Automatic Real-Time Pose Estimation of Machinery from Images
The automatic positioning of machines in a large number of application areas is an important aspect of automation. Today, this is often done using classic geodetic sensors such as Global Navigation Satellite Systems (GNSS) and robotic total stations. In this work, a stereo camera system was develope...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/7/2627 |
| _version_ | 1797437745345331200 |
|---|---|
| author | Marcel Bertels Boris Jutzi Markus Ulrich |
| author_facet | Marcel Bertels Boris Jutzi Markus Ulrich |
| author_sort | Marcel Bertels |
| collection | DOAJ |
| description | The automatic positioning of machines in a large number of application areas is an important aspect of automation. Today, this is often done using classic geodetic sensors such as Global Navigation Satellite Systems (GNSS) and robotic total stations. In this work, a stereo camera system was developed that localizes a machine at high frequency and serves as an alternative to the previously mentioned sensors. For this purpose, algorithms were developed that detect active markers on the machine in a stereo image pair, find stereo point correspondences, and estimate the pose of the machine from these. Theoretical influences and accuracies for different systems were estimated with a Monte Carlo simulation, on the basis of which the stereo camera system was designed. Field measurements were used to evaluate the actual achievable accuracies and the robustness of the prototype system. The comparison is present with reference measurements with a laser tracker. The estimated object pose achieved accuracies higher than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>16</mn><mo> </mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">m</mi></mrow></mrow></semantics></math></inline-formula> with the translation components and accuracies higher than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3</mn><mo> </mo><mrow><mi mathvariant="normal">mrad</mi></mrow></mrow></semantics></math></inline-formula> with the rotation components. As a result, 3D point accuracies higher than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>16</mn><mo> </mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">m</mi></mrow></mrow></semantics></math></inline-formula> were achieved by the machine. For the first time, a prototype could be developed that represents an alternative, powerful image-based localization method for machines to the classical geodetic sensors. |
| first_indexed | 2024-03-09T11:27:04Z |
| format | Article |
| id | doaj.art-eaf819e7109b4e2cb5541c4441108f14 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T11:27:04Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-eaf819e7109b4e2cb5541c4441108f142023-12-01T00:02:19ZengMDPI AGSensors1424-82202022-03-01227262710.3390/s22072627Automatic Real-Time Pose Estimation of Machinery from ImagesMarcel Bertels0Boris Jutzi1Markus Ulrich2Institute of Photogrammetry and Remote Sensing (IPF), Karlsruhe Institute of Technology, 76128 Karlsruhe, GermanyInstitute of Photogrammetry and Remote Sensing (IPF), Karlsruhe Institute of Technology, 76128 Karlsruhe, GermanyInstitute of Photogrammetry and Remote Sensing (IPF), Karlsruhe Institute of Technology, 76128 Karlsruhe, GermanyThe automatic positioning of machines in a large number of application areas is an important aspect of automation. Today, this is often done using classic geodetic sensors such as Global Navigation Satellite Systems (GNSS) and robotic total stations. In this work, a stereo camera system was developed that localizes a machine at high frequency and serves as an alternative to the previously mentioned sensors. For this purpose, algorithms were developed that detect active markers on the machine in a stereo image pair, find stereo point correspondences, and estimate the pose of the machine from these. Theoretical influences and accuracies for different systems were estimated with a Monte Carlo simulation, on the basis of which the stereo camera system was designed. Field measurements were used to evaluate the actual achievable accuracies and the robustness of the prototype system. The comparison is present with reference measurements with a laser tracker. The estimated object pose achieved accuracies higher than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>16</mn><mo> </mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">m</mi></mrow></mrow></semantics></math></inline-formula> with the translation components and accuracies higher than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3</mn><mo> </mo><mrow><mi mathvariant="normal">mrad</mi></mrow></mrow></semantics></math></inline-formula> with the rotation components. As a result, 3D point accuracies higher than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>16</mn><mo> </mo><mrow><mi mathvariant="normal">m</mi><mi mathvariant="normal">m</mi></mrow></mrow></semantics></math></inline-formula> were achieved by the machine. For the first time, a prototype could be developed that represents an alternative, powerful image-based localization method for machines to the classical geodetic sensors.https://www.mdpi.com/1424-8220/22/7/2627machine visionstereo camera systemlocalizationreal-timepose estimationmarker detection |
| spellingShingle | Marcel Bertels Boris Jutzi Markus Ulrich Automatic Real-Time Pose Estimation of Machinery from Images Sensors machine vision stereo camera system localization real-time pose estimation marker detection |
| title | Automatic Real-Time Pose Estimation of Machinery from Images |
| title_full | Automatic Real-Time Pose Estimation of Machinery from Images |
| title_fullStr | Automatic Real-Time Pose Estimation of Machinery from Images |
| title_full_unstemmed | Automatic Real-Time Pose Estimation of Machinery from Images |
| title_short | Automatic Real-Time Pose Estimation of Machinery from Images |
| title_sort | automatic real time pose estimation of machinery from images |
| topic | machine vision stereo camera system localization real-time pose estimation marker detection |
| url | https://www.mdpi.com/1424-8220/22/7/2627 |
| work_keys_str_mv | AT marcelbertels automaticrealtimeposeestimationofmachineryfromimages AT borisjutzi automaticrealtimeposeestimationofmachineryfromimages AT markusulrich automaticrealtimeposeestimationofmachineryfromimages |