Unsupervised Intrinsic Calibration of Depth Sensors via SLAM

By Alex Teichman, Stephen D. Miller, Sebastian Thrun. 2013

95 citations recorded by the source corpus.

We present a new, generic approach to the calibration of depth sensor intrinsics that requires only the ability to run SLAM. In particular, no specialized hardware, calibration target, or hand measurement is required. Essential to this approach is the idea that certain intrinsic parameters, identified here as myopic, govern distortions that increase with range. We demonstrate these ideas on the calibration of the popular Kinect and Xtion Pro Live RGBD sensors, which typically exhibit significant depth distortion at ranges greater than three meters. Making use of the myopic property, we show how to efficiently learn a discrete grid of 32,000 depth multipliers that resolve this distortion. Compared to the most similar unsupervised calibration work in the literature, this is a 100-fold increase in the maximum number of calibration parameters previously learned. Compared to the supervised calibration approach, the work of this paper means the difference between A) printing a poster of a checkerboard, mounting it to a rigid plane, and recording data of it from many different angles and ranges a process that often requires two people or repeated use of a special easel versus B) recording a few minutes of data from unmodified, natural environments. This is advantageous both for individuals who wish to calibrate their own sensors as well as for a robot that needs to calibrate automatically while in the field.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, methodology): “To align a depth image D to color image C , we need to estimate intrinsic parameters of both sensors, the infrared camera K D and color camera K C , as well as extrinsic transformation T D→C .”
Elastic Fragments for Dense Scene Reconstruction (2013, unknown): “[31], which reduces low-frequency distortion.”
Online Reconstruction of Indoor Scenes from RGB-D Streams (2016, background): “An exception is [38], in which the authors mentioned that the calibration approach of [28] has been applied to their sensor.”
Nonparametric Calibration for Depth Sensors (2015, unknown): “al [11].”