Raster-Based Background Filtering for Roadside LiDAR Data

Lv, Bin; Xu, Hao; Jian, Wu; Tian, Yuan; Cao, Yuan

doi:10.1109/access.2019.2919624

Cited by 32 publications

(18 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The volumetric-based method converts the LiDAR data into the volumetric space with the rasterization procedure, which is also called the raster-based method [16]. The volumetric-based method usually divides the space into small cubes after aggregating multiple frames.…”

Section: Related Workmentioning

confidence: 99%

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

Song

Zhang²,

Liu³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The connected vehicle environment is significant for the future road network. For constructing the connected vehicle environment, real-time data acquirement is always the prerequisite. Recently, using Light Detection and Ranging (LiDAR)-based roadside infrastructures are becoming a prevalent method of obtaining real-time traffic data. However, the collected raw data from LiDAR cannot usually be used directly. The steps of data processing, like background filtering and object detection, are necessary. The processed data can then be employed in different applications. This paper proposed a novel layer-based searching method that is established with the help of the point distribution features to distinguish moving objects from the point cloud. It aimed to address the unexpected influence of factors such as congested situations and package loss. The new approach was also evaluated compared with the state-of-the-art methods by applying field data. The results showed that the proposed method is more effective than other methods. This method may be applicable to other types of rotating LiDAR for improving the background filtering performance.

show abstract

Section: Related Workmentioning

confidence: 99%

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

Song

Zhang²,

Liu³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Figure 1 shows an example of before-and-after background filtering. The previous studies [33][34][35] showed that 3D-DSF can exclude more than 95% of background points from the raw LiDAR data.…”

Section: Background Filteringmentioning

confidence: 99%

Real-Time Queue Length Detection with Roadside LiDAR Data

Zhang

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Real-time queue length information is an important input for many traffic applications. This paper presents a novel method for real-time queue length detection with roadside LiDAR data. Vehicles on the road were continuously tracked with the LiDAR data processing procedures (including background filtering, point clustering, object classification, lane identification and object association). A detailed method to identify the vehicle at the end of the queue considering the occlusion issue and package loss issue was documented in this study. The proposed method can provide real-time queue length information. The performance of the proposed queue length detection method was evaluated with the ground-truth data collected from three sites in Reno, Nevada. Results show the proposed method can achieve an average of 98% accuracy at the six investigated sites. The errors in the queue length detection were also diagnosed.

show abstract

“…The roadside LiDAR technology provides a good solution for HRMTD collection. Compared with the traditional methods (camera/video and radar), the LiDAR sensor usually have a higher resolution and cover a wide detecting range [15]. Furthermore, the LiDAR is insensitive for light variation.…”

Section: High-resolution Micro Traffic Data (Hrmtd) Collection Wimentioning

confidence: 99%

“…However, the object of interest for our research is road users, which means the background points (surrounding buildings, trees, and ground surface) should be excluded from the space. A raster-based method (RA) was developed to exclude background points based on the features of point distribution in the space [15]. RA is a volumetric processing method for the point clouds.…”

Section: High-resolution Micro Traffic Data (Hrmtd) Collection Wimentioning

confidence: 99%

“…It was found that the change of point density in the background cubes followed a normal-like distribution and the change of point density in the non-background cubes followed a constant trend at different frames. This study considered the cube with the change of point number higher than 2 in two adjacent frames as non-background, as recommended by Lv et al [15]. Fig.…”

Section: High-resolution Micro Traffic Data (Hrmtd) Collection Wimentioning

confidence: 99%

See 1 more Smart Citation

An Automatic Trigged Rectangular Rapid Flashing Beacons (RRFB) System Using the Roadside LiDAR Sensor

Cui

Jian

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

The existing rectangular rapid flashing beacons (RRFB) could not be automatically trigged with acceptable accuracy. This paper introduces a strategy to develop an automatic trigged RRFB system using the roadside Light Detection and Ranging (LiDAR). The trajectories of the road users can be extracted in real-time with the proposed LiDAR data processing algorithms. The pedestrian/bicycle crossing intention was predicted with Naïve Bayes (NB) classifier. Different detection zones were provided to detect the pedestrian/bicycle crossing movements in real-time. The updated RRFB system was implemented at one intersection in Henderson, Nevada, United States. The results of the field test showed that the overall false rate of the updated RRFB system is very low (0.68%). The performance of the proposed method is superior compared to the state-of-the-art method. The updated RRFB system can greatly improve pedestrian safety at unsignalized intersections. INDEX TERMS Roadside LiDAR, vehicle-pedestrian conflicts, object tracking, rectangular rapid flashing beacons, pedestrian safety.

show abstract

Raster-Based Background Filtering for Roadside LiDAR Data

Cited by 32 publications

References 37 publications

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

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

Real-Time Queue Length Detection with Roadside LiDAR Data

An Automatic Trigged Rectangular Rapid Flashing Beacons (RRFB) System Using the Roadside LiDAR Sensor

Contact Info

Product

Resources

About