ROCHADE: Robust Checkerboard Advanced Detection for Camera Calibration

Abstract

We present a new checkerboard detection algorithm which is able to detect checkerboards at extreme poses, or checkerboards which are highly distorted due to lens distortion even on low-resolution images. On the detected pattern we apply a surface fitting based subpixel refinement specifically tailored for checkerboard X-junctions. Finally, we investigate how the accuracy of a checkerboard detector affects the overall calibration result in multi-camera setups. The proposed method is evaluated on real images captured with different camera models to show its wide applicability. Quantitative comparisons to OpenCV's checkerboard detector show that the proposed method detects up to 80% more checkerboards and detects corner points more accurately, even under strong perspective distortion as often present in wide baseline stereo setups.

Accurate Camera Calibration Robust to Defocus Using a Smartphone

“…In real experiments, the accuracy and the validity of the proposed method are verified in various perspectives. Methods for comparison The proposed feature refinement algorithm is compared with three existing methods: the Harris corner detector [7] which is one of the most representative corner detectors, and the two recent corner refinement methods by Geiger et al [5] and Placht et al [17]. Given an initial feature location, Geiger et al [5] estimate the corner by finding the local maximum point of cornerness.…”

“…By adding the separately calculated skeleton masks, the initial mask for our feature grid is obtained. To find initial feature points on this grid mask, we utilize the checkerboard detection algorithm proposed in [17]. This detection algorithm finds initial feature points on the given mask of feature point grid by checking the numbers of neighbor pixels and label the feature points according to their connected relationship as a graph.…”

“…tection, low cost and simple structure [27,12,24,17]. A traditional way of producing a calibration pattern is to print out the pattern on a piece of paper and attach it on a planar board so that the pattern maintains the plane assumption.…”

Accurate laser scanner to camera calibration with application to range sensor evaluation

“…The authors of the pattern detector report 3-D measurement errors between 1 and 7 mm, depending on the sensor resolution [26].…”

“…In this work we use the detector proposed in [26]. With the known dimensions of the patterns and the intrinsic parameters of the camera, the 3-D coordinates of the calibration features (e.g., checkerboard corners) can be calculated.…”