On-site calibration method for outdoor binocular stereo vision sensors

Liu, Zhen; Yin, Yong; Wu, Qun; Li, Xiaojing; Zhang, Guangjun

doi:10.1016/j.optlaseng.2016.05.015

Cited by 16 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three-dimensional measurement technology is widely applied in significant domains [ 1 ], such as aviation, aerospace, and nuclear energy, primarily facilitating tasks such as defect detection and dimensional measurement [ 2 , 3 , 4 , 5 ]. This technology encompasses stereovision [ 6 ], line laser scanning [ 7 ], and structured light illumination (SLI). Among these methods, SLI stands out for its higher applicability and growth potential due to its advantages in terms of high speed, high precision, and cost-effectiveness.…”

Section: Introductionmentioning

confidence: 99%

Quaternary Categorization Strategy for Reconstructing High-Reflectivity Surface in Structured Light Illumination

Xu,

Qu,

et al. 2023

Sensors

View full text Add to dashboard Cite

Structured light illumination is widely applied for surface defect detection due to its advantages in terms of speed, precision, and non-contact capabilities. However, the high reflectivity of metal surfaces often results in the loss of point clouds, thus reducing the measurement accuracy. In this paper, we propose a novel quaternary categorization strategy to address the high-reflectivity issue. Firstly, we classify the pixels into four types according to the phase map characteristics. Secondly, we apply tailored optimization and reconstruction strategies to each type of pixel. Finally, we fuse point clouds from multi-type pixels to accomplish precise measurements of high-reflectivity surfaces. Experimental results show that our strategy effectively reduces the high-reflectivity error when measuring metal surfaces and exhibits stronger robustness against noise compared to the conventional method.

show abstract

Section: Introductionmentioning

confidence: 99%

Quaternary Categorization Strategy for Reconstructing High-Reflectivity Surface in Structured Light Illumination

Xu,

Qu,

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…This greatly improved the practicability of the measurement system, but the algorithm is sensitive to the size of the template matching, which affects the calculation of the position information to a certain extent. Liu [22] focused on the camera calibration of BSV and proposed an online calibration method based on dual parallel cylindrical targets and linear laser projectors. This method does not require feature points or contour information of the target image, and the camera calibration process can be completed by obtaining the laser strip of the target image, but the algorithm has a high computational cost and the universality is weak.…”

Section: Introductionmentioning

confidence: 99%

Recognition and Depth Estimation of Ships Based on Binocular Stereo Vision

Zheng

Liu

Qian

et al. 2022

JMSE

View full text Add to dashboard Cite

To improve the navigation safety of inland river ships and enrich the methods of environmental perception, this paper studies the recognition and depth estimation of inland river ships based on binocular stereo vision (BSV). In the stage of ship recognition, considering the computational pressure brought by the huge network parameters of the classic YOLOv4 model, the MobileNetV1 network was proposed as the feature extraction module of the YOLOv4 model. The results indicate that the mAP value of the MobileNetV1-YOLOv4 model reaches 89.25%, the weight size of the backbone network was only 47.6 M, which greatly reduced the amount of computation while ensuring the recognition accuracy. In the stage of depth estimation, this paper proposes a feature point detection and matching algorithm based on the ORB algorithm at sub-pixel level, that is, firstly, the FSRCNN algorithm was used to perform super-resolution reconstruction of the original image, to further increase the density of image feature points and detection accuracy, which was more conducive to the calculation of the image parallax value. The ships’ depth estimation results indicate that when the distance to the target is about 300 m, the depth estimation error is less than 3%, which meets the depth estimation needs of inland ships. The ship target recognition and depth estimation technology based on BSV proposed in this paper makes up for the shortcomings of the existing environmental perception methods, improves the navigation safety of ships to a certain extent, and greatly promotes the development of intelligent ships in the future.

show abstract

“…While the target is large volume and inconvenient placement. Liu et al [26] proposed a calibration method when camera equipped with filters by double-cylinder and auxiliary laser. Nevertheless, the size of double cylinder is limited and the elliptical stripe is easily affected by the size of cylinder and background, which is not suitable for large space calibration.…”

Section: Introductionmentioning

confidence: 99%

High-Accuracy Calibration of On-Site Multi-Vision Sensors Based on Flexible and Optimal 3D Field

2019

Self Cite

View full text Add to dashboard Cite

Global calibration of multi-vision sensors in the railway fields is easily affected by on-site complex environments, such as lighting and self-occlusion, which makes it difficult for existing methods to achieve high-accuracy calibration. In this paper, a high-accuracy and flexible calibration method of multi-vision sensors in the outdoor railway fields based on flexible and optimal 3D data field through the combination of articular arm and metal target embedded with luminescent LEDs is proposed. Firstly, a high-accuracy and flexible 3D data field with multiple angles and views is constructed by the articular arm and the metal target rapidly; Secondly, the high-frequency multi-exposure imaging mode and multi-scale image feature points extraction are adopted, and the high-accuracy reposition is achieved through Kalman filter, which can reduce the impact of image noise efficiently; Finally, the RANSAC method is utilized to optimize the 3D data field, forming the optimal 3D data field, and the optimal target chains corresponding to each group of cameras are established. The maximum likelihood solution of global parameters is solved by nonlinear optimization. Simulation experiments verify the feasibility of the proposed method. Meanwhile, physical experiment results show this method can reduce the outdoor environment impact and improve the calibration and measurement precision effectively. In addition, the computational efficiency of the proposed method is about 11.2 times than multi-images averaging method, the calibration and measurement accuracy improve about 20 and 2.9 times respectively, which is suitable for the high-accuracy and flexible global calibration in the complex railway environment. INDEX TERMS Flexible, global calibration, high-accuracy, multi-vision sensors, optimal, 3D data field.

show abstract

On-site calibration method for outdoor binocular stereo vision sensors

Cited by 16 publications

References 22 publications

Quaternary Categorization Strategy for Reconstructing High-Reflectivity Surface in Structured Light Illumination

Quaternary Categorization Strategy for Reconstructing High-Reflectivity Surface in Structured Light Illumination

Recognition and Depth Estimation of Ships Based on Binocular Stereo Vision

High-Accuracy Calibration of On-Site Multi-Vision Sensors Based on Flexible and Optimal 3D Field

Contact Info

Product

Resources

About