A Feasibility Study on Indoor Localization and Multiperson Tracking Using Sparsely Distributed Camera Network With Edge Computing
Camera-based activity monitoring systems are becoming an attractive solution for smart building applications with the advances in computer vision and edge computing technologies. In this article, we present a feasibility study and systematic analysis of a camera-based indoor localization and multipe...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Indoor and Seamless Positioning and Navigation |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10329418/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850051529892954112 |
|---|---|
| author | Hyeokhyen Kwon Chaitra Hegde Yashar Kiarashi Venkata Siva Krishna Madala Ratan Singh ArjunSinh Nakum Robert Tweedy Leandro Miletto Tonetto Craig M. Zimring Matthew Doiron Amy D. Rodriguez Allan I. Levey Gari D. Clifford |
| author_facet | Hyeokhyen Kwon Chaitra Hegde Yashar Kiarashi Venkata Siva Krishna Madala Ratan Singh ArjunSinh Nakum Robert Tweedy Leandro Miletto Tonetto Craig M. Zimring Matthew Doiron Amy D. Rodriguez Allan I. Levey Gari D. Clifford |
| author_sort | Hyeokhyen Kwon |
| collection | DOAJ |
| description | Camera-based activity monitoring systems are becoming an attractive solution for smart building applications with the advances in computer vision and edge computing technologies. In this article, we present a feasibility study and systematic analysis of a camera-based indoor localization and multiperson tracking system implemented on edge computing devices within a large indoor space. To this end, we deployed an end-to-end edge computing pipeline that utilizes multiple cameras to achieve localization, body orientation estimation, and tracking of multiple individuals within a large therapeutic space spanning <inline-formula><tex-math notation="LaTeX">$\text{1700}\, \text{m}^{2}$</tex-math></inline-formula>, all while maintaining a strong focus on preserving privacy. Our pipeline consists of 39 edge computing camera systems equipped with tensor processing units (TPUs) placed in the indoor space's ceiling. To ensure the privacy of individuals, a real-time multiperson pose estimation algorithm runs on the TPU of the computing camera system. This algorithm extracts poses and bounding boxes, which are utilized for indoor localization, body orientation estimation, and multiperson tracking. Our pipeline demonstrated an average localization error of 1.41 m, a multiple-object tracking accuracy score of 88.6%, and a mean absolute body orientation error of 29<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula>. These results show that localization and tracking of individuals in a large indoor space is feasible even with the privacy constrains. |
| format | Article |
| id | doaj-art-c9c7c3cfcff04cf6b192e59e1fbcee86 |
| institution | DOAJ |
| issn | 2832-7322 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Indoor and Seamless Positioning and Navigation |
| spelling | doaj-art-c9c7c3cfcff04cf6b192e59e1fbcee862025-08-20T02:53:07ZengIEEEIEEE Journal of Indoor and Seamless Positioning and Navigation2832-73222023-01-01118719810.1109/JISPIN.2023.333718910329418A Feasibility Study on Indoor Localization and Multiperson Tracking Using Sparsely Distributed Camera Network With Edge ComputingHyeokhyen Kwon0https://orcid.org/0000-0002-5693-3278Chaitra Hegde1https://orcid.org/0000-0002-2791-4254Yashar Kiarashi2Venkata Siva Krishna Madala3https://orcid.org/0009-0001-0314-2843Ratan Singh4ArjunSinh Nakum5https://orcid.org/0009-0006-4792-9070Robert Tweedy6https://orcid.org/0000-0003-2092-940XLeandro Miletto Tonetto7https://orcid.org/0000-0002-4403-2085Craig M. Zimring8Matthew Doiron9Amy D. Rodriguez10https://orcid.org/0000-0002-5725-3848Allan I. Levey11Gari D. Clifford12https://orcid.org/0000-0002-5709-201XDepartment of Biomedical Informatics, School of Medicine, Emory University, Atlanta, GA, USASchool of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USADepartment of Biomedical Informatics, School of Medicine, Emory University, Atlanta, GA, USASchool of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USASchool of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USASchool of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USADepartment of Biomedical Informatics, School of Medicine, Emory University, Atlanta, GA, USASchool of Industrial Design, College of Design, Georgia Institute of Technology, Atlanta, GA, USASchool of Architecture, College of Design, Georgia Institute of Technology, Atlanta, GA, USADepartment of Neurology, School of Medicine, Emory University, Atlanta, GA, USADepartment of Neurology, School of Medicine, Emory University, Atlanta, GA, USADepartment of Neurology, School of Medicine, Emory University, Atlanta, GA, USADepartment of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, USACamera-based activity monitoring systems are becoming an attractive solution for smart building applications with the advances in computer vision and edge computing technologies. In this article, we present a feasibility study and systematic analysis of a camera-based indoor localization and multiperson tracking system implemented on edge computing devices within a large indoor space. To this end, we deployed an end-to-end edge computing pipeline that utilizes multiple cameras to achieve localization, body orientation estimation, and tracking of multiple individuals within a large therapeutic space spanning <inline-formula><tex-math notation="LaTeX">$\text{1700}\, \text{m}^{2}$</tex-math></inline-formula>, all while maintaining a strong focus on preserving privacy. Our pipeline consists of 39 edge computing camera systems equipped with tensor processing units (TPUs) placed in the indoor space's ceiling. To ensure the privacy of individuals, a real-time multiperson pose estimation algorithm runs on the TPU of the computing camera system. This algorithm extracts poses and bounding boxes, which are utilized for indoor localization, body orientation estimation, and multiperson tracking. Our pipeline demonstrated an average localization error of 1.41 m, a multiple-object tracking accuracy score of 88.6%, and a mean absolute body orientation error of 29<inline-formula><tex-math notation="LaTeX">$^{\circ }$</tex-math></inline-formula>. These results show that localization and tracking of individuals in a large indoor space is feasible even with the privacy constrains.https://ieeexplore.ieee.org/document/10329418/Body orientation estimationcloud computingcomputer visionedge computingindoor localizationmultiperson tracking |
| spellingShingle | Hyeokhyen Kwon Chaitra Hegde Yashar Kiarashi Venkata Siva Krishna Madala Ratan Singh ArjunSinh Nakum Robert Tweedy Leandro Miletto Tonetto Craig M. Zimring Matthew Doiron Amy D. Rodriguez Allan I. Levey Gari D. Clifford A Feasibility Study on Indoor Localization and Multiperson Tracking Using Sparsely Distributed Camera Network With Edge Computing IEEE Journal of Indoor and Seamless Positioning and Navigation Body orientation estimation cloud computing computer vision edge computing indoor localization multiperson tracking |
| title | A Feasibility Study on Indoor Localization and Multiperson Tracking Using Sparsely Distributed Camera Network With Edge Computing |
| title_full | A Feasibility Study on Indoor Localization and Multiperson Tracking Using Sparsely Distributed Camera Network With Edge Computing |
| title_fullStr | A Feasibility Study on Indoor Localization and Multiperson Tracking Using Sparsely Distributed Camera Network With Edge Computing |
| title_full_unstemmed | A Feasibility Study on Indoor Localization and Multiperson Tracking Using Sparsely Distributed Camera Network With Edge Computing |
| title_short | A Feasibility Study on Indoor Localization and Multiperson Tracking Using Sparsely Distributed Camera Network With Edge Computing |
| title_sort | feasibility study on indoor localization and multiperson tracking using sparsely distributed camera network with edge computing |
| topic | Body orientation estimation cloud computing computer vision edge computing indoor localization multiperson tracking |
| url | https://ieeexplore.ieee.org/document/10329418/ |
| work_keys_str_mv | AT hyeokhyenkwon afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT chaitrahegde afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT yasharkiarashi afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT venkatasivakrishnamadala afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT ratansingh afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT arjunsinhnakum afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT roberttweedy afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT leandromilettotonetto afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT craigmzimring afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT matthewdoiron afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT amydrodriguez afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT allanilevey afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT garidclifford afeasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT hyeokhyenkwon feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT chaitrahegde feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT yasharkiarashi feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT venkatasivakrishnamadala feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT ratansingh feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT arjunsinhnakum feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT roberttweedy feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT leandromilettotonetto feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT craigmzimring feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT matthewdoiron feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT amydrodriguez feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT allanilevey feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing AT garidclifford feasibilitystudyonindoorlocalizationandmultipersontrackingusingsparselydistributedcameranetworkwithedgecomputing |