3D Scene Reconstruction with Sparse LiDAR Data and Monocular Image in Single Frame

Zhong, Yuanxin; Wang, Sijia; Xie, Shichao; Cao, Zhong; Jiang, Kun; Yang, Daoguo

doi:10.4271/07-11-01-0005

Cited by 17 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has significant implications as it allows us to not only make better-informed decisions but also to fully exploit the capabilities of each sensor in their respective domains. An example of this is the projection of semantic information from images labelled by a CNN to create a labelled pointcloud [5], [6], or using 2D object bounding boxes to generate 3D frustums as region proposals for 3D object detection [7], [8].…”

Section: Antonmentioning

confidence: 99%

Optimising the selection of samples for robust lidar camera calibration

Tsai

Shan

Lohr³

et al. 2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

We propose a robust calibration pipeline that optimises the selection of calibration samples for the estimation of calibration parameters that fit the entire scene. We minimise user error by automating the data selection process according to a metric, called Variability of Quality (VOQ) that gives a score to each calibration set of samples. We show that this VOQ score is correlated with the estimated calibration parameter's ability to generalise well to the entire scene, thereby overcoming the overfitting problems of existing calibration algorithms. Our approach has the benefits of simplifying the calibration process for practitioners of any calibration expertise level and providing an objective measure of the quality for our calibration pipeline's input and output data. We additionally use a novel method of assessing the accuracy of the calibration parameters. It involves computing reprojection errors for the entire scene to ensure that the parameters are well fitted to all features in the scene. Our proposed calibration pipeline takes 90s, and obtains an average reprojection error of 1-1.2cm, with standard deviation of 0.4-0.5cm over 46 poses evenly distributed in a scene. This process has been validated by experimentation on a high resolution, software definable lidar, Baraja Spectrum-Scan™; and a low, fixed resolution lidar, Velodyne VLP-16. We have shown that despite the vast differences in lidar technologies, our proposed approach manages to estimate robust calibration parameters for both. Our code and data set used for this paper are made available at https://gitlab.acfr.usyd.edu.au/its/ cam_lidar_calibration.

show abstract

Section: Antonmentioning

confidence: 99%

Optimising the selection of samples for robust lidar camera calibration

Tsai

Shan

Lohr³

et al. 2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

show abstract

“…It works mainly through the use of relevant instruments to obtain two-dimensional image data information for objects. The acquired data information is then analyzed and processed and, finally, the theory of 3D reconstruction is used to reconstruct the contour information for the object surface in the real environment [2][3][4][5][6][7][8][9]. Vision-based 3D reconstruction technology has been widely used in the fields of unmanned vehicles [10], virtual reality [11], 3D printing [12], and engineering surveys [13].…”

Section: Introductionmentioning

confidence: 99%

Scene Reconstruction Algorithm for Unstructured Weak-Texture Regions Based on Stereo Vision

et al. 2023

View full text Add to dashboard Cite

At present, Chinese 3D reconstruction solutions using stereo cameras mainly face known, indoor, structured scenes; for the reconstruction of unstructured, larger-scale scenes with a large variety of texture information of different intensities, there are certain difficulties in ensuring accuracy and real-time processing. For the above problems, we propose a scene reconstruction method using stereo vision. Firstly, considering the influence of outdoor lighting and weather on the captured 2D images, the optimized SAD-FAST feature detection algorithm and stereo-matching strategy were employed in the stereo-matching stage to improve the overall efficiency and matching quality at this stage. Then, a homogenized feature extraction algorithm with gradient value decreasing step by step (GVDS) was used in the depth value calculation to ensure a sufficient number of feature points for strong texture information while extracting features from weak-texture areas, which greatly improved the quality and speed of unstructured scene reconstruction. We conducted experiments to validate the proposed method, and the results showed the feasibility of the proposed method and its high practical value.

show abstract

“…The creation of new vehicles is impossible without computer modeling [1]. Modern vehicles have numerous electronic systems that increase its traffic safety ABS, ESP, ACC, driving comfort, route planning [2][3][4], image processing [5] and autonomous driving soon. All modern systems are integrated and must ensure the safety and comfort of passengers.…”

Section: Introductionmentioning

confidence: 99%

Determination of the parameters of the curvilinear movement of vehicles

Petrov

Абрамов

2023

E3S Web of Conf.

View full text Add to dashboard Cite

Today, the creation of new vehicles is impossible without computer modeling. Modern vehicles have numerous electronic systems that increase its traffic safety, comfort, and route planning management. Reliable operation of all systems is achieved by using an accurate dynamic model of the vehicle to assess safety and the possibility of movement along specified trajectories. Creating an accurate dynamic vehicle model requires correct initial parameters. When modeling the curvilinear movement of motor vehicles, such parameters as the coefficients of resistance to lateral sliding of tires and the angles of sliding of axles, which are mainly determined on test benches in laboratory conditions, are important to obtain the adequacy of the object under study. However, quite often it is impossible to obtain reliable information from tire manufacturers or testing laboratories, which ultimately affects the adequacy of modeling the parameters of vehicle movement. A method is proposed for determining the design parameters of tires using primary information sensors, which are sensors of angular and linear velocities, linear accelerations, rotation angles of controlled wheels and an on-board information processing device. The advantages of this method are that it allows real-time measurement of the angles of the axles and the coefficients of resistance to the lateral withdrawal of the axles when the vehicle is moving at an arbitrary speed along a trajectory of variable curvature. This method can be used to create an accurate dynamic model in the study of the controllability and stability of the vehicle, as well as an integral part of the vehicle dynamics control system.

show abstract

3D Scene Reconstruction with Sparse LiDAR Data and Monocular Image in Single Frame

Cited by 17 publications

References 16 publications

Optimising the selection of samples for robust lidar camera calibration

Optimising the selection of samples for robust lidar camera calibration

Scene Reconstruction Algorithm for Unstructured Weak-Texture Regions Based on Stereo Vision

Determination of the parameters of the curvilinear movement of vehicles

Contact Info

Product

Resources

About