CCDN: Checkerboard Corner Detection Network for Robust Camera Calibration

TL;DR

This paper introduces CCDN, a robust checkerboard corner detection network that maintains high accuracy under poor image conditions, improving camera calibration reliability without prior pattern knowledge.

Contribution

The paper presents a novel fully convolutional network for checkerboard corner detection that is robust to distortions, noise, and extreme poses, with effective post-processing for false positive removal.

Findings

Outperforms state-of-the-art methods in robustness and accuracy

Effective on images with lens distortion, noise, and extreme poses

Demonstrates wide applicability across different datasets

Abstract

Aiming to improve the checkerboard corner detection robustness against the images with poor quality, such as lens distortion, extreme poses, and noise, we propose a novel detection algorithm which can maintain high accuracy on inputs under multiply scenarios without any prior knowledge of the checkerboard pattern. This whole algorithm includes a checkerboard corner detection network and some post-processing techniques. The network model is a fully convolutional network with improvements of loss function and learning rate, which can deal with the images of arbitrary size and produce correspondingly-sized output with a corner score on each pixel by efficient inference and learning. Besides, in order to remove the false positives, we employ three post-processing techniques including threshold related to maximum response, non-maximum suppression, and clustering. Evaluations on two different datasets show its superior robustness, accuracy and wide applicability in quantitative comparisons with the state-of-the-art methods, like MATE, ChESS, ROCHADE and OCamCalib.