A novel probability iterative closest point with normal vector algorithm for robust rail profile registration

Abstract Regular inspection of rail wear is very important to ensure the safety of railway transportation. Rail profile registration is a key step in rail wear measurement. However, the accuracy of rail profile registration cannot be guaranteed due to soil and corrosion on the rail waist. To solve this problem, a new rail profile registration method based on probability iterative closest point algorithm with normal vector direction (N-PICP) is proposed in this paper. First, rail profile data is obtained using a line structured light measurement system. Then, the rail profile data is divided into rail head and rail waist according to the distance between adjacent points. The data of the rail waist is used to register with the corresponding part of the standard profile data by N-PICP. Finally, the rail head data is also converted according to the calculated transformation matrix. The experimental results demonstrate that the proposed method can realize the registration of the rail profile with a high precision and strong robustness.

[1]  Hongli Liu,et al.  Distortion Rectifying for Dynamically Measuring Rail Profile Based on Self-Calibration of Multiline Structured Light , 2018, IEEE Transactions on Instrumentation and Measurement.

[2]  Hongli Liu,et al.  The Outlier and Integrity Detection of Rail Profile Based on Profile Registration , 2020, IEEE Transactions on Intelligent Transportation Systems.

[3]  Ziji Ma,et al.  Distortion calibrating method of measuring rail profile based on local affine invariant feature descriptor , 2017 .

[4]  Zhen Liu,et al.  On-site calibration of line-structured light vision sensor in complex light environments. , 2015, Optics express.

[5]  Feng Chen,et al.  Dynamic inspection of a rail profile under affine distortion based on the reweighted-scaling iterative closest point method , 2019, Measurement Science and Technology.

[6]  Ke Li,et al.  Probability iterative closest point algorithm for m-D point set registration with noise , 2015, Neurocomputing.

[7]  Long Liu,et al.  Sparse Scaling Iterative Closest Point for Rail Profile Inspection , 2019, J. Comput. Inf. Sci. Eng..

[8]  Yong Hu,et al.  Rail wear inspection based on computer-aided design model and point cloud data , 2018, Advances in Mechanical Engineering.

[9]  Bing Yi,et al.  An Accurate and Fast Method to Inspect Rail Wear Based on Revised Global Registration , 2018, IEEE Access.

[10]  Wanlin Dai,et al.  Novel method for rail wear inspection based on the sparse iterative closest point method , 2017 .

[11]  Guangjun Zhang,et al.  Simple and fast rail wear measurement method based on structured light , 2011 .

[12]  Peng Zhou,et al.  Rail Profile Measurement Based on Line-structured Light Vision , 2018, IEEE Access.

[13]  Paul J. Besl,et al.  Method for registration of 3-D shapes , 1992, Other Conferences.