Object Classification with Roadside LiDAR Data Using a Probabilistic Neural Network

Object classification is important information for different transportation areas. This research developed a probabilistic neural network (PNN) classifier for object classification using roadside Light Detection and Ranging (LiDAR). The objective was to classify the road user on the urban road into one of four classes: Pedestrian, bicycle, passenger car, and truck. Five features calculated from the point cloud generated from the roadside LiDAR were selected to represent the difference between different classes. A total of 2736 records (2062 records for training, and 674 records for testing) were manually marked for training and testing the PNN algorithm. The data were collected at three different sites representing different scenarios. The performance of the classification was evaluated by comparing the result of the PNN with those of the support vector machine (SVM) and the random forest (RF). The comparison results showed that the PNN can provide the results of classification with the highest accuracy among the three investigated methods. The overall accuracy of the PNN for object classification was 97.6% using the testing database. The errors in the classification results were also diagnosed. Discussions about the direction of future studies were also provided at the end of this paper.

[1]  Alois Knoll,et al.  Vehicle detection based on LiDAR and camera fusion , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[2]  Chia-Feng Juang,et al.  Moving Object Classification Using a Combination of Static Appearance Features and Spatial and Temporal Entropy Values of Optical Flows , 2015, IEEE Transactions on Intelligent Transportation Systems.

[3]  T. Cacoullos.  Estimation of a multivariate density , 1966 .

[4]  Han Zhang,et al.  Background Filtering and Object Detection With a Stationary LiDAR Using a Layer-Based Method , 2020, IEEE Access.

[5]  Ho Lee,et al.  Side-Fire Lidar-Based Vehicle Classification , 2012 .

[6]  Hao Xu,et al.  Data Registration with Ground Points for Roadside LiDAR Sensors , 2019, Remote. Sens..

[7]  Filip Biljecki,et al.  Transportation mode-based segmentation and classification of movement trajectories , 2013, Int. J. Geogr. Inf. Sci..

[8]  Paulo Peixoto,et al.  A Lidar and Vision-based Approach for Pedestrian and Vehicle Detection and Tracking , 2007, 2007 IEEE Intelligent Transportation Systems Conference.

[9]  Bowen Gong,et al.  Slice-Based Instance and Semantic Segmentation for Low-Channel Roadside LiDAR Data , 2020, Remote. Sens..

[10]  Bin Tian,et al.  3D Vehicle Detection With RSU LiDAR for Autonomous Mine , 2021, IEEE Transactions on Vehicular Technology.

[11]  Baher Abdulhai,et al.  Enhancing the universality and transferability of freeway incident detection using a Bayesian-based neural network , 1999 .

[12]  Yongsheng Zhang,et al.  Automatic Vehicle Tracking with LiDAR-Enhanced Roadside Infrastructure , 2020 .

[13]  Yuan Tian,et al.  Vehicle Detection under Adverse Weather from Roadside LiDAR Data , 2020, Sensors.

[14]  Heng Wang,et al.  Robotics and Autonomous Systems , 2022 .

[15]  Hongbo Zhang,et al.  Analysis of Crash Severity for Hazard Material Transportation Using Highway Safety Information System Data , 2020 .

[16]  Juntae Kim,et al.  Toward Developing Efficient Conv-AE-Based Intrusion Detection System Using Heterogeneous Dataset , 2020, Electronics.

[17]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

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

[19]  Nicolas Saunier,et al.  Automated classification based on video data at intersections with heavy pedestrian and bicycle traffic: Methodology and application , 2015 .

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

[21]  Jianqiang Wang,et al.  Object Classification Using CNN-Based Fusion of Vision and LIDAR in Autonomous Vehicle Environment , 2018, IEEE Transactions on Industrial Informatics.

[22]  Nicolas Saunier,et al.  Automated Classification in Traffic Video at Intersections with Heavy Pedestrian and Bicycle Traffic , 2014 .

[23]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[24]  Adam Glowacz,et al.  Fault diagnosis of electric impact drills using thermal imaging , 2021 .

[25]  Zezhi Chen,et al.  Vehicle type categorization: A comparison of classification schemes , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[26]  Stefan Hinz,et al.  Extraction and motion estimation of vehicles in single-pass airborne LiDAR data towards urban traffic analysis , 2011 .

[27]  V. Willhoeft,et al.  Object tracking and classification using laserscanners-pedestrian recognition in urban environment , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[28]  Junxuan Zhao,et al.  Automatic Vehicle Tracking With Roadside LiDAR Data for the Connected-Vehicles System , 2019, IEEE Intelligent Systems.

[29]  Yuan Tian,et al.  Real-Time Queue Length Detection with Roadside LiDAR Data , 2020, Sensors.

[30]  Bowen Gong,et al.  Passenger Flow Prediction Based on Land Use around Metro Stations: A Case Study , 2020, Sustainability.

[31]  Hao Xu,et al.  Revolution and rotation-based method for roadside LiDAR data integration , 2019 .

[32]  Samy Missoum.  Controlling structural failure modes during an impact in the presence of uncertainties , 2007 .

[33]  Yangwoo Kim,et al.  A Two-Stage Big Data Analytics Framework with Real World Applications Using Spark Machine Learning and Long Short-Term Memory Network , 2018, Symmetry.

[34]  Junxuan Zhao,et al.  An automatic lane identification method for the roadside light detection and ranging sensor , 2020, J. Intell. Transp. Syst..

[35]  Yao-Jan Wu,et al.  Video-Based Vehicle Detection and Tracking Using Spatiotemporal Maps , 2009 .

[36]  Simon Fong,et al.  CNN-based 3D object classification using Hough space of LiDAR point clouds , 2020, Human-centric Computing and Information Sciences.

[37]  Osama Masoud,et al.  Vision-based vehicle classification , 2000, ITSC2000. 2000 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.00TH8493).

[38]  Cheol Oh,et al.  Development of probabilistic pedestrian fatality model for characterizing pedestrian-vehicle collisions , 2008 .

[39]  Junxuan Zhao,et al.  Detection and tracking of pedestrians and vehicles using roadside LiDAR sensors , 2019, Transportation Research Part C: Emerging Technologies.

[40]  Zong Tian,et al.  Automatic Vehicle Classification using Roadside LiDAR Data , 2019, Transportation Research Record: Journal of the Transportation Research Board.

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

[42]  S. M. Mahbubur Rahman,et al.  Detection and Classification of Vehicles From Video Using Multiple Time-Spatial Images , 2012, IEEE Transactions on Intelligent Transportation Systems.

[43]  Wei Liu,et al.  Points Registration for Roadside LiDAR Sensors , 2019, Transportation Research Record: Journal of the Transportation Research Board.

[44]  Suliman A. Gargoum,et al.  Automated Highway Sign Extraction Using Lidar Data , 2017 .

[45]  Guohui Zhang,et al.  Video-Based Vehicle Detection and Classification System for Real-Time Traffic Data Collection Using Uncalibrated Video Cameras , 2007, Transportation Research Record: Journal of the Transportation Research Board.

[46]  Bowen Gong,et al.  Background Point Filtering of Low-Channel Infrastructure-Based LiDAR Data Using a Slice-Based Projection Filtering Algorithm , 2020, Sensors.