Automatic Background Filtering Method for Roadside LiDAR Data

Abstract

The high-resolution micro traffic data (HRMTD) of all roadway users is important for serving the connected-vehicle system in mixed traffic situations. The roadside LiDAR sensor gives a solution to providing HRMTD from real-time 3D point clouds of its scanned objects. Background filtering is the preprocessing step to obtain the HRMTD of different roadway users from roadside LiDAR data. It can significantly reduce the data processing time and improve the vehicle/pedestrian identification accuracy. An algorithm is proposed in this paper, based on the spatial distribution of laser points, which filters both static and moving background efficiently. Various thresholds of point density are applied in this algorithm to exclude background at different distances from the roadside sensor. The case study shows that the algorithm can filter background LiDAR points in different situations (different road geometries, different traffic demands, day/night time, different speed limits). Vehicle and pedestrian shape can be retained well after background filtering. The low computational load guarantees this method can be applied for real-time data processing such as vehicle monitoring and pedestrian tracking.

Data Registration with Ground Points for Roadside LiDAR Sensors

“…The advantages of LiDAR sensors and the recently reduced unit prices triggered the innovative application of LiDAR sensors at traffic infrastructures, which can uniquely offer high-resolution high-accuracy trajectory data of all traffic users [41][42][43][44]. The deployment of LiDAR sensors provides the data required by connected-vehicle systems and will reform different areas of traffic engineering and research.…”

Background Filtering and Object Detection With a Stationary LiDAR Using a Layer-Based Method

“…Since the density of background points is higher than that of the moving object points after aggregation, the cube can be distinguished into background cube or non-background cube by giving a pre-defined density threshold. Wu et al [18] firstly provided a fixed threshold of point density in the cube for background filtering based on their experience. A dynamic threshold was then developed by considering the point distribution and the mechanical properties of the LiDAR, namely, three-dimensional density-spatial filtering (3D-DSF).…”

Real-Time Queue Length Detection with Roadside LiDAR Data

“…The scanning rate of the LiDAR is set as 10 Hz. The proposed vehicle detection procedure includes five major steps: background filtering [26], point clustering [27], object classification [28,29], lane identification [30,31] and object association [32]. Vehicle trajectories can be generated with the proposed method.…”

“…By giving a pre-defined threshold of point density, the location of the cubes representing background can be then identified and stored in a 3D array. An automatic threshold identification method was well documented in the reference [26]. Any point located in the 3D array was then excluded from the space.…”

“…The 3D-DSF first integrated the data collected in a time period (such as 5 minutes of data) into one space based on the XYZ coordinates of the LiDAR points. The whole space was then rasterized into small cubes with the same side length (0.1 m was used as the side length considering the accuracy and the computation load) [26]. The point density of the cubes representing the background should be higher than that of the cubes representing the moving objects after frame aggregation.…”