Regression detection based adaptive inverse perspective mapping for vehicle arc lane detection

Abstract

Inverse perspective mapping (IPM) plays an important role in intelligent vehicles and machine vision, which can eliminate perspective distortion and get a top view for lane detection and location. However, on the curved slope, the changing road surface brings the changing characteristics of pitch Angle and camera height, which distorts the bending Angle of the lane, resulting in the decrease of IPM recognition accuracy. In order to solve this problem, an adaptive IPM method based on surface and vanishing point (VP) is proposed to eliminate perspective distortion of complex pavement such as flat pavement and curved slope. In the adaptive IPM method, VP is used as a feature reflecting road changes and detected by Residual Neural Network with Split-attention (ResNeSt-50). The adaptive IPM method uses the differential judgment mechanism of VP variation characteristics to automatically determine the road section and select the corresponding IPM model in real time. Simplified IPM is adopted in the flat section, robust IPM is adopted in the transition section, and full csipm is adopted in the circular slope section. Finally, the dynamic IPM experiment verifies the effectiveness of the adaptive IPM method in the whole driving process. The method can maintain the effect of removing distortion under different slope angles and reduce the complexity of lane detection.

Keywords

Lane detection intelligent vehicles machine vision inverse perspective mapping vanishing point

Get full access to this article

View all access options for this article.

References

Pan

Gao

, et al. Iterative residual optimization network for limited-angle tomographic reconstruction. IEEE Trans Image Process 2024; 33: 910–925.

Tian

Zhang

Wang

, et al. ACF-Net: asymmetric cascade fusion for 3D detection with LiDAR point clouds and images. IEEE Trans Intell Vehicles 2024; 9(2): 3360–3371.

Zhang

Tong

, et al. Review of visual simultaneous localization and mapping based on deep learning. Remote Sens 2023; 15(11): 2740.

Zeng

. Lane-line detection based on inverse perspective mapping and Kalman Filter. In: 2024 International conference on computer vision, mechanical automation and remote sensing mapping, 2024, vol. 11, no. 1, p.1.

Huang

. Lane detection based on inverse perspective transformation and Kalman filter. KSII Trans Internet Inf Syst 2018; 12(2): 643–661.

Wang

, et al. A robust lane detection method based on hyperbolic model. Soft Comput 2019; 23(19): 9161–9174.

Alaa

Salama

Galal

, et al. A robust lane detection method for urban roads. J Adv Eng Trends 2022; 41(1): 13–26.

Youjin

Wei

Xingguang

, et al. A robust lane detection method based on vanishing point estimation. Procedia Comput Sci 2018; 131: 354–360.

Bertozz

Broggi

Fascioli

. Stereo inverse perspective mapping: theory and applications. Image Vis Comput 1998; 16(8): 585–590.

10.

Guo

, et al. Inverse perspective transform based on directional 2-D interpolation. J. Tsinghua Univ 2006; 6(5): 712–715.

11.

Lin

Shen

Shou

. Construction of fisheye lens inverse perspective mapping model and its applications of obstacle detection. EURASIP J Adv Signal Process 2010; 1(1): 1–23.

12.

Bruls

Porav

Kunze

, et al. The right (angled) perspective: improving the understanding of road scenes using boosted inverse perspective mapping. In: Intelligent vehicles symposium proceedings 2019, pp.302–309.

13.

Yaghoobi Ershadi

Menéndez

Jiménez Bermejo

. Evaluating the effect of MIPM on vehicle detection performance. Transp Lett 2020; 12(4): 257–273.

14.

Guillet

Ravanel

. Camera orientation, calibration and inverse perspective with uncertainties: A Bayesian method applied to area estimation from diverse photographs. ISPRS J Photogramm Remote Sens 2020; 159: 237–255.

15.

Xie

Shi

, et al. Research on the vanishing point detection method based on an improved lightweight AlexNet network for narrow waterway scenarios. J Mar Sci Eng 2024; 12(5): 765.

16.

Lee

Hyun

, et al. LiDAR ground detection-based dynamic inverse perspective mapping of BEV lanes. IEEE Sens J 2023; 23(24): 30950–30959.

17.

Guo

Zhou

, et al. Lane detection and road surface reconstruction based on multiple vanishing point & symposia. In: IEEE IEEE Intelligent vehicles symposium, 2018, pp. 209–214.

18.

Shi

Wang

. Fast and robust vanishing point detection for unstructured road following. IEEE Trans Intell Transp Syst 2016; 17(4): 970–979.

19.

Yang

, et al. A fast vanishing point detection method based on row space features suitable for real driving scenarios. Sci Rep 2023; 13(1): 3088.

20.

Jiao

Yang

Jiang

, et al. Real-time lane detection and tracking for autonomous vehicle applications. Proc. Inst. Mech. Eng., Part D 2019; 233(9): 2301–2311.

21.

Chang

Zhao

Itti

. DeepVP: deep learning for vanishing point detection on 1 million street view images. In: IEEE International conference on robotics and automation (ICRA), 2018, pp. 4496–4503.

22.

Liu

Zeng

Meng

. D-VPnet: a network for real-time dominant vanishing point detection in natural scenes. Neurocomputing 2020; 417(5): 432–440.

23.

Khac

Choi

Park

, et al. A robust road vanishing point detection adapted to the real-world driving scenes. Sensors 2021; 21(6): 2133.

24.

Lee

Hwang

. Fast and accurate self-calibration using vanishing point detection in manmade environments. Int J Control Autom Syst 2020; 18(10): 2609–2620.

25.

Liu

Zeng

Meng

. Unstructured road vanishing point detection using convolutional neural networks and heatmap regression. IEEE Trans Instrum Meas 2021; 70: 1–8.

26.

Choi

Kang

. Regression with residual neural network for vanishing point detection. Image Vis Comput 2019; 91: 103797.

27.

Liu

Fan

Han

, et al. RVPNet: a real time unstructured road vanishing point detection algorithm using attention mechanism and global context information. Multimed Tools Appl 2024; 83(9): 28263–28280.

28.

Krishnan

. Design of collision detection system for smart car using Li-Fi and ultrasonic sensor. IEEE Trans Vehicular Technol 2019; 67(12): 11420–11426.

29.

Yang

, et al. Road detection and centerline extraction via deep recurrent convolutional neural network U-Net. IEEE Trans Geosci Remote Sens 2019; 57(9): 7209–7220.