Intrinsic Calibration of Depth Cameras for Mobile Robots using a Radial Laser Scanner

David Zu\~niga-No\"el; Javier Gonzalez-Jimenez; Jose-Raul Ruiz-Sarmiento

arxiv: 1907.01839 · v1 · pith:Y65OZZZ3new · submitted 2019-07-03 · 💻 cs.RO · cs.CV

Intrinsic Calibration of Depth Cameras for Mobile Robots using a Radial Laser Scanner

David Zu\~niga-No\"el , Jose-Raul Ruiz-Sarmiento , Javier Gonzalez-Jimenez This is my paper

Pith reviewed 2026-05-25 10:13 UTC · model grok-4.3

classification 💻 cs.RO cs.CV

keywords depth camera calibrationradial laser scannermaximum likelihood estimationsystematic errorsmobile robotsRGB-D sensorsautomatic calibration3D reconstruction

0 comments

The pith

A maximum likelihood estimation method uses radial laser scanner data to calibrate systematic errors in depth cameras automatically on mobile robots.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops a calibration technique for depth cameras that models their non-linear measurement errors as a probabilistic estimation problem solved via maximum likelihood. It treats the radial laser scanner as a reference sensor to estimate the error model, enabling the process to run without human intervention on robotic platforms where both sensors are often already present. The approach targets improvements in local accuracy of 3D planar surfaces and overall consistency of depth values. Readers would care because uncalibrated depth errors directly impair core robot functions such as obstacle avoidance, map building, and safe interaction. The laser can be removed after calibration completes.

Core claim

The calibration of systematic errors in depth cameras is formulated as a Maximum Likelihood Estimation problem that leverages reference measurements from a radial laser scanner. This probabilistic approach allows the calibration to be executed automatically by mobile robotic platforms, resulting in considerably more accurate results for local distortion of 3D planar reconstructions and global shifts in the measurements.

What carries the argument

The maximum likelihood estimation problem that estimates the depth camera's systematic error model from paired laser scanner reference measurements.

If this is right

Mobile robots can execute the calibration process without external equipment or manual setup.
3D environment reconstructions exhibit reduced local distortion on planar surfaces.
Global depth measurement shifts decrease, improving consistency across the sensor field of view.
Tasks such as free-space detection and visual robot-human interaction become more reliable after calibration.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same MLE framing could be adapted to calibrate other paired range sensors on the same robot platform.
Embedding the calibration routine into periodic maintenance cycles would allow robots to refresh their depth models over time without halting operation.
The method's reliance on joint sensor mounting suggests testing in configurations where the laser and depth camera have adjustable relative poses.

Load-bearing premise

The radial laser scanner supplies precise and unbiased measurements that can serve as ground truth for modeling the depth camera errors.

What would settle it

Running the calibration on a set of known planar surfaces, then measuring whether the residual error in reconstructed 3D points drops below the level observed without the laser-based MLE step.

Figures

Figures reproduced from arXiv: 1907.01839 by David Zu\~niga-No\"el, Javier Gonzalez-Jimenez, Jose-Raul Ruiz-Sarmiento.

**Figure 2.** Figure 2: The observed bias (2a) and bias noise (2b) as a function of the measured depth, along with quadratic curve fits, for two different pixels. the measured depth are reported in Figure 2b. Notice that, unlike the bias, the uncertainty of the measurements is similar for different pixels. This phenomenon has also been considered in our framework by modeling a single variance function for all pixels (see Section … view at source ↗

**Figure 3.** Figure 3: Left, Giraff robot with annotations of the sensors involved in the calibra [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗

**Figure 4.** Figure 4: Local distortion performance evaluation for the two RGB-D cameras [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗

**Figure 5.** Figure 5: Global distortion performance evaluation for the two RGB-D cameras [PITH_FULL_IMAGE:figures/full_fig_p010_5.png] view at source ↗

**Figure 6.** Figure 6: Reconstructed point clouds form raw (left) and calibrated measurements [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗

read the original abstract

Depth cameras, typically in RGB-D configurations, are common devices in mobile robotic platforms given their appealing features: high frequency and resolution, low price and power requirements, among others. These sensors may come with significant, non-linear errors in the depth measurements that jeopardize robot tasks, like free-space detection, environment reconstruction or visual robot-human interaction. This paper presents a method to calibrate such systematic errors with the help of a second, more precise range sensor, in our case a radial laser scanner. In contrast to what it may seem at first, this does not mean a serious limitation in practice since these two sensors are often mounted jointly in many mobile robotic platforms, as they complement well each other. Moreover, the laser scanner can be used just for the calibration process and get rid of it after that. The main contributions of the paper are: i) the calibration is formulated from a probabilistic perspective through a Maximum Likelihood Estimation problem, and ii) the proposed method can be easily executed automatically by mobile robotic platforms. To validate the proposed approach we evaluated for both, local distortion of 3D planar reconstructions and global shifts in the measurements, obtaining considerably more accurate results. A C++ open-source implementation of the presented method has been released for the benefit of the community.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper gives a usable MLE formulation for calibrating depth camera distortion with a co-mounted radial laser, but it treats laser ranges as exact references without propagating their own noise or bias.

read the letter

The main thing here is a practical way to fix systematic depth errors on RGB-D cameras by treating a radial laser scanner as the reference and solving via maximum likelihood. The setup is automatic and fits platforms that already carry both sensors, which is common. They release the C++ code, which helps reproducibility. That part is straightforward and addresses a real pain point in robot mapping and reconstruction tasks. What is new is the explicit MLE framing for this exact sensor pair rather than a generic least-squares fit; the abstract does not show it differs much from earlier calibration work, but the automatic execution angle is useful. The validation claims better local planar accuracy and reduced global shifts, though the numbers and error models are not shown. The soft spot is the assumption that laser measurements are deterministic ground truth. If the laser has its own angle-dependent bias or noise (typical specs are 10-30 mm), those errors get folded into the camera parameters without being modeled. The abstract gives no sign that laser uncertainty is included in the likelihood or jointly estimated. That makes the central accuracy claims harder to trust without the full equations and data. This is aimed at mobile robotics groups that already use paired sensors and want an off-the-shelf calibration routine. It is narrow but grounded enough to deserve referee time rather than a desk reject; the open-source release and concrete use case give it weight even if the laser modeling needs tightening.

Referee Report

2 major / 1 minor

Summary. The paper claims that depth camera systematic errors can be calibrated by formulating the problem as a Maximum Likelihood Estimation using a co-mounted radial laser scanner as reference. The method is designed for automatic execution on mobile robots. Validation shows considerably more accurate results for both local distortion in 3D planar reconstructions and global measurement shifts. A C++ open-source implementation is released.

Significance. If the central claim holds, the work enables practical, automatic intrinsic calibration of depth cameras on robots that already carry laser scanners, without external rigs, which could improve reconstruction and navigation tasks. The open-source release supports reproducibility and community use.

major comments (2)

[Section 3] Section 3 (probabilistic formulation): the likelihood (Eqs. 4-6) models only camera measurement noise while treating laser ranges as deterministic references. This assumption is load-bearing for the MLE objective and the reported accuracy gains, because unmodeled laser bias or noise (typically 10-30 mm) would be absorbed into the estimated depth error parameters, undermining both the local planar and global shift claims.
[Validation] Validation section: the abstract and method description provide no equations for the depth error model, no explicit error propagation from the laser, no data exclusion rules, and no quantitative metrics (e.g., RMSE values before/after), so the claim of 'considerably more accurate results' cannot be verified from the presented formulation.

minor comments (1)

[Abstract] Abstract: states validation results but omits any numerical metrics or model details, which reduces clarity even if the full text contains them.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below, proposing revisions where the manuscript can be strengthened while defending the core formulation on substantive grounds.

read point-by-point responses

Referee: [Section 3] Section 3 (probabilistic formulation): the likelihood (Eqs. 4-6) models only camera measurement noise while treating laser ranges as deterministic references. This assumption is load-bearing for the MLE objective and the reported accuracy gains, because unmodeled laser bias or noise (typically 10-30 mm) would be absorbed into the estimated depth error parameters, undermining both the local planar and global shift claims.

Authors: The formulation treats the co-mounted radial laser scanner as a higher-precision reference, consistent with standard practice when calibrating depth cameras against laser data. Typical laser noise (a few mm) is substantially lower than depth camera errors at the ranges used. We acknowledge that an explicit treatment of laser uncertainty would be valuable and will add a dedicated discussion of this modeling choice plus a sensitivity analysis to laser noise in the revision. revision: partial
Referee: [Validation] Validation section: the abstract and method description provide no equations for the depth error model, no explicit error propagation from the laser, no data exclusion rules, and no quantitative metrics (e.g., RMSE values before/after), so the claim of 'considerably more accurate results' cannot be verified from the presented formulation.

Authors: We agree that the validation section would benefit from greater explicitness. The depth error model appears in the MLE formulation of Section 3; we will add the explicit functional form, data exclusion criteria, error propagation discussion, and numerical metrics (RMSE before/after) to the revised validation section so that the accuracy claims are directly verifiable. revision: yes

Circularity Check

0 steps flagged

No circularity; laser scanner treated as independent external reference

full rationale

The paper's central derivation formulates depth camera calibration as an MLE problem that takes radial laser scanner ranges as fixed, more-precise inputs (abstract and Section 3). No equation or step defines camera parameters in terms of themselves, renames a fitted quantity as a prediction, or relies on a load-bearing self-citation whose content reduces to the present work. The laser is explicitly positioned as an external benchmark that can be removed after calibration, satisfying the self-contained-against-external-benchmarks criterion.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

Central claim rests on the laser scanner being a reliable external reference and on the existence of a parametric model for the depth errors that MLE can recover.

free parameters (1)

depth error model parameters
Estimated via MLE; exact number and form not stated in abstract.

axioms (1)

domain assumption Laser scanner measurements are more precise than depth camera and can be treated as ground truth.
Invoked to justify using laser data to calibrate camera.

pith-pipeline@v0.9.0 · 5767 in / 1097 out tokens · 24085 ms · 2026-05-25T10:13:08.491325+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

arg max a,b,c ∏ p(zi | z∗i, μ(zi), σ(zi)) with μ(z) = a z² + b z + c and normality assumption (Eqs. 12-13)
IndisputableMonolith/Foundation/RealityFromDistinction.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

laser scanner treated as deterministic reference for z* (Sec. 4.1, Eq. 8)

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

26 extracted references · 26 canonical work pages · 2 internal anchors

[1]

In: International Conference on Mechatronics and Machine Vision in Practice (M2VIP) (2017)

Jing, C., Potgieter, J., Noble, F., Wang, R.: A comparison and analysis of RGB-D cameras’ depth performance for robotics application. In: International Conference on Mechatronics and Machine Vision in Practice (M2VIP) (2017)

work page 2017
[2]

The International Journal of Robotics Research 36(2) (2017)

Ruiz-Sarmiento, J.R., Galindo, C., Gonzalez-Jimenez, J.: Robot@Home, a robotic dataset for semantic mapping of home environments. The International Journal of Robotics Research 36(2) (2017)

work page 2017
[3]

The International Journal of Robotics Research 37(4-5) (2018)

Schwarz, M., Milan, A., Periyasamy, A.S., Behnke, S.: RGB-D object detection and semantic segmentation for autonomous manipulation in clutter. The International Journal of Robotics Research 37(4-5) (2018)

work page 2018
[4]

application to scene object recognition

Ruiz-Sarmiento, J.R., Galindo, C., Gonzalez-Jimenez, J.: A survey on learning ap- proaches for undirected graphical models. application to scene object recognition. International Journal of Approximate Reasoning 83 (2017)

work page 2017
[5]

International Journal of Ad- vanced Robotic Systems 12(5) (2015)

Jaimez, M., Blanco, J.L., Gonzalez-Jimenez, J.: Eﬃcient reactive navigation with exact collision determination for 3D robot shapes. International Journal of Ad- vanced Robotic Systems 12(5) (2015)

work page 2015
[6]

In: Computer Vision – ECCV 2016 (2016) 12 D

K¨ ahler, O., Prisacariu, V.A., Murray, D.W.: Real-time large-scale dense 3D recon- struction with loop closure. In: Computer Vision – ECCV 2016 (2016) 12 D. Zu˜ niga-No¨ el et al

work page 2016
[7]

RGB-Depth SLAM Review

Jamiruddin, R., Sari, A.O., Shabbir, J., Anwer, T.: RGB-depth SLAM review. arXiv preprint arXiv:1805.07696 (2018)

work page internal anchor Pith review Pith/arXiv arXiv 2018
[8]

Knowledge-Based Systems 119 (2017)

Ruiz-Sarmiento, J.R., Galindo, C., Gonzalez-Jimenez, J.: Building multiversal se- mantic maps for mobile robot operation. Knowledge-Based Systems 119 (2017)

work page 2017
[9]

In: Robotics: Science and Systems

Zhang, J., Singh, S.: LOAM: Lidar odometry and mapping in real-time. In: Robotics: Science and Systems. vol. 2 (2014)

work page 2014
[10]

IEEE Sensors Journal 11(9) (2011)

Foix, S., Aleny` a, G., Torras, C.: Lock-in time-of-ﬂight (ToF) cameras: A survey. IEEE Sensors Journal 11(9) (2011)

work page 2011
[11]

In: International Conference on Robotics and Automation (2011)

Rusu, R.B., Cousins, S.: 3D is here: Point cloud library (PCL). In: International Conference on Robotics and Automation (2011)

work page 2011
[12]

Multimedia Tools and Ap- plications 77(12) (2018)

Song, X., Zheng, J., Zhong, F., Qin, X.: Modeling deviations of RGB-D cameras for accurate depth map and color image registration. Multimedia Tools and Ap- plications 77(12) (2018)

work page 2018
[13]

In: Advances in Depth Image Analysis and Applications (2013)

Fiedler, D., M¨ uller, H.: Impact of thermal and environmental conditions on the Kinect sensor. In: Advances in Depth Image Analysis and Applications (2013)

work page 2013
[14]

Ruiz-Sarmiento, J.R., Galindo, C., Gonzalez-Jimenez, J.: Experimental study of the performance of the Kinect range camera for mobile robotics. Tech. rep., Uni- versity of Malaga, Dpt. of System Engineering and Automation (2013)

work page 2013
[15]

In: International Conference on Intelligent Robots and Systems (2014)

Fernandez-Moral, E., Gonzalez-Jimenez, J., Rives, P., Arevalo, V.: Extrinsic cali- bration of a set of range cameras in 5 seconds without pattern. In: International Conference on Intelligent Robots and Systems (2014)

work page 2014
[16]

IEEE Robotics and Automation Letters 4(2) (2019)

Della Corte, B., Andreasson, H., Stoyanov, T., Grisetti, G.: Uniﬁed motion-based calibration of mobile multi-sensor platforms with time delay estimation. IEEE Robotics and Automation Letters 4(2) (2019)

work page 2019
[17]

In: Robotics: Science and Systems

Teichman, A., Miller, S., Thrun, S.: Unsupervised intrinsic calibration of depth sensors via SLAM. In: Robotics: Science and Systems. vol. 248 (2013)

work page 2013
[18]

Robotics and Autonomous Systems 74 (2015)

Di Cicco, M., Iocchi, L., Grisetti, G.: Non-parametric calibration for depth sensors. Robotics and Autonomous Systems 74 (2015)

work page 2015
[19]

IEEE Transactions on Robotics 34(5) (2018)

Basso, F., Menegatti, E., Pretto, A.: Robust intrinsic and extrinsic calibration of RGB-D cameras. IEEE Transactions on Robotics 34(5) (2018)

work page 2018
[20]

In: 2012 IEEE RO- MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication (2012)

Gonz´ alez-Jim´ enez, J., Galindo, C., Ruiz-Sarmiento, J.R.: Technical improvements of the Giraﬀ telepresence robot based on users’ evaluation. In: 2012 IEEE RO- MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication (2012)

work page 2012
[21]

In: International Conference on Multimedia and Expo (2011)

Zhang, C., Zhang, Z.: Calibration between depth and color sensors for commodity depth cameras. In: International Conference on Multimedia and Expo (2011)

work page 2011
[22]

IEEE Transactions on Pattern Analysis and Machine Intelligence 34(10) (2012)

Herrera C., D., Kannala, J., Heikkil¨ a, J.: Joint depth and color camera calibration with distortion correction. IEEE Transactions on Pattern Analysis and Machine Intelligence 34(10) (2012)

work page 2012
[23]

In: International Conference on Intelligent Robots and Systems (2017)

Quenzel, J., Rosu, R.A., Houben, S., Behnke, S.: Online depth calibration for RGB- D cameras using visual SLAM. In: International Conference on Intelligent Robots and Systems (2017)

work page 2017
[24]

In: International Conference on Computer Vision Workshops (2011)

Smisek, J., Jancosek, M., Pajdla, T.: 3D with Kinect. In: International Conference on Computer Vision Workshops (2011)

work page 2011
[25]

Automatic Multi-Sensor Extrinsic Calibration for Mobile Robots

Zu˜ niga-No¨ el, D., Ruiz-Sarmiento, J.R., Gomez-Ojeda, R., Gonzalez-Jimenez, J.: Automatic multi-sensor extrinsic calibration for mobile robots. arXiv preprint arXiv:1906.04670 (2019)

work page internal anchor Pith review Pith/arXiv arXiv 1906
[26]

In: International Conference on 3D Imaging, Model- ing, Processing, Visualization Transmission (2012)

Nguyen, C.V., Izadi, S., Lovell, D.: Modeling Kinect sensor noise for improved 3D reconstruction and tracking. In: International Conference on 3D Imaging, Model- ing, Processing, Visualization Transmission (2012)

work page 2012

[1] [1]

In: International Conference on Mechatronics and Machine Vision in Practice (M2VIP) (2017)

Jing, C., Potgieter, J., Noble, F., Wang, R.: A comparison and analysis of RGB-D cameras’ depth performance for robotics application. In: International Conference on Mechatronics and Machine Vision in Practice (M2VIP) (2017)

work page 2017

[2] [2]

The International Journal of Robotics Research 36(2) (2017)

Ruiz-Sarmiento, J.R., Galindo, C., Gonzalez-Jimenez, J.: Robot@Home, a robotic dataset for semantic mapping of home environments. The International Journal of Robotics Research 36(2) (2017)

work page 2017

[3] [3]

The International Journal of Robotics Research 37(4-5) (2018)

Schwarz, M., Milan, A., Periyasamy, A.S., Behnke, S.: RGB-D object detection and semantic segmentation for autonomous manipulation in clutter. The International Journal of Robotics Research 37(4-5) (2018)

work page 2018

[4] [4]

application to scene object recognition

Ruiz-Sarmiento, J.R., Galindo, C., Gonzalez-Jimenez, J.: A survey on learning ap- proaches for undirected graphical models. application to scene object recognition. International Journal of Approximate Reasoning 83 (2017)

work page 2017

[5] [5]

International Journal of Ad- vanced Robotic Systems 12(5) (2015)

Jaimez, M., Blanco, J.L., Gonzalez-Jimenez, J.: Eﬃcient reactive navigation with exact collision determination for 3D robot shapes. International Journal of Ad- vanced Robotic Systems 12(5) (2015)

work page 2015

[6] [6]

In: Computer Vision – ECCV 2016 (2016) 12 D

K¨ ahler, O., Prisacariu, V.A., Murray, D.W.: Real-time large-scale dense 3D recon- struction with loop closure. In: Computer Vision – ECCV 2016 (2016) 12 D. Zu˜ niga-No¨ el et al

work page 2016

[7] [7]

RGB-Depth SLAM Review

Jamiruddin, R., Sari, A.O., Shabbir, J., Anwer, T.: RGB-depth SLAM review. arXiv preprint arXiv:1805.07696 (2018)

work page internal anchor Pith review Pith/arXiv arXiv 2018

[8] [8]

Knowledge-Based Systems 119 (2017)

Ruiz-Sarmiento, J.R., Galindo, C., Gonzalez-Jimenez, J.: Building multiversal se- mantic maps for mobile robot operation. Knowledge-Based Systems 119 (2017)

work page 2017

[9] [9]

In: Robotics: Science and Systems

Zhang, J., Singh, S.: LOAM: Lidar odometry and mapping in real-time. In: Robotics: Science and Systems. vol. 2 (2014)

work page 2014

[10] [10]

IEEE Sensors Journal 11(9) (2011)

Foix, S., Aleny` a, G., Torras, C.: Lock-in time-of-ﬂight (ToF) cameras: A survey. IEEE Sensors Journal 11(9) (2011)

work page 2011

[11] [11]

In: International Conference on Robotics and Automation (2011)

Rusu, R.B., Cousins, S.: 3D is here: Point cloud library (PCL). In: International Conference on Robotics and Automation (2011)

work page 2011

[12] [12]

Multimedia Tools and Ap- plications 77(12) (2018)

Song, X., Zheng, J., Zhong, F., Qin, X.: Modeling deviations of RGB-D cameras for accurate depth map and color image registration. Multimedia Tools and Ap- plications 77(12) (2018)

work page 2018

[13] [13]

In: Advances in Depth Image Analysis and Applications (2013)

Fiedler, D., M¨ uller, H.: Impact of thermal and environmental conditions on the Kinect sensor. In: Advances in Depth Image Analysis and Applications (2013)

work page 2013

[14] [14]

Ruiz-Sarmiento, J.R., Galindo, C., Gonzalez-Jimenez, J.: Experimental study of the performance of the Kinect range camera for mobile robotics. Tech. rep., Uni- versity of Malaga, Dpt. of System Engineering and Automation (2013)

work page 2013

[15] [15]

In: International Conference on Intelligent Robots and Systems (2014)

Fernandez-Moral, E., Gonzalez-Jimenez, J., Rives, P., Arevalo, V.: Extrinsic cali- bration of a set of range cameras in 5 seconds without pattern. In: International Conference on Intelligent Robots and Systems (2014)

work page 2014

[16] [16]

IEEE Robotics and Automation Letters 4(2) (2019)

Della Corte, B., Andreasson, H., Stoyanov, T., Grisetti, G.: Uniﬁed motion-based calibration of mobile multi-sensor platforms with time delay estimation. IEEE Robotics and Automation Letters 4(2) (2019)

work page 2019

[17] [17]

In: Robotics: Science and Systems

Teichman, A., Miller, S., Thrun, S.: Unsupervised intrinsic calibration of depth sensors via SLAM. In: Robotics: Science and Systems. vol. 248 (2013)

work page 2013

[18] [18]

Robotics and Autonomous Systems 74 (2015)

Di Cicco, M., Iocchi, L., Grisetti, G.: Non-parametric calibration for depth sensors. Robotics and Autonomous Systems 74 (2015)

work page 2015

[19] [19]

IEEE Transactions on Robotics 34(5) (2018)

Basso, F., Menegatti, E., Pretto, A.: Robust intrinsic and extrinsic calibration of RGB-D cameras. IEEE Transactions on Robotics 34(5) (2018)

work page 2018

[20] [20]

In: 2012 IEEE RO- MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication (2012)

Gonz´ alez-Jim´ enez, J., Galindo, C., Ruiz-Sarmiento, J.R.: Technical improvements of the Giraﬀ telepresence robot based on users’ evaluation. In: 2012 IEEE RO- MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication (2012)

work page 2012

[21] [21]

In: International Conference on Multimedia and Expo (2011)

Zhang, C., Zhang, Z.: Calibration between depth and color sensors for commodity depth cameras. In: International Conference on Multimedia and Expo (2011)

work page 2011

[22] [22]

IEEE Transactions on Pattern Analysis and Machine Intelligence 34(10) (2012)

Herrera C., D., Kannala, J., Heikkil¨ a, J.: Joint depth and color camera calibration with distortion correction. IEEE Transactions on Pattern Analysis and Machine Intelligence 34(10) (2012)

work page 2012

[23] [23]

In: International Conference on Intelligent Robots and Systems (2017)

Quenzel, J., Rosu, R.A., Houben, S., Behnke, S.: Online depth calibration for RGB- D cameras using visual SLAM. In: International Conference on Intelligent Robots and Systems (2017)

work page 2017

[24] [24]

In: International Conference on Computer Vision Workshops (2011)

Smisek, J., Jancosek, M., Pajdla, T.: 3D with Kinect. In: International Conference on Computer Vision Workshops (2011)

work page 2011

[25] [25]

Automatic Multi-Sensor Extrinsic Calibration for Mobile Robots

Zu˜ niga-No¨ el, D., Ruiz-Sarmiento, J.R., Gomez-Ojeda, R., Gonzalez-Jimenez, J.: Automatic multi-sensor extrinsic calibration for mobile robots. arXiv preprint arXiv:1906.04670 (2019)

work page internal anchor Pith review Pith/arXiv arXiv 1906

[26] [26]

In: International Conference on 3D Imaging, Model- ing, Processing, Visualization Transmission (2012)

Nguyen, C.V., Izadi, S., Lovell, D.: Modeling Kinect sensor noise for improved 3D reconstruction and tracking. In: International Conference on 3D Imaging, Model- ing, Processing, Visualization Transmission (2012)

work page 2012