An official website of the United States government
This paper develops a cost-effective vehicle detection and tracking system based on fusion of a 2-D LIDAR and a monocular camera to protect electric micromobility devices, especially e-scooters, by predicting the real- time danger of a car- scooter collision. The cost and size disadvantages of 3-D LIDAR sensors make them an unsuitable choice for micromobility devices. Therefore, a 2-D RPLIDAR Mapper sensor is used. Although low-cost, this sensor comes with major shortcomings such as the narrow vertical field of view and its low density of data points. Due to these factors, the sensor does not have a robust output in outdoor applications, and the measurements keep jumping and sliding on the vehicle surface. To improve the performance of the LIDAR, a single monocular camera is fused with the LIDAR data not only to detect vehicles, but also to separately detect the front and side of a target vehicle and to find its corner. It is shown that this corner detection method is more accurate than strategies that are only based on the LIDAR data. The corner measurements are used in a high-gain observer to estimate the location, velocity, and orientation of the target vehicle. The developed system is implemented on a Ninebot e-scooter platform, and multiple experiments are performed to evaluate the performance of the algorithm.
more »
« less
Using spatiotemporal stacks for precise vehicle tracking from roadside 3D LiDAR data
This paper develops a non-model based vehicle tracking methodology for extracting road user trajectories as they pass through the field of view of a 3D LiDAR sensor mounted on the side of the road. To minimize the errors, our work breaks from conventional practice and postpones target segmentation until after collecting LiDAR returns over many scans. Specifically, our method excludes all non-vehicle returns in each scan and retains the ungrouped vehicle returns. These vehicle returns are stored over time in a spatiotemporal stack (ST stack) and we develop a vehicle motion estimation framework to cluster the returns from the ST stack into distinct vehicles and extract their trajectories. This processing includes removing the impacts of the target's changing orientation relative to the LiDAR sensor while separately taking care to preserve the crisp transition to/from a stop that would normally be washed out by conventional data smoothing or filtering. This proof of concept study develops the methodology using a single LiDAR sensor, thus, limiting the surveillance region to the effective range of the given sensor. It should be clear from the presentation that, provided sufficient georeferencing, the surveillance region can be extended indefinitely by deploying multiple LiDAR sensors with overlapping fields of view.
more »
« less
- Award ID(s):
- 2023857
- PAR ID:
- 10560107
- Publisher / Repository:
- https://www.sciencedirect.com/science/article/pii/S0968090X23002693
- Date Published:
- Journal Name:
- Transportation Research Part C: Emerging Technologies
- Volume:
- 154
- Issue:
- C
- ISSN:
- 0968-090X
- Page Range / eLocation ID:
- 104280
- Subject(s) / Keyword(s):
- LiDAR Vehicle Tracking Spatiotemporal Stacks Highway Traffic Vehicle Trajectories
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
LiDAR data were acquired over the footprint of the flux tower and established long-term study plots at Thompson Farm Observatory, Durham, NH during the growing season. Data were acquired using a LiVox Avia lidar sensor on a Green Valley International LiAirV70 payload. The LiVox Avia is a triple echo 905 nm lidar sensor with a non-repetitive circular scanning pattern that can retrieve ~700,000 returns per second. The sensor payload was flown on board a DJI M300 at an altitude of ~65 m above ground level in a double grid pattern with ~32 m flight line spacing, yielding a return density across the sampling area >500 points per square meter. Returns were georeferenced to WGS84 UTM Zone 19N coordinates with heights above ellipsoid using Green Valley International’s LiGeoreference software with automatic boresight calibration. Outliers were removed, then flight line point clouds were merged. Returns were classified as ground and non-ground returns using Green Valley International’s Lidar360 software and output as LAS (v 1.4) data sets. LAS files were subsequently tiled for publication.more » « less
-
LiDAR data were acquired over the footprint of the flux tower and established long-term study plots at Thompson Farm Observatory, Durham, NH during leaf-off conditions in November 2022. Data were acquired using a LiVox Avia lidar sensor on a Green Valley International LiAirV70 payload. The LiVox Avia is a triple echo 905 nm lidar sensor with a non-repetitive circular scanning pattern that can retrieve ~700,000 returns per second. The sensor payload was flown on board a DJI M300 at an altitude of ~65 m above ground level in a double grid pattern with ~32 m flight line spacing, yielding a return density across the sampling area >500 points per square meter. Returns were georeferenced to WGS84 UTM Zone 19N coordinates with heights above ellipsoid using Green Valley International’s LiGeoreference software with automatic boresight calibration. Outliers were removed, then flight line point clouds were merged. Returns were classified as ground and non-ground returns using Green Valley International’s Lidar360 software and output as LAS (v 1.4) data sets. LAS files were subsequently tiled for publication.more » « less
-
This paper presents a cost-effective, non-intrusive, and easy-to-deploy traffic count data collection method using two-dimensional light-detection and ranging (LiDAR) technology. The proposed method integrates a LiDAR sensor, continuous wavelet transform (CWT), and support vector machine (SVM) into a single framework for traffic count. LiDAR is adopted since the technology is economical and easily accessible. Moreover, its 360° visibility and accurate distance information make it more reliable compared with radar, which uses electromagnetic waves instead of light rays. The obtained distance data are converted into the signals. CWT is employed to detect any deviation in distance profile, because of its efficiency in detecting modest changes over a period of time. SVM is one of the supervised machine learning tools for data classification and regression. In the methodology, the SVM is applied to classify the distance data points obtained from the sensor into detection and non-detection cases, which are highly complex. Proof-of-concept (POC) test is conducted in three different places in Newark, New Jersey, to examine the performance of the proposed method. The POC test results demonstrate that the proposed method achieves acceptable performances in vehicle count collection, resulting in 83–94% accuracy. It is discovered that the accuracy of the proposed method is affected by the color of the exterior surface of a vehicle.more » « less
-
Vehicles can easily lose control unexpectedly when encountering unforeseen hazardous road friction conditions. With automation and connectivity increasingly available to assist drivers, vehicle performance can significantly benefit from a road friction preview map, particularly to identify where and how friction ahead of a vehicle may be suddenly decreasing. Although many techniques enable the vehicle to measure the local friction as driving upon a surface, these encounters limit the ability of a vehicle to slow down before a low-friction surface is already encountered. Using the connectivity of connected and autonomous vehicles (CAVs), a global road friction map can be created by aggregating information from vehicles. A challenge in the creation of these global friction maps is the very large quantity of data involved, and that the measurements populating the map are generated by vehicle trajectories that do not uniformly cover the grid. This paper presents a road friction map generation strategy that aggregates the measured road-tire friction coefficients along the individual trajectories of CAVs into a road surface grid. In addition, through clustering the friction grids further, an insight of this work is that the friction map can be represented compactly by rectangular boxes defined by a pair of corner coordinates in space, a friction value, and a confidence interval within the box. To demonstrate the method, a simulation is presented that integrates traffic simulations, vehicle dynamics and on-vehicle friction estimators, and a highway road surface, where friction is changing in space, particularly over a bridge segment. The experimental results indicate that the road friction distribution can be measured effectively by collecting and aggregating the friction data from CAVs.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1016/j.trc.2023.104280
