.; Papandreou, G.; Schroff, F.; et al. Rethinking atrous convolution for semantic image segmentation. arXiv 2017, arXiv:1706.05587.
20.
Blum, H.; Sarlin, P.E.; Nieto, J.; et al. Fishyscapes: A benchmark for safe semantic segmentation in autonomous driving. In Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Republic of Korea, 27–28 October 2019; pp. 2403–2412.
21.
Lambert, J.; Liu, Z.; Sener, O.; et al. MSeg: A composite dataset for multi-domain semantic segmentation. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 14–19 June 2020; pp. 2876–2885.
22.
Jiang, P.; Osteen, P.; Wigness, M.; et al. RELLIS-3D dataset: Data, benchmarks and analysis. In Proceedings of the 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi’an, China, 30 May–5 June 2021; pp. 1110–1116.
23.
Upadhyay, P.; Srivastava, S.; Pandey, S.S.; et al. Lane line detection using machine learning. In Proceedings of the 2022 3rd International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), Ghaziabad, India, 11–12 November 2022; pp. 1–6.
24.
Wang, H.; Wang, Y.; Zhao, X.; et al. Lane detection of curving road for structural highway with straight–curve model on vision. IEEE Trans. Veh. Technol. 2019, 68, 5321–5330.
25.
Kasyap, V.L.V.S.K.B.; Macharla, A.; Sri, T.K.; et al. RoadSDNet: A robust algorithm for road boundary detection and segmentation using mixed networks and Hough transform. In Proceedings of the 2022 Algorithms, Computing and Mathematics Conference (ACM), Chennai, India, 29–30 August 2022; pp. 30–34.
26.
Wang, L.; Wei, H. Bending path understanding based on angle projections in field environments. J. Artif. Intell. Soft Comput. Res. 2024, 14, 25–43.
27.
Galimova, G.; Volkov, V.; Demyanov, D. An MPC-based path-following control algorithm of the road train. In Proceedings of the 2021 International Russian Automation Conference (RusAutoCon), Sochi, Russia, 5–11 September 2021; pp. 964–969.
28.
Dai, M.; Feng, T.; Guo, L.; et al. Vehicle tracking and motion estimation on curve road segment by using smartphone sensors. In Proceedings of the 2019 5th International Conference on Transportation Information and Safety (ICTIS), Liverpool, UK, 14–17 July 2019; pp. 1117–1121.
29.
Li, Z.; Liang, T.; Ren, Q. Curve trajectory prediction through vehicle infrastructure cooperation. In Proceedings of the 2022 IEEE 17th Conference on Industrial Electronics and Applications (ICIEA), Chengdu, China, 16–19 December 2022; pp. 1092–1097.
30.
Shipitko, O.; Kabakov, A.; Grigoryev, A.; et al. Road markings and road edges mapping with inverse visual detector model. In Proceedings of the 2022 IEEE 95th Vehicular Technology Conference (VTC2022-Spring), Helsinki, Finland, 19–22 June 2022; pp. 1–6.
31.
Salleh, D.N.S.D.A.; Seignez, E.; Kipli, K. Visual odometry based vehicle lane-changing detection. In Proceedings of the 2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), Kota Kinabalu, Malaysia, 13–15 September 2022; pp. 1–6.
32.
Mei, J. Dataset url. Available online: http://www.poss.pku.edu.cn/index.html (accessed on 21 July 2024).
33.
Li, Y.; Tong, G.; Sun, A.; et al. Road extraction algorithm based on intrinsic image and vanishing point for unstructured road image. Robot. Auton. Syst. 2018, 109, 86–96.
34.
Geiger, A.; Lenz, P.; Stiller, C.; et al. Vision meets robotics: The KITTI dataset. Int. J. Robot. Res. 2013, 32, 1231–1237.
35.
The Cityscapes Dataset url. Available online: https://www.cityscapes-dataset.com/ (accessed on 2 August 2024).
36.
Public FDWW Dataset url: Available online: https://download.csdn.net/download/u011280710/74922587 (accessed on 4 August 2024).
37.
Wigness, M.B.; Eum, S.; Rogers, J.G.; et al. A RUGD dataset for autonomous navigation and visual perception in unstructured outdoor environments. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China, 3–8 November 2019; pp. 5000–5007.
38.
CurveLane-Dataset url. Available online: https://github.com/SoulmateB/CurveLanes (accessed on 5 August 2024).
39.
Chaurasia, A.; Culurciello, E. LinkNet: Exploiting encoder representations for efficient semantic segmentation. In Proceedings of the 2017 IEEE Visual Communications and Image Processing (VCIP), St. Petersburg, FL, USA 10–13 December 2017; pp. 1–4.
40.
Romera, E.; Álvarez, J.M.; Bergasa, L.M.; et al. ERFNet: Efficient residual factorized ConvNet for real-time semantic segmentation. IEEE Trans. Intell. Transp. Syst. 2018, 19, 263–272.
41.
Yu, C.; Wang, J.; Peng, C.; et al. BiSeNet: Bilateral segmentation network for real-time semantic segmentation. arXiv 2018, arXiv:1808.00897.
42.
Poudel, R.P.K.; Liwicki, S.; Cipolla, R. Fast-SCNN: Fast semantic segmentation network. In Proceedings of the 30th British Machine Vision Conference (BMVC), Cardiff, UK, September 9–12, 2019; BMVA Press: Durham, UK, 2019; p. 289.

Scilight Press

Author Information

Abstract

Keywords

References

About Scilight

Journals

Publishing Policies

Contact Us