Study of a Multi-Beam LiDAR Perception Assessment Model for Real-Time Autonomous Driving

Li, Xiaolu; Zhou, Yier; Bai, Hua

doi:10.1109/tim.2021.3094230

Cited by 21 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technology harnesses acoustic pulse methods to generate an image reflecting the seabed's composition within a designated swath on both sides of the survey vessel. The system employs two transducers, selectively mounted on the survey vessel or towed behind it, equipped with display devices to visualize the echo signals [8] . The intensity of these echoes-a function of the size, shape, and density of the seabed contact points-is meticulously recorded, with the paper's vertical axis representing the vessel's movement along its trajectory.…”

Section: Related Workmentioning

confidence: 99%

Research on multibeam depth measurement optimization model based on genetic algorithm

Wang,

Shi,

Liu

et al. 2024

Fourth International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2024)

View full text Add to dashboard Cite

In recent years, applications ranging from underwater navigation and construction to environmental monitoring and marine resource management have driven an escalating need for accurate and comprehensive bathymetric mapping of the marine environment. However, the complexity of the marine environment requires sound mathematical modeling of survey lines to ensure comprehensive coverage, optimal resource utilization, and high-quality data collection. This work outlines a mathematical model based on geometric and projection relationships in three-dimensional space to simulate a scenario in a designated sea area for bathymetric surveying. By knowing the slope angle of the seabed, assuming a planar seabed and considering the ship's position along a survey line, a model is developed to determine the coverage width of multibeam sonar beams on the seabed. The model involves calculating the water depth at different points along the survey line using the tangent of the slope angle, and then employing trigonometric functions and equations to establish a relationship for the coverage width, which is equal to the length of the segment intersected by the sonar beams on the seabed line. Further, the model accounts for the overlap ratio between adjacent survey stripes to optimize survey line planning for complete area coverage while minimizing resources and time. Additionally, a visualization of the seabed depth variation is suggested through plotting, simplifying the calculation by projecting the varying slope onto a horizontal plane. This approach facilitates the design of survey lines across the sea area, ensuring efficient and comprehensive bathymetric mapping.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on multibeam depth measurement optimization model based on genetic algorithm

Wang,

Shi,

Liu

et al. 2024

Fourth International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2024)

View full text Add to dashboard Cite

show abstract

“…Three dimensional (3D) environment perception has an important role in the field of autonomous driving [1]. It analyzes the real-time information of the surroundings to ensure traffic safety.…”

Section: Introductionmentioning

confidence: 99%

“…As 3D object detection requires spatial information from the environment, light detection and ranging (LiDAR) is a suitable sensor because it can generate a 3D point cloud in real-time [4]. Thanks to its ranging accuracy and stability, multi-beam mechanical LiDAR is the mainstream LiDAR sensor for environment perception [1,5]. It is referred to as LiDAR henceforth for discussion simplicity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging Self-Paced Semi-Supervised Learning with Prior Knowledge for 3D Object Detection on a LiDAR-Camera System

Liang

Hong

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Three dimensional (3D) object detection with an optical camera and light detection and ranging (LiDAR) is an essential task in the field of mobile robot and autonomous driving. The current 3D object detection method is based on deep learning and is data-hungry. Recently, semi-supervised 3D object detection (SSOD-3D) has emerged as a technique to alleviate the shortage of labeled samples. However, it is still a challenging problem for SSOD-3D to learn 3D object detection from noisy pseudo labels. In this paper, to dynamically filter the unreliable pseudo labels, we first introduce a self-paced SSOD-3D method SPSL-3D. It exploits self-paced learning to automatically adjust the reliability weight of the pseudo label based on its 3D object detection loss. To evaluate the reliability of the pseudo label in accuracy, we present prior knowledge based SPSL-3D (named as PSPSL-3D) to enhance the SPSL-3D with the semantic and structure information provided by a LiDAR-camera system. Extensive experimental results in the public KITTI dataset demonstrate the efficiency of the proposed SPSL-3D and PSPSL-3D.

show abstract

Simple linear iterative clustering based low-cost pseudo-LiDAR for 3D object detection in autonomous driving

Nguyen

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Study of a Multi-Beam LiDAR Perception Assessment Model for Real-Time Autonomous Driving

Cited by 21 publications

References 28 publications

Research on multibeam depth measurement optimization model based on genetic algorithm

Research on multibeam depth measurement optimization model based on genetic algorithm

Leveraging Self-Paced Semi-Supervised Learning with Prior Knowledge for 3D Object Detection on a LiDAR-Camera System

Simple linear iterative clustering based low-cost pseudo-LiDAR for 3D object detection in autonomous driving

Contact Info

Product

Resources

About