A new robust 2D camera calibration method using RANSAC

Lv, Yaowen; Jin, Feng; Li, Zhaokun; Liu, Wei; Cao, Jingtai

doi:10.1016/j.ijleo.2015.09.117

Cited by 18 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Standard RANSAC In computer vision, RANSAC [2] is widely used for robust estimating a model from a data set contaminated by gross error. First a minimal subset of the data is randomly selected from the input data to estimate the model parameters.…”

Section: Locally Optimized Ransacmentioning

confidence: 99%

“…Hence the IAC is crucial for the nonlinear optimization to avoid local optimum. To remove unreliable IAC, the authors [2] defined a distance between the homography and the IAC as follows.…”

Section: Camera Calibration With Lo-ransacmentioning

confidence: 99%

“…This method is flexible, but the performance is not accurate [1]. Moreover, such calibration doesn't consider the lens distortion [2], which restricts its applications. The object based camera calibration is performed by observing a 3D object with known coordinates.…”

Section: Introductionmentioning

confidence: 99%

“…To this end, Lv etc. [2] proposed to use the RANSAC (Random Sample Consensus) [4] to remove the unreliable images. Although the method can get more robust and accurate results than the convention one, the standard RANSAC has some drawbacks: 1) The RANSAC runs much longer (even by an order of magnitude) than theoretically predicted [5]; 2) The assumption in RANSAC, i.e., a model with parameters computed from an outlier-free sample is consistent with all inliers, is not true in practice because there is noise in a real system.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving 2D Camera Calibration by LO-RANSAC

Zhang¹,

Wu²,

Wang³

et al. 2017

(IJIEE

View full text Add to dashboard Cite

Abstract-The performance of the traditional 2D pattern based camera calibration is affected by sample viewpoints, positions and feature point localization. In this paper, the Locally Optimized RANSAC (Random Sample Consensus) (LO-RANSAC) is employed to remove the unreliable information automatically. To be more particular, a distance between a specific circular point and the underlying image of the absolute conic is adopted, and a local optimization is achieved when the so-far-best model in the RANSAC iterations has been reached. The experiments on artificial and real data demonstrate that the proposed method alleviates the randomness of the RANSAC solution and get more accurate and reliable calibration results than the traditional methods.Index Terms-2D camera calibration; RANSAC; Lo-RANSAC.

show abstract

Section: Locally Optimized Ransacmentioning

confidence: 99%

“…Hence the IAC is crucial for the nonlinear optimization to avoid local optimum. To remove unreliable IAC, the authors [2] defined a distance between the homography and the IAC as follows.…”

Section: Camera Calibration With Lo-ransacmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving 2D Camera Calibration by LO-RANSAC

Zhang¹,

Wu²,

Wang³

et al. 2017

(IJIEE

View full text Add to dashboard Cite

show abstract

“…Fig. 5 initial matching results In view of the problem of false matching, the method of random sample consensus [13] algorithm is used to remove the points with poor quality. The refined matching results are shown as Fig.…”

Section: Feature Point Matchingmentioning

confidence: 99%