High-precision laser monitoring system with enhanced non-uniform scanning for railway safety

Abstract

The intrusion of obstacles onto railway tracks presents a significant threat to train safety, characterized by sudden and unpredictable occurrences. With China leading the world in high-speed rail mileage, ensuring railway security is paramount. The current laser monitoring technologies suffer from high false alarm rates and unreliable intrusion identification. This study addresses these issues by investigating high-resolution laser monitoring technology for railway obstacles, focusing on key parameters such as monitoring range and resolution. We propose an enhanced non-uniform laser scanning method, developing a laser monitoring system that reduces the obstacle false alarm rate to 2.00%, significantly lower than the 20% standard (TJ/GW135-2015). This rate is the best record for laser monitoring systems on China Railway. Our system operates seamlessly in all weather conditions, providing superior accuracy, resolution, and identification efficiency. It is the only 3D LiDAR system certified by the China State Railway Group Co., Ltd. (Certificate No. [2023] 008). Over three years, our system has been deployed at numerous points along various lines managed by the China State Railway Group, accumulating a dataset of 300,000 observations. This extensive deployment has significantly enhanced railway safety. The development and implementation of our railway laser monitoring system represent a substantial advancement in railway safety technology. Its low false alarm rate (2.00%), high accuracy (20 cm × 20 cm × 20 cm), and robust performance in diverse conditions underscore its potential for widespread adoption, promising to enhance railway safety in China and internationally.

Keywords

Laser monitoring technology / Non-uniform laser scanning method / False alarm rate / Railway safety

References

[1] China’s high-speed rail operation mileage reaches 45,000 km, http://www.china-railway.com.cn/xwzx/zhxw/202401/t20240112_132652.html. Accessed 12th Jan 2024

[2] Fanos AM Pradhan B. A novel rockfall hazard assessment using laser scanning data and 3D modelling in GIS. CATENA, 2019 172 435-450

[3] Mentani A Govoni L Gottardi G . A new approach to evaluate the effectiveness of rockfall barriers. Proc Eng, 2016 158 398-403

[4] Lan H Martin CD Zhou C . Rockfall hazard analysis using LiDAR and spatial modeling. Geomorphology, 2010 118 1–2 213-223

[5] Ryan AK Hutchinson DJ Lato MJ . Identifying rock slope failure precursors using LiDAR for transportation corridor hazard management. Eng Geol, 2015 195 93-103

[6] Soilán M Sánchez-Rodríguez A del Río-Barral P . Review of laser scanning technologies and their applications for road and railway infrastructure monitoring. Infrastructures, 2019 4 4 58

[7] Dunham L Wartman J Olsen MJ . Rockfall activity index (RAI): a lidar-derived, morphology-based method for hazard assessment. Eng Geol, 2017 221 184-192

[8] Ferrari F Giacomini A Thoeni K . Qualitative evolving rockfall hazard assessment for highwalls. Int J Rock Mech Min Sci, 2017 98 88-101

[9] Netti T Castelli M De Biagi V. Effect of the number of simulations on the accuracy of a rockfall analysis. Proc Eng, 2016 158 464-469

[10] Piszczek M. Data fusion in application of image information. Acta Phys Polon Ser A, 2011 120 4 716

[11] Nairat M Voelz D. Performance characteristics of a scanning laser imaging system through atmospheric turbulence. Opt Eng, 2012 51 10 101708

[12] Piszczek M Kowalski M Karol M . Laser photography device-spatial parameters of imaging. Acta Phys Polon Ser A, 2013 124 3 550

[13] Christnacher F Schertzer S Metzger N . Influence of gating and of the gate shape on the penetration capacity of range-gated active imaging in scattering environments. Opt Expr, 2015 23 26 32897

[14] Lutz Y Bacher E Schertzer S. Accumulation mode laser range-gated viewing in the eye-safe spectral region. Opt Laser Technol, 2017 96 1-6

[15] Laurenzis M Christnacher F Monnin D. Long-range three-dimensional active imaging with super-resolution depth mapping. Opt Lett, 2007 32 21 3146-3148

[16] Schilling BW Barr DN Templeton GC . Multiple-return laser radar for three-dimensional imaging through obscurations. Appl Opt, 2002 41 15 2791-2799

[17] Zhang X Yan H Zhou Q. Overcoming the shot-noise limitation of three-dimensional active imaging. Opt Lett, 2011 36 8 1434-1436

[18] Chua SY Wang X Guo N . Influence of target reflection on three-dimensional range gated reconstruction. Appl Opt, 2016 55 24 6588-6595

[19] Li L Wu L Wang X . Gated viewing laser imaging with compressive sensing. Appl Opt, 2012 51 14 2706-2712

[20] Luo H Yuan X Zeng Y. Range accuracy of photon heterodyne detection with laser pulse based on Geiger-mode APD. Opt Expr, 2013 21 16 18983-18993

[21] Chua SY Wang X Guo N . Range compensation for accurate 3D imaging system. Appl Opt, 2015 55 1 153-158

[22] Oh MS Kong HJ Kim TH . Development and analysis of a photon-counting three-dimensional imaging laser detection and ranging (LADAR) system. J Opt Soc Am A, 2011 28 5 759-765

[23] Gézero L Antunes C. Automated three-dimensional linear elements extraction from mobile LiDAR point clouds in railway environments. Infrastructures, 2019 4 3 46

[24] Che E Jung J Olsen MJ. Object recognition, segmentation, and classification of mobile laser scanning point clouds: a state of the art review. Sensors, 2019 19 4 810

[25] Yadav M Singh AK Lohani B. Extraction of road surface from mobile LiDAR data of complex road environment. Int J Remote Sens, 2017 38 16 4655-4682

[26] Jung J Che E Olsen MJ . Efficient and robust lane marking extraction from mobile lidar point clouds. ISPRS J Photogram Remote Sens, 2019 147 1-18

[27] Huang P Cheng M Chen Y . Traffic sign occlusion detection using mobile laser scanning point clouds. IEEE Trans Intell Transp Syst, 2017 18 9 2364-2376

[28] Mroué A Heddebaut M Elbahhar F . Automatic radar target recognition of objects falling on railway tracks. Meas Sci Technol, 2012 23 2 25401-25410

[29] Nan Z Zhu G Zhang X . A novel high-precision railway obstacle detection algorithm based on 3D LiDAR. Sensors, 2024 24 10 3148

[30] Kuk C. Enhanced clustering method using 3 D laser range data for an autonomous vehicle. Recent Adv Electr Eng, 2014 8 6 209-218

[31] Zhou Y, Tuzel O (2018) VoxelNet: end-to-end learning for point cloud based 3D object detection. In: 2018 IEEE/CVF conference on computer vision and pattern recognition. Salt Lake City, pp 4490–4499

[32] Yang S Yang Y Zhang L . Real time measurement of subgrade settlement in high speed railways with a resolution of 025 mm using a laser imaging method. Lasers Eng, 2020 45 1–3 1-14

[33] Nan Z Zhu G Zhang X . Development of a high-precision lidar system and improvement of key steps for railway obstacle detection algorithm. Remote Sens, 2024 16 10 1761

Funding

National Natural Science Foundation of China(62275244)