Learning-Based Distortion Correction and Feature Detection for High Precision and Robust Camera Calibration

Zhang, Yesheng; Zhao, Xu; Qian, Dahong

doi:10.1109/lra.2022.3192610

Cited by 15 publications

(18 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Much development post-2019 has focused on calibration using few or single images, 24 – 27 calibration of atypical camera types or cameras in combination with other sensors, 28 – 33 or improvements of target fiducial detection 34 – 36 However, alternative methods of data collection and processing in Zhang-like algorithms continue to be explored, as shown in Table 1.…”

Section: Related Studiesmentioning

confidence: 99%

Precision camera calibration using known target motions along three perpendicular axes

Shkurti,

Nahari,

Newman

et al. 2024

Opt. Eng.

View full text Add to dashboard Cite

We present a method for precision intrinsic calibration of pinhole-model cameras. We refer to this method as "3-Axis." The algorithm employs a target moving with known displacements along three perpendicular axes to decrease the number of unknown terms that must be determined. This method along with new evaluation strategies for comparing the accuracy of pinhole camera calibration algorithms is described in detail. The 3-Axis approach is then compared with the current stateof-the art algorithms in simulated and physical settings and is shown to exceed them in accuracy and computational performance assuming an equal number of samples acquired.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Precision camera calibration using known target motions along three perpendicular axes

Shkurti,

Nahari,

Newman

et al. 2024

Opt. Eng.

View full text Add to dashboard Cite

show abstract

“…Firstly, various types of distortion [1,2] existing in image data (such as radial distortion and tangential distortion) need to be accurately identified and modelled in order to achieve effective repair. Traditional image correction methods use camera calibration technology to obtain internal parameters and distortion parameters of the camera [3,4] and then use these parameters to correct the image. While these methods work well under sufficient prior conditions, they are not expected to work well under limited conditions.…”

Section: Introductionmentioning

confidence: 99%

A Method of Image Restoration for Distortion of Object in Water-Air Cross-Media

Gao,

Jia,

Cai

et al. 2024

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Uneven water-air media distribution or irregular liquid flow can cause changes in light propagation, leading to blurring and distortion of the extracted image, which presents a challenge for object recognition accuracy. To address these issues, this paper proposes a repair network to correct object image distortion in water-air cross-media. Firstly, convolutional combination performs feature extraction on water-air cross-media images, which retains the same features at the same scale and marks feature points with large differences. Then, an attention correction module for geometric lines is proposed to correct geometric lines in water-air cross-media images by comparing and sensing the marked feature points with large differences and utilizing the line similarity in positive and negative samples. Finally, the blurring artifact elimination module eliminates artifacts caused by image blurring and geometric line correction by using multiscale fusion of individual U-Net information streams. This completes the image restoration of object distortion under water-air cross-media. The proposed method is feasible and effective for restoring aberrated objects in water-air cross-media environments, with numerous experiments conducted on water-air cross-media image datasets.

show abstract

“…With the rapid development of deep learning, a convolution neural network is introduced to detect the board pattern. Zhang et al (2022) proposed a learning‐based framework to accurately detect the corner with a learned heatmap, but it required a specially designed post‐processing stage to increase the detection stability. Wu & Wan (2021) trained the linear detection network on the synthetic data for the X‐Junction corner.…”

Section: Introductionmentioning

confidence: 99%

Learning‐based encoded target detection on iteratively orthorectified images for accurate fisheye calibration

Dong

Yao

Gong

et al. 2023

The Photogrammetric Record

View full text Add to dashboard Cite

Fisheye camera calibration is an essential task in photogrammetry. However, previous calibration patterns and the robustness of the adjoint processing methods are limited due to the fisheye distortion and various lighting. This problem leads to additional manual intervention in the data collection. Moreover, it is arduous to accurately detect the board target under fisheye's distortion. To increase the robustness in this task, we present a novel encoded board “Meta‐Board” and a learning‐based target detection method. Additionally, an automatic image orthorectification is integrated to alleviate the distortion effect on the target iteratively until convergence. A low‐cost control field with the proposed boards is built for the experiment. Results on both virtual and real camera lenses and multi‐camera rigs show that our method can be robustly used in calibrating the fisheye camera and reaches state‐of‐the‐art accuracy.

show abstract

Learning-Based Distortion Correction and Feature Detection for High Precision and Robust Camera Calibration

Cited by 15 publications

References 28 publications

Precision camera calibration using known target motions along three perpendicular axes

Precision camera calibration using known target motions along three perpendicular axes

A Method of Image Restoration for Distortion of Object in Water-Air Cross-Media

Learning‐based encoded target detection on iteratively orthorectified images for accurate fisheye calibration

Contact Info

Product

Resources

About