Skeleton-based continuous extrinsic calibration of multiple RGB-D kinect cameras

Desai, Kevin; Prabhakaran, Balakrishnan; Raghuraman, Suraj

doi:10.1145/3204949.3204969

Cited by 13 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods are typically not accurate enough, and additional refinement using depth data should be added. Secondly, most of the methods require a human to be present in the environment to function as a key point or to move an object to be targeted [4,5,6,10,45]. Lastly, several of the methods are invasive in terms of cluttering the environment with installations such as spheres [7,8].…”

Section: Discussionmentioning

confidence: 99%

“…Desai et al [6] proposed a method using skeleton tracking. Here, the sensors identify the human skeleton joints and use the 3D joint positions as point correspondences between cameras on a pair by pair basis.…”

Section: Related Workmentioning

confidence: 99%

“…Using the skeleton approach gave an average Euclidean distance error of 1.5 cm. The approach in [6] can re-calibrate automatically as long as a human is present in the scene. However, it does not include an automatic method to calibrate the camera network w.r.t.…”

Section: Related Workmentioning

confidence: 99%

“…Obtaining the camera pose from images requires finding the correspondences between known points in the environment and their camera projections [1]. Such key points [2,3] or calibration objects [4,5,6] may be found in the image naturally, or they may be inserted artificially [7,8,9,10,11,12,13,14,15]. Even if natural landmarks are the preferred choice, as they require no intervention in the environment, artificial landmarks have some clear benefits such as higher precision, robustness, and speed [16].…”

Section: Introductionmentioning

confidence: 99%

“…However, as the marker becomes small, the errors in the corner estimation grow, and ambiguity comes as a problem. For 3D cameras, such as RGB-D, an additional refinement is typically performed utilizing the depth information [6,8,9,10,11,28].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automatic Calibration of an Industrial RGB-D Camera Network Using Retroreflective Fiducial Markers

Aalerud

Dybedal

Hovland

2019

Sensors

View full text Add to dashboard Cite

This paper describes a non-invasive, automatic, and robust method for calibrating a scalable RGB-D sensor network based on retroreflective ArUco markers and the iterative closest point (ICP) scheme. We demonstrate the system by calibrating a sensor network comprised of six sensor nodes positioned in a relatively large industrial robot cell with an approximate size of 10 m × 10 m × 4 m. Here, the automatic calibration achieved an average Euclidean error of 3 cm at distances up to 9.45 m. To achieve robustness, we apply several innovative techniques: Firstly, we mitigate the ambiguity problem that occurs when detecting a marker at long range or low resolution by comparing the camera projection with depth data. Secondly, we use retroreflective fiducial markers in the RGB-D calibration for improved accuracy and detectability. Finally, the repeating ICP refinement uses an exact region of interest such that we employ the precise depth measurements of the retroreflective surfaces only. The complete calibration software and a recorded dataset are publically available and open source.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Calibration of an Industrial RGB-D Camera Network Using Retroreflective Fiducial Markers

Aalerud

Dybedal

Hovland

2019

Sensors

View full text Add to dashboard Cite

show abstract

Fast automatic camera network calibration through human mesh recovery

Garau

Natale

Conci

2020

J Real-Time Image Proc

View full text Add to dashboard Cite

Camera calibration is a necessary preliminary step in computer vision for the estimation of the position of objects in the 3D world. Despite the intrinsic camera parameters can be easily computed offline, extrinsic parameters need to be computed each time a camera changes its position, thus not allowing for fast and dynamic network re-configuration. In this paper we present an unsupervised and automatic framework for the estimation of the extrinsic parameters of a camera network, which leverages on optimised 3D human mesh recovery from a single image, and which does not require the use of additional markers. We show how it is possible to retrieve the real-world position of the cameras in the network together with the floor plane, exploiting regular RGB images and with a weak prior knowledge of the internal parameters. Our framework can also work with a single camera and in real-time, allowing the user to add, re-position, or remove cameras from the network in a dynamic fashion.

show abstract

Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras

Huang

Yuan

Wang

2021

2021 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

Multi-view image compression is vital for 3D-related applications. To effectively model correlations between views, existing methods typically predict disparity between two views on a 2D plane, which works well for small disparities, such as in stereo images, but struggles with larger disparities caused by significant view changes. To address this, we propose a novel approach: learning-based multi-view image coding with 3D Gaussian geometric priors (3D-GP-LMVIC). Our method leverages 3D Gaussian Splatting to derive geometric priors of the 3D scene, enabling more accurate disparity estimation across views within the compression model. Additionally, we introduce a depth map compression model to reduce redundancy in geometric information between views. A multi-view sequence ordering method is also proposed to enhance correlations between adjacent views. Experimental results demonstrate that 3D-GP-LMVIC surpasses both traditional and learning-based methods in performance, while maintaining fast encoding and decoding speed. The code is available at https://github.com/YujunHuang063/3D-GP-LMVIC.

show abstract

Skeleton-based continuous extrinsic calibration of multiple RGB-D kinect cameras

Cited by 13 publications

References 32 publications

Automatic Calibration of an Industrial RGB-D Camera Network Using Retroreflective Fiducial Markers

Automatic Calibration of an Industrial RGB-D Camera Network Using Retroreflective Fiducial Markers

Fast automatic camera network calibration through human mesh recovery

Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras

Contact Info

Product

Resources

About