Utilizing color information in 3D scan-registration using planar-patches matching

Abstract

In previous work, the authors presented a 3D scan-registration algorithm based on minimizing the uncertainty-volume of the estimated inter-scan transform, computed by matching planar-patches extracted from a pair of 3D range-images. The method was shown to have a larger region of convergence than points-based methods like ICP. With the advent of newer sensors, color-information is now also available in addition to the depth-information in range-images. In this work, we show how this information can be exploited to make our algorithm computationally more efficient. The results are presented for two commercially available sensors providing color: the high-resolution, large field-of-view (FOV), slow scanning Faro sensor, and the low-resolution, small FOV, faster Kinect sensor.