Visual Marker Guided Point Cloud Registration in a Large Multi-Sensor Industrial Robot Cell

Ujkani, Erind; Dybedal, Joacim; Aalerud, Atle; Kaldestad, Knut Berg; Hovland, Geir

doi:10.1109/mesa.2018.8449195

Cited by 10 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sensors were placed along the outer peripheral of the lab and manually calibrated based on the method in [16]. Calibration of the camera intrinsic parameters was performed according to [17]. Note that, compared to the setup in [16], some of the sensors’ mounting locations have been moved such that the monitored area is smaller.…”

Section: Methodsmentioning

confidence: 99%

Embedded Processing and Compression of 3D Sensor Data for Large Scale Industrial Environments

Dybedal

Aalerud

Hovland

2019

Sensors

Self Cite

View full text Add to dashboard Cite

This paper presents a scalable embedded solution for processing and transferring 3D point cloud data. Sensors based on the time-of-flight principle generate data which are processed on a local embedded computer and compressed using an octree-based scheme. The compressed data is transferred to a central node where the individual point clouds from several nodes are decompressed and filtered based on a novel method for generating intensity values for sensors which do not natively produce such a value. The paper presents experimental results from a relatively large industrial robot cell with an approximate size of 10 m × 10 m × 4 m. The main advantage of processing point cloud data locally on the nodes is scalability. The proposed solution could, with a dedicated Gigabit Ethernet local network, be scaled up to approximately 440 sensor nodes, only limited by the processing power of the central node that is receiving the compressed data from the local nodes. A compression ratio of 40.5 was obtained when compressing a point cloud stream from a single Microsoft Kinect V2 sensor using an octree resolution of 4 cm.

show abstract

Section: Methodsmentioning

confidence: 99%

Embedded Processing and Compression of 3D Sensor Data for Large Scale Industrial Environments

Dybedal

Aalerud

Hovland

2019

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper, we propose a fully automatic and scalable calibration of an RGB-D sensor network that requires no human involvement. The method had similarities to previous work presented in [28] as ArUco markers, ICP, and the same sensor network and environment were used. However, we introduced several new aspects and overcome all the drawbacks described in Section 2.…”

Section: Calibration Methodsmentioning

confidence: 99%

“…Ujkani et al [28] present a benchmark and accuracy analysis of 3D sensor calibration in a large industrial robot cell. Here, a rough calibration using a single ArUco marker is performed.…”

Section: Related Workmentioning

confidence: 99%

“…For a volume measuring 10 normalm×15 normalm×5 m, a typical Euclidean distance error of 5 cm to 10 cm was achieved using six sensor nodes. Although the method presented in [28] worked well, it contains several drawbacks as follows: (1) the method requires some interaction by the operator, (2) there is no automatic camera to world calibration, (3) the solution could not easily refine the calibration when cameras observed the scene from different perspectives, (4) due to the various cross-calibrations involved, the process was susceptible to inaccurate RGB-to-depth calibration and (5) small and non-reflective ArUco markers were used.…”

Section: Related Workmentioning

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 2 more Smart Citations

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

Aalerud

Dybedal

Hovland

2019

Sensors

Self Cite

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

An indoor localization dataset and data collection framework with high precision position annotation

Daniş

Naskalı²,

Cemgil³

et al. 2022

Pervasive and Mobile Computing

View full text Add to dashboard Cite

Visual Marker Guided Point Cloud Registration in a Large Multi-Sensor Industrial Robot Cell

Cited by 10 publications

References 8 publications

Embedded Processing and Compression of 3D Sensor Data for Large Scale Industrial Environments

Embedded Processing and Compression of 3D Sensor Data for Large Scale Industrial Environments

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

An indoor localization dataset and data collection framework with high precision position annotation

Contact Info

Product

Resources

About