Automatic Vehicle Detection With Roadside LiDAR Data Under Rainy and Snowy Conditions

The previous studies showed that rainy and snowy weather can reduce the quality of LiDAR data. In rainy and snowy weather, laser beams of LiDAR were often blocked by raindrops or snowflakes, which was called weather occlusion. The vehicle detection with weather occlusion is a challenge. When the traditional density-based spatial clustering of applications with noise (DBSCAN) was used for vehicle clustering, the data processing showed that the false detection rate of the conventional DBSCAN under the snowy weather was high. This paper aims to present the characteristics of roadside LiDAR data in snowy and rainy days and improve the accuracy of vehicle detection during challenging weather conditions. A revised DBSCAN method named 3D-SDBSCAN is raised up to distinguish vehicle points and snowflakes in the LiDAR data. Adaptive parameters were applied in the revised DBSCAN method to detect vehicles with different distances from the roadside LiDAR sensor. The performance of the proposed method and the conventional DBSCAN algorithm were compared using the data collected under rainy and snowy conditions. The results showed that the 3D-SDBSCAN algorithm could overcome weather occlusion issue better than the conventional one.

[1]  Michal Daszykowski,et al.  Revised DBSCAN algorithm to cluster data with dense adjacent clusters , 2013 .

[2]  Jianqing Wu,et al.  An Automatic Procedure for Vehicle Tracking with a Roadside LiDAR Sensor , 2018 .

[3]  Junxuan Zhao,et al.  An Artificial Neural Network to Identify Pedestrians and Vehicles from Roadside 360-Degree LiDAR Data , 2018 .

[4]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[5]  Andreas Riener,et al.  Introduction to rain and fog attenuation on automotive surround sensors , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[6]  Ming Chen,et al.  Machine Learning Approach to Decomposing Arterial Travel Time Using a Hidden Markov Model with Genetic Algorithm , 2018, J. Comput. Civ. Eng..

[7]  Thomas Brandmeier,et al.  Test methodology for rain influence on automotive surround sensors , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[8]  Hao Xu,et al.  Driver behavior analysis for right-turn drivers at signalized intersections using SHRP 2 naturalistic driving study data. , 2017, Journal of safety research.

[9]  Ralph Helmar Rasshofer,et al.  Influences of weather phenomena on automotive laser radar systems , 2011 .

[10]  Zygmunt Mierczyk,et al.  Comparison of 905 nm and 1550 nm semiconductor laser rangefinders’ performance deterioration due to adverse environmental conditions , 2014 .

[11]  Yuan Sun,et al.  Automatic Background Filtering Method for Roadside LiDAR Data , 2018, Transportation Research Record: Journal of the Transportation Research Board.

[12]  Alistair M. S. Smith,et al.  Discrete Return Lidar in Natural Resources: Recommendations for Project Planning, Data Processing, and Deliverables , 2009, Remote. Sens..

[13]  Gloria Bordogna,et al.  Fuzzy extensions of the DBScan clustering algorithm , 2016, Soft Comput..

[14]  Hao Xu,et al.  Automatic background filtering and lane identification with roadside LiDAR data , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[15]  Mohan M. Trivedi,et al.  A General Active-Learning Framework for On-Road Vehicle Recognition and Tracking , 2010, IEEE Transactions on Intelligent Transportation Systems.

[16]  Hao Xu,et al.  3-D Data Processing to Extract Vehicle Trajectories from Roadside LiDAR Data , 2018, Transportation Research Record: Journal of the Transportation Research Board.

[17]  Junxuan Zhao,et al.  Trajectory tracking and prediction of pedestrian's crossing intention using roadside LiDAR , 2019, IET Intelligent Transport Systems.

[18]  Hao Xu,et al.  The influence of road familiarity on distracted driving activities and driving operation using naturalistic driving study data , 2018 .

[19]  Junxuan Zhao,et al.  Autonomous Wildlife Crossing Detection Method with Roadside Lidar Sensors , 2018 .

[20]  Zehang Sun,et al.  On-road vehicle detection: a review , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Yichen Zheng,et al.  Design and Implementation of the DSRC-Bluetooth Communication and Mobile Application with LiDAR Sensor , 2018 .

[23]  Zied Elouedi,et al.  Fuzzy density based clustering method: Soft DBSCAN-GM , 2016, 2016 IEEE 8th International Conference on Intelligent Systems (IS).

[24]  M. Abdel-Aty,et al.  A correlated random parameter approach to investigate the effects of weather conditions on crash risk for a mountainous freeway , 2014 .

[25]  Junxuan Zhao,et al.  Automatic Lane Identification Using the Roadside LiDAR Sensors , 2020, IEEE Intelligent Transportation Systems Magazine.

[26]  Zong Tian,et al.  A novel method of vehicle-pedestrian near-crash identification with roadside LiDAR data. , 2018, Accident; analysis and prevention.

[27]  José Luis Lerma,et al.  Unsupervised robust planar segmentation of terrestrial laser scanner point clouds based on fuzzy clustering methods , 2008 .

[28]  James M. Keller,et al.  A possibilistic fuzzy c-means clustering algorithm , 2005, IEEE Transactions on Fuzzy Systems.

[29]  Matti Kutila,et al.  Automotive LIDAR sensor development scenarios for harsh weather conditions , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[30]  Thomas Brandmeier,et al.  Modeling and simulation of rain for the test of automotive sensor systems , 2016, 2016 IEEE Intelligent Vehicles Symposium (IV).