Accurate calibration of intrinsic camera parameters by observing parallel light pairs

Sagawa, Ryusuke; Yagi, Yasushi

doi:10.1109/robot.2008.4543397

Cited by 6 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is the set of matched features (here we ignore all unmatched features), h m : I × I → I 2 is a mapping that represents the features matching algorithm, w m k is the effect of the white noise w k on the matching, and from false feature matching (wrong association), errors in the calibration of the intrinsic parameters of the camera, ... etc [21], [22]. An example of matching errors in the VO pipeline is shown in Fig.…”

Section: Error Modeling In Visual Odometrymentioning

confidence: 99%

Drift Reduction for Monocular Visual Odometry of Intelligent Vehicles Using Feedforward Neural Networks

Wagih

Osman

Awad

et al. 2022

2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

In this paper, an approach for reducing the drift in monocular visual odometry algorithms is proposed based on a feedforward neural network. A visual odometry algorithm computes the incremental motion of the vehicle between the successive camera frames, then integrates these increments to determine the pose of the vehicle. The proposed neural network reduces the errors in the pose estimation of the vehicle which results from the inaccuracies in features detection and matching, camera intrinsic parameters, and so on. These inaccuracies are propagated to the motion estimation of the vehicle causing larger amounts of estimation errors. The drift reducing neural network identifies such errors based on the motion of features in the successive camera frames leading to more accurate incremental motion estimates. The proposed drift reducing neural network is trained and validated using the KITTI dataset and the results show the efficacy of the proposed approach in reducing the errors in the incremental orientation estimation, thus reducing the overall error in the pose estimation.

show abstract

Section: Error Modeling In Visual Odometrymentioning

confidence: 99%

Drift Reduction for Monocular Visual Odometry of Intelligent Vehicles Using Feedforward Neural Networks

Wagih

Osman

Awad

et al. 2022

2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

show abstract

“…Given the singular value decomposition Q=U•S•V, the best rotation matrix is R=U•V T . For further reference to matrix computation, see Golub and Loan [25].…”

Section: Is Used Let C=[h 1 H 2 H 3 ]mentioning

confidence: 99%

The Influence of Autofocus Lenses in the Camera Calibration Process

Ricolfe-Viala

Esparza

2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Camera calibration is a crucial step in robotics and computer vision. Accurate camera parameters are necessary to achieve robust applications. Nowadays, camera calibration process consists of adjusting a set of data to a pin-hole model, assuming that with a reprojection error close to zero, camera parameters are correct. Since all camera parameters are unknown, computed results are considered true. However, the pin-hole model does not represent the camera behavior accurately if the autofocus is considered. Real cameras with autofocus lenses change the focal length slightly to obtain sharp objects in the image and this feature skews the calibration result if a unique pin-hole model is computed with a constant focal length.In this paper, a deep analysis of the camera calibration process is done to detect and strengthen its weaknesses when autofocus lenses is used. To demonstrate that significant errors exist in computed extrinsic parameters, the camera is mounted in a robot arm to know true extrinsic camera parameters with an accuracy under 1mm. It is demonstrated also that errors in extrinsic camera parameters are compensated with bias in intrinsic camera parameters. Since significant errors exist with autofocus lenses, a modification of the widely accepted camera calibration method using images of a planar template is presented. A pin-hole model with distance dependent focal length is proposed to improve the calibration process substantially.

show abstract

“…As the field of computer vision and image processing continues to evolve, camera calibration technology plays a pivotal role in multiple domains. Camera calibration is the process of determining the intrinsic and extrinsic parameters of a camera, providing a crucial foundation for applications such as photogrammetry, 3D reconstruction, augmented reality, and autonomous driving [1]. In the realm of camera calibration research, the Direct Linear Transform (DLT) method has been widely adopted; however, it faces accuracy limitations in certain scenarios, such as correcting lens distortion and calibrating complex scenes.…”

Section: Introductionmentioning

confidence: 99%

Camera calibration method based on improved DLT algorithm

Liu,

Zhou

et al. 2023

Optoelectronic Imaging and Multimedia Technology X

View full text Add to dashboard Cite

Camera calibration is one of the key tasks in the field of computer vision, finding extensive applications in various domains, including photogrammetry, 3D reconstruction, augmented reality, and autonomous driving. The Direct Linear Transform (DLT) algorithm, a classical approach for camera calibration, estimates camera parameters by solving a system of linear equations. However, traditional DLT methods may face accuracy and stability issues when dealing with noise, distortion, and nonlinear effects.To address these limitations, this paper introduces a camera calibration method based on the Improved DLT algorithm. This method incorporates distortion models into the traditional DLT algorithm and utilizes Levenberg-Marquardt (LM) optimization techniques to enhance calibration accuracy and stability. The key steps involve data preparation, DLT estimation, and nonlinear optimization.Experimental results demonstrate that the Improved DLT algorithm outperforms traditional DLT methods, particularly in cameras with significant distortion and wide field of view. It exhibits smaller reprojection errors and achieves a more uniform error distribution, especially at image edges. This research contributes by providing a more accurate and robust camera calibration method, offering valuable tools for computer vision applications, and advancing the development and application of computer vision technology.

show abstract

Accurate calibration of intrinsic camera parameters by observing parallel light pairs

Cited by 6 publications

References 18 publications

Drift Reduction for Monocular Visual Odometry of Intelligent Vehicles Using Feedforward Neural Networks

Drift Reduction for Monocular Visual Odometry of Intelligent Vehicles Using Feedforward Neural Networks

The Influence of Autofocus Lenses in the Camera Calibration Process

Camera calibration method based on improved DLT algorithm

Contact Info

Product

Resources

About