Towards Industrial IoT-AR Systems using Deep Learning-Based Object Pose Estimation
Augmented Reality (AR) is known to enhance user experience, however, it remains under-adopted in industry. We present an AR interaction system improving human-machine coordination in Internet of Things (IoT) and Industry 4.0 applications including manufacturing and assembly, maintenance and safety,...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2020
|
| Online Access: | https://hdl.handle.net/1721.1/127845 |
| _version_ | 1826213726260297728 |
|---|---|
| author | Sun, Yongbin Kantareddy, Sai Nithin R. Siegel, Joshua Armengol Urpi, Alexandre Wu, Xiaoyu Wang, Hongyu Sarma, Sanjay |
| author2 | Massachusetts Institute of Technology. Auto-ID Laboratory |
| author_facet | Massachusetts Institute of Technology. Auto-ID Laboratory Sun, Yongbin Kantareddy, Sai Nithin R. Siegel, Joshua Armengol Urpi, Alexandre Wu, Xiaoyu Wang, Hongyu Sarma, Sanjay |
| author_sort | Sun, Yongbin |
| collection | MIT |
| description | Augmented Reality (AR) is known to enhance user experience, however, it remains under-adopted in industry. We present an AR interaction system improving human-machine coordination in Internet of Things (IoT) and Industry 4.0 applications including manufacturing and assembly, maintenance and safety, and other highly-interactive functions. A driver of slow adoption is the computational complexity and inaccuracy in localization and rendering digital content. AR systems may render digital content close to the associated physical objects, but traditional object recognition and localization modules perform poorly when tracking texture-less objects and complex shapes, presenting a need for robust and efficient digital content rendering techniques. We propose a method of improving IoT-AR by integrating Deep Learning with AR to increase accuracy and robustness of the target object localization module, taking both color and depth images as input and outputting the target's pose parameters. Quantitative and qualitative experiments prove this system's efficacy and show potential for fusing these emerging technologies in real-world applications. |
| first_indexed | 2024-09-23T15:53:50Z |
| format | Article |
| id | mit-1721.1/127845 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:53:50Z |
| publishDate | 2020 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1278452022-10-02T04:55:15Z Towards Industrial IoT-AR Systems using Deep Learning-Based Object Pose Estimation Sun, Yongbin Kantareddy, Sai Nithin R. Siegel, Joshua Armengol Urpi, Alexandre Wu, Xiaoyu Wang, Hongyu Sarma, Sanjay Massachusetts Institute of Technology. Auto-ID Laboratory Massachusetts Institute of Technology. Department of Mechanical Engineering Augmented Reality (AR) is known to enhance user experience, however, it remains under-adopted in industry. We present an AR interaction system improving human-machine coordination in Internet of Things (IoT) and Industry 4.0 applications including manufacturing and assembly, maintenance and safety, and other highly-interactive functions. A driver of slow adoption is the computational complexity and inaccuracy in localization and rendering digital content. AR systems may render digital content close to the associated physical objects, but traditional object recognition and localization modules perform poorly when tracking texture-less objects and complex shapes, presenting a need for robust and efficient digital content rendering techniques. We propose a method of improving IoT-AR by integrating Deep Learning with AR to increase accuracy and robustness of the target object localization module, taking both color and depth images as input and outputting the target's pose parameters. Quantitative and qualitative experiments prove this system's efficacy and show potential for fusing these emerging technologies in real-world applications. 2020-10-08T20:24:57Z 2020-10-08T20:24:57Z 2020-01 2019-10 2020-09-21T17:18:46Z Article http://purl.org/eprint/type/ConferencePaper 9781728110257 2374-9628 https://hdl.handle.net/1721.1/127845 Sun, Yongbin et al. "Towards Industrial IoT-AR Systems using Deep Learning-Based Object Pose Estimation." 38th International Performance Computing and Communications Conference, October 2019, London, United Kingdom, United Kingdom, Institute of Electrical and Electronics Engineers, January 2020. © 2019 IEEE en http://dx.doi.org/10.1109/ipccc47392.2019.8958753 38th International Performance Computing and Communications Conference Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) Prof. Sarma via Elizabeth Soergel |
| spellingShingle | Sun, Yongbin Kantareddy, Sai Nithin R. Siegel, Joshua Armengol Urpi, Alexandre Wu, Xiaoyu Wang, Hongyu Sarma, Sanjay Towards Industrial IoT-AR Systems using Deep Learning-Based Object Pose Estimation |
| title | Towards Industrial IoT-AR Systems using Deep Learning-Based Object Pose Estimation |
| title_full | Towards Industrial IoT-AR Systems using Deep Learning-Based Object Pose Estimation |
| title_fullStr | Towards Industrial IoT-AR Systems using Deep Learning-Based Object Pose Estimation |
| title_full_unstemmed | Towards Industrial IoT-AR Systems using Deep Learning-Based Object Pose Estimation |
| title_short | Towards Industrial IoT-AR Systems using Deep Learning-Based Object Pose Estimation |
| title_sort | towards industrial iot ar systems using deep learning based object pose estimation |
| url | https://hdl.handle.net/1721.1/127845 |
| work_keys_str_mv | AT sunyongbin towardsindustrialiotarsystemsusingdeeplearningbasedobjectposeestimation AT kantareddysainithinr towardsindustrialiotarsystemsusingdeeplearningbasedobjectposeestimation AT siegeljoshua towardsindustrialiotarsystemsusingdeeplearningbasedobjectposeestimation AT armengolurpialexandre towardsindustrialiotarsystemsusingdeeplearningbasedobjectposeestimation AT wuxiaoyu towardsindustrialiotarsystemsusingdeeplearningbasedobjectposeestimation AT wanghongyu towardsindustrialiotarsystemsusingdeeplearningbasedobjectposeestimation AT sarmasanjay towardsindustrialiotarsystemsusingdeeplearningbasedobjectposeestimation |