Multi-Cue-Based Circle Detection and Its Application to Robust Extrinsic Calibration of RGB-D Cameras

Abstract

RGB-Depth (RGB-D) cameras are widely used in computer vision and robotics applications such as 3D modeling and human–computer interaction. To capture 3D information of an object from different viewpoints simultaneously, we need to use multiple RGB-D cameras. To minimize costs, the cameras are often sparsely distributed without shared scene features. Due to the advantage of being visible from different viewpoints, spherical objects have been used for extrinsic calibration of widely-separated cameras. Assuming that the projected shape of the spherical object is circular, this paper presents a multi-cue-based method for detecting circular regions in a single color image. Experimental comparisons with existing methods show that our proposed method accurately detects spherical objects with cluttered backgrounds under different illumination conditions. The circle detection method is then applied to extrinsic calibration of multiple RGB-D cameras, for which we propose to use robust cost functions to reduce errors due to misdetected sphere centers. Through experiments, we show that the proposed method provides accurate calibration results in the presence of outliers and performs better than a least-squares-based method.

Robust alternating optimisation for extrinsic calibration of RGB‐D cameras

“…Subsequently, we show that the alternating optimisation algorithm introduced by Su et al [1] is a special case of our developed alternating optimisation algorithm. Finally, our experiments show that the proposed algorithm with a robust cost function has comparable computation time to Su et al [1] and comparable accuracy to Kwon et al [2]. Using the method in [2], we can estimate the 3D sphere centre in each depth image.…”

“…Finally, our experiments show that the proposed algorithm with a robust cost function has comparable computation time to Su et al [1] and comparable accuracy to Kwon et al [2]. Using the method in [2], we can estimate the 3D sphere centre in each depth image. The 3D sphere centre of I (q) i is denoted by C (q) i , whose X, Y, and Z coordinates are denoted by C (q) i, X , C (q) i, Y , and C (q) i, Z , respectively.…”

“…To simplify the extrinsic calibration, several methods have been developed based on a spherical calibration object [1][2][3]. Two recent methods [1,2] share a common set of steps: the RGB-D cameras simultaneously acquire multiple pairs of colour and depth images of the spherical object. The spherical object is placed differently each time.…”

Iterative K-Closest Point Algorithms for Colored Point Cloud Registration

“…In practice, we can employ global registration algorithms [ 18 , 19 , 20 , 21 ] to estimate them. For a multi-view system, they can be estimated by calibrating the camera network [ 34 ].…”

Real-Time Docking Ring Detection Based on the Geometrical Shape for an On-Orbit Spacecraft

“…A docking ring [6] is a circular hatch of spacecraft that allows servicing spacecraft to dock in various space missions. The accurate detection of docking ring can be greatly beneficial to the target’s visual tracking, recognition [7,8] and localization [9,10,11,12,13]. The geometrical shape of the docking ring is distinctive, since it is a regular circular part on the man-made spacecraft.…”