An Automatic Marker–Object Offset Calibration Method for Precise 3D Augmented Reality Registration in Industrial Applications
Industrial augmented reality (AR) applications demand high on the visual consistency of virtual-real registration. To present, the marker-based registration method is most popular because it is fast, robust, and convenient to obtain the registration matrix. In practice, the registration matrix shoul...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/20/4464 |
| _version_ | 1818014020971528192 |
|---|---|
| author | Xuyue Yin Xiumin Fan Xu Yang Shiguang Qiu Zhinan Zhang |
| author_facet | Xuyue Yin Xiumin Fan Xu Yang Shiguang Qiu Zhinan Zhang |
| author_sort | Xuyue Yin |
| collection | DOAJ |
| description | Industrial augmented reality (AR) applications demand high on the visual consistency of virtual-real registration. To present, the marker-based registration method is most popular because it is fast, robust, and convenient to obtain the registration matrix. In practice, the registration matrix should multiply an offset matrix that describes the transformation between the attaching position and the initial position of the marker relative to the object. However, the offset matrix is usually measured, calculated, and set manually, which is not accurate and convenient. This paper proposes an accurate and automatic marker−object offset matrix calibration method. First, the normal direction of the target object is obtained by searching and matching the top surface of the CAD model. Then, the spatial translation is estimated by aligning the projected and the imaged top surface. Finally, all six parameters of the offset matrix are iteratively optimized using a 3D image alignment framework. Experiments were performed on the publicity monocular rigid 3D tracking dataset and an automobile gearbox. The average translation and rotation errors of the optimized offset matrix are 2.10 mm and 1.56 degree respectively. The results validate that the proposed method is accurate and automatic, which contributes to a universal offset matrix calibration tool for marker-based industrial AR applications. |
| first_indexed | 2024-04-14T06:40:24Z |
| format | Article |
| id | doaj.art-935558ac34e74c0d82698b42b21764d1 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-04-14T06:40:24Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-935558ac34e74c0d82698b42b21764d12022-12-22T02:07:21ZengMDPI AGApplied Sciences2076-34172019-10-01920446410.3390/app9204464app9204464An Automatic Marker–Object Offset Calibration Method for Precise 3D Augmented Reality Registration in Industrial ApplicationsXuyue Yin0Xiumin Fan1Xu Yang2Shiguang Qiu3Zhinan Zhang4Institute of Intelligent Manufacturing and Information Engineering, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaInstitute of Intelligent Manufacturing and Information Engineering, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaInstitute of Intelligent Manufacturing and Information Engineering, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaChengdu Aircraft Industry (Group) Co. Ltd. of Aviation Industry Corporation of China, Chengdu 610092, ChinaInstitute of Intelligent Manufacturing and Information Engineering, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaIndustrial augmented reality (AR) applications demand high on the visual consistency of virtual-real registration. To present, the marker-based registration method is most popular because it is fast, robust, and convenient to obtain the registration matrix. In practice, the registration matrix should multiply an offset matrix that describes the transformation between the attaching position and the initial position of the marker relative to the object. However, the offset matrix is usually measured, calculated, and set manually, which is not accurate and convenient. This paper proposes an accurate and automatic marker−object offset matrix calibration method. First, the normal direction of the target object is obtained by searching and matching the top surface of the CAD model. Then, the spatial translation is estimated by aligning the projected and the imaged top surface. Finally, all six parameters of the offset matrix are iteratively optimized using a 3D image alignment framework. Experiments were performed on the publicity monocular rigid 3D tracking dataset and an automobile gearbox. The average translation and rotation errors of the optimized offset matrix are 2.10 mm and 1.56 degree respectively. The results validate that the proposed method is accurate and automatic, which contributes to a universal offset matrix calibration tool for marker-based industrial AR applications.https://www.mdpi.com/2076-3417/9/20/4464augmented realityar registrationoffset calibrationindustrial arpose estimationimage descriptorimage alignmentcad model |
| spellingShingle | Xuyue Yin Xiumin Fan Xu Yang Shiguang Qiu Zhinan Zhang An Automatic Marker–Object Offset Calibration Method for Precise 3D Augmented Reality Registration in Industrial Applications Applied Sciences augmented reality ar registration offset calibration industrial ar pose estimation image descriptor image alignment cad model |
| title | An Automatic Marker–Object Offset Calibration Method for Precise 3D Augmented Reality Registration in Industrial Applications |
| title_full | An Automatic Marker–Object Offset Calibration Method for Precise 3D Augmented Reality Registration in Industrial Applications |
| title_fullStr | An Automatic Marker–Object Offset Calibration Method for Precise 3D Augmented Reality Registration in Industrial Applications |
| title_full_unstemmed | An Automatic Marker–Object Offset Calibration Method for Precise 3D Augmented Reality Registration in Industrial Applications |
| title_short | An Automatic Marker–Object Offset Calibration Method for Precise 3D Augmented Reality Registration in Industrial Applications |
| title_sort | automatic marker object offset calibration method for precise 3d augmented reality registration in industrial applications |
| topic | augmented reality ar registration offset calibration industrial ar pose estimation image descriptor image alignment cad model |
| url | https://www.mdpi.com/2076-3417/9/20/4464 |
| work_keys_str_mv | AT xuyueyin anautomaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications AT xiuminfan anautomaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications AT xuyang anautomaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications AT shiguangqiu anautomaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications AT zhinanzhang anautomaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications AT xuyueyin automaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications AT xiuminfan automaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications AT xuyang automaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications AT shiguangqiu automaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications AT zhinanzhang automaticmarkerobjectoffsetcalibrationmethodforprecise3daugmentedrealityregistrationinindustrialapplications |