4.6 Article

Research on an Adaptive Method for the Angle Calibration of Roadside LiDAR Point Clouds

Related references

Note: Only part of the references are listed.
Article Mathematics, Applied

Solution methods to the nearest rotation matrix problem in Double-struck capital R3: A comparative survey

Soheil Sarabandi et al.

Summary: Nowadays, the Singular Value Decomposition (SVD) is commonly used for solving the nearest rotation matrix problem. However, there are many other methods available for the 3D case. This article reviews and proposes alternative methods, and presents a comparative analysis to determine their computational costs and error performances. The analysis concludes that some algebraic closed-form methods are as robust as SVD, but faster and more accurate.

NUMERICAL LINEAR ALGEBRA WITH APPLICATIONS (2023)

Article Chemistry, Analytical

A Novel Point Cloud Registration Method Based on ROPNet

Yuan Li et al.

Summary: This paper introduces a new loss function based on cross-entropy and applies it to the ROPNet point cloud registration model. Additionally, the ROPNet is improved by incorporating channel attention to focus on global and local important information, leading to enhanced registration performance and reduced registration error. Experimental results on the ModelNet40 dataset validate the effectiveness of the proposed method.

SENSORS (2023)

Article Chemistry, Analytical

A Trajectory Compensation Method Considering the Car-Following Behavior for Data Missing of Millimeter-Wave Radar in Roadside Detection Applications

Rui Zhang et al.

Summary: This paper proposes a trajectory compensation method to address the missing data problem of millimeter-wave radar caused by target occlusion or the absence of features in low-speed conditions. A coordinate transformation method is presented to unify the radar spatial coordinates with the road coordinates based on the installation scheme of the detector. Car-following models including the optimal velocity model (OV), full velocity difference model (FVD), and full velocity difference and acceleration (FVDA) model are applied to track the vehicle's trajectory in relation to the movement of the vehicle ahead. The proposed methods are found to be effective for compensating for missing data and reconstructing target trajectories, with the FVDA model performing well compared to the OV and FVD models, as demonstrated by statistical results.

SENSORS (2023)

Article Computer Science, Information Systems

3D Point Cloud Stitching for Object Detection with Wide FoV Using Roadside LiDAR

Xiaowei Lan et al.

Summary: This paper presents a 3D point cloud stitching method for object detection with wide horizontal field of view using roadside LiDAR. The proposed approach improves the detection performance of roadside LiDAR by stitching multiple sets of detection results to build a 360 degrees detection range and solve the problem of overlapping objects.

ELECTRONICS (2023)

Article Chemistry, Analytical

3D LiDAR Point Cloud Registration Based on IMU Preintegration in Coal Mine Roadways

Lin Yang et al.

Summary: This paper proposes a point cloud registration method based on IMU preintegration to solve the problems of registration accuracy decline and z-axis drift caused by point cloud feature differences in coal mine roadway environments. By introducing IMU data and using linear interpolation to correct motion distortion in LiDAR scanning, and constructing IMU preintegration error function, combined with ground segmentation and feature point extraction methods, the point cloud registration is completed by optimizing the constraint relationship using Gaussian Newton method. Experimental results show that compared with traditional methods, this method has higher registration accuracy, success rate, and computational efficiency.

SENSORS (2023)

Article Engineering, Civil

Vehicle Trajectory Tracking Using Adaptive Kalman Filter from Roadside Lidar

Qi Zhang et al.

Summary: Recently, roadside lidar sensors have been utilized to extract high-resolution vehicle trajectory data from the field. However, the current methods for trajectory optimization still face challenges in terms of fluctuations. This paper proposes an effective method for trajectory smoothing using the adaptive Kalman filter, with a multipoint matching algorithm for velocity estimation and a robust adaptive strategy for the Kalman filter. The method shows satisfactory performance when evaluated using field data collected in Reno, Nevada, and it is user-friendly for real-world applications.

JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS (2023)

Article Computer Science, Hardware & Architecture

Vision-based vehicle tracking on highway traffic using bounding-box features to extract statistical information

Jahongir Azimjonov et al.

Summary: A new bounding-box based vehicle tracking algorithm is proposed in this study to extract statistical information in highway traffic. The algorithm successfully detects and tracks vehicles using a novel shaking filter and voting approach, and classifies and determines the time-dependent vehicle trajectory through successive frames.

COMPUTERS & ELECTRICAL ENGINEERING (2022)

Article Automation & Control Systems

Prescribed performance-based tracking control for quadrotor UAV under input delays and input saturations

Bing Zhu et al.

Summary: In this paper, a semi-global trajectory tracking control scheme is proposed for quadrotor UAV with time-varying input delays, input saturations, and bounded disturbances. By introducing error transformation function, state prediction method, and dynamic surface control, the proposed scheme can limit the tracking error within the prescribed bound and ensure that all signals in the closed-loop system are bounded.

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL (2022)

Article Engineering, Electrical & Electronic

Quantifying the performance and optimizing the placement of roadside sensors for cooperative vehicle-infrastructure systems

Yuchuan Du et al.

Summary: This paper investigates the vehicle perception technology of cooperative vehicle-infrastructure systems, which provides perception information beyond the visual range for autonomous vehicles through roadside sensors. By establishing an occlusion degree model and conducting microscopic traffic simulation, the impacts of traffic density, vehicle model composition, and sensor configurations on perception performance are studied, and an optimization model for roadside sensor placement is proposed. A case study demonstrates that the proposed approach significantly improves vehicle perception performance compared to conventional schemes.

IET INTELLIGENT TRANSPORT SYSTEMS (2022)

Article Computer Science, Information Systems

Traffic Sign Based Point Cloud Data Registration with Roadside LiDARs in Complex Traffic Environments

Zheyuan Zhang et al.

Summary: This paper focuses on point cloud registration in a complex traffic environment and proposes a 3D registration method based on traffic signs and prior knowledge of traffic scenes. By using traffic signs with reflective films as reference targets, the point cloud data from roadside LiDARs can be registered. The method includes vertical registration and horizontal registration, and has been verified in actual scenarios.

ELECTRONICS (2022)

Review Chemistry, Analytical

Object Detection Based on Roadside LiDAR for Cooperative Driving Automation: A Review

Pengpeng Sun et al.

Summary: This paper systematically studies methods and datasets for roadside LiDAR perception, which provides important guidance for further promoting the research of roadside LiDAR perception for practical applications.

SENSORS (2022)

Article Computer Science, Artificial Intelligence

3D Multi-Object Tracking With Adaptive Cubature Kalman Filter for Autonomous Driving

Ge Guo et al.

IEEE Transactions on Intelligent Vehicles (2022)

Article Engineering, Electrical & Electronic

Infrared and Visible Image Fusion via Decoupling Network

Xue Wang et al.

Summary: This article proposes a decoupling network-based method for infrared and visible image fusion, which effectively retains the texture details and luminance information of the source images while preserving the high-contrast regions. Extensive experiments demonstrate that the proposed method generates fused images with saliency objects and clear details, outperforming other state-of-the-art methods.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

Proceedings Paper Engineering, Electrical & Electronic

Object Recognition Network using Continuous Roadside Cameras

Gunhee Cho et al.

Summary: This paper proposes an object recognition network architecture using high-definition camera images, which detects and tracks vehicles through edge computing resources and reduces data traffic through a localized backhaul network.

2022 IEEE 95TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2022-SPRING) (2022)

Article Transportation

Determining optimal sensor locations under uncertainty for a truck activity monitoring system on California freeways

Jaeyoung Jung et al.

Summary: This article investigates two proposed strategies for optimally deploying a new hybrid sensor technology on California freeways: a flow-interception approach and a truck re-identification approach. The flow-interception model focuses on selecting locations emphasizing different body types based on flow-based weight factors, while the truck re-identification model aims to identify heavy truck movement by selecting pairwise locations.

JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS (2021)

Article Computer Science, Information Systems

Multi-Sensor Fusion in Automated Driving: A Survey

Zhangjing Wang et al.

IEEE ACCESS (2020)

Article Environmental Sciences

Data Registration with Ground Points for Roadside LiDAR Sensors

Rui Yue et al.

REMOTE SENSING (2019)

Article Chemistry, Analytical

Accurate Calibration of Multi-LiDAR-Multi-Camera Systems

Zoltan Pusztai et al.

SENSORS (2018)

Article Robotics

Motion-Based Calibration of Multimodal Sensor Extrinsics and Timing Offset Estimation

Zachary Taylor et al.

IEEE TRANSACTIONS ON ROBOTICS (2016)

Article Robotics

Vision meets robotics: The KITTI dataset

A. Geiger et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2013)