Multiple Depth Sensor Setup and Synchronization for Marker-Less 3D Human Foot Tracking in a Hallway

Gutta, Vinod; Baddour, Natalie; Fallavollita, Pascal; Lemaire, Edward D.

doi:10.1109/seh.2019.00021

Cited by 4 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

Section: B Room Coordinate Systemmentioning

confidence: 99%

“…3D point cloud points were constructed from each sensor's background-subtracted depth images and then transformed into the first sensor's coordinate system [20]. This "combined point cloud" points were transformed into RCS by multiplying with transformation matrix #⃪% , obtained from (1).…”

Section: Point Cloud Constructionmentioning

confidence: 99%

“…In our previous work [20] , a physical setup with six Intel RealSense D415 sensors was configured in the lab to replicate a hallway scenario ( Fig. 1 ).…”

Section: System Setup and Synchronizationmentioning

confidence: 99%

“…This reference coordinate system was labelled as the Room Coordinate System (RCS). Methods from our previous study [20] were used to transform point cloud data from all the sensors into the first sensor’s color coordinate system, then transformed into the RCS by determining a transformation matrix \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$T_{R\leftarrow 1}$ \end{document} (1) .

FIGURE 2.…”

Section: System Setup and Synchronizationmentioning

confidence: 99%

“…3D point cloud points were constructed from each sensor’s background-subtracted depth images and then transformed into the first sensor’s coordinate system [20] . This “combined point cloud” points were transformed into RCS by multiplying with transformation matrix \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$T_{R\leftarrow 1}$ \end{document} , obtained from (1) .…”

Section: Point Cloudmentioning

confidence: 99%

See 4 more Smart Citations

Development of a Smart Hallway for Marker-Less Human Foot Tracking and Stride Analysis

Gutta

Fallavollita

Baddour

et al. 2021

IEEE J. Transl. Eng. Health Med.

Self Cite

View full text Add to dashboard Cite

In this research, a marker-less 'smart hallway' is proposed where stride parameters are computed as a person walks through an institutional hallway. Stride analysis is a viable tool for identifying mobility changes, classifying abnormal gait, estimating fall risk, monitoring progression of rehabilitation programs, and indicating progression of nervous system related disorders. Methods: Smart hallway was build using multiple Intel RealSense D415 depth cameras. A novel algorithm was developed to track a human foot using combined point cloud data obtained from the smart hallway. A method was implemented to separate the left and right leg point cloud data, then find the average foot dimensions. Foot tracking was achieved by fitting a box with average foot dimensions to the foot, with the box's base on the foot's bottom plane. A smart hallway with this novel foot tracking algorithm was tested with 22 able-bodied volunteers by comparing marker-less system stride parameters with Vicon motion analysis output. Results: With smart hallway frame rate at approximately 60fps, temporal stride parameter absolute mean differences were less than 30ms. Random noise around the foot's point cloud was observed, especially during foot strike phases. This caused errors in medial-lateral axis dependent parameters such as step width and foot angle. Anterior-posterior dependent (stride length, step length) absolute mean differences were less than 25mm. Conclusion: This novel marker-less smart hallway approach delivered promising results for stride analysis with small errors for temporal stride parameters, anterior-posterior stride parameters, and reasonable errors for medial-lateral spatial parameters.

show abstract

Section: B Room Coordinate Systemmentioning

confidence: 99%

Section: Point Cloud Constructionmentioning

confidence: 99%

“…In our previous work [20] , a physical setup with six Intel RealSense D415 sensors was configured in the lab to replicate a hallway scenario ( Fig. 1 ).…”

Section: System Setup and Synchronizationmentioning

confidence: 99%

FIGURE 2.…”

Section: System Setup and Synchronizationmentioning

confidence: 99%

Section: Point Cloudmentioning

confidence: 99%

See 3 more Smart Citations

Development of a Smart Hallway for Marker-Less Human Foot Tracking and Stride Analysis

Gutta

Fallavollita

Baddour

et al. 2021

IEEE J. Transl. Eng. Health Med.

Self Cite

View full text Add to dashboard Cite

show abstract

Perancangan dan Penerapan Motion Capture Pada Karakter 3D Dalam Video

Pratama

Frenky

2022

oai

View full text Add to dashboard Cite

Perancangan dan Penerapan Motion Capture pada Karakter 3D dalam Video. Motion Capture adalah teknologi yang dapat merekam pergerakan model manusia menjadi digital 2D atau 3D secara realistis. Di Indonesia sendiri, pengguna teknologi Motion Capture masih minim peminat, factor cost sangat mahal dan ketersediaan sistem Motion Capture terbatas. Seiring berjalannya waktu, ditemukan teknologi Mocap yang lebih sederhana dan mudah digunakan oleh masyarakat umum dengan menggunakan kamera Kinect, yang memungkinkan kita menghasilkan informasi kedalaman, tekstur, pengguna, dan kerangka. Metode penelitian video animasi 3D ini menggunakan MDLC (Multimedia Development Life Cycle). Video animasi ini dibuat dengan menggunakan teknik Mocap Markerless dan aplikasi Blender 2.79b sebagai media pembuatan karakter 3D hingga ke tahap animasi 3D. Perancangan dan implementasi Motion Capture pada karakter 3D dalam video ini bertujuan untuk membuktikan dan dapat membantu pengguna Mocap memahami bagaimana merancang dan mengimplementasikan kreasi Motion Capture sederhana pada karakter 3D ke dalam video.

show abstract

Validity and Reliability of a Non-Radiographic Postural Analysis Device Based on an RGB-Depth Camera Comparing EOS 3D Imaging: A Prospective Observational Study

et al. 2023

View full text Add to dashboard Cite

The posture-analyzing and virtual reconstructing device (PAViR) used a Red Green Blue-Depth camera as a sensor and skeleton reconstruction images were produced. This PAViR quickly analyzed the whole posture from multiple repetitive shots without radiation exposure in clothes and provided a virtual skeleton within seconds. This study aims to evaluate the reliability when shooting repeatedly and to assess the validity compared to parameters of full-body, low-dose X-rays (EOSs) when applied as diagnostic imaging. As a prospective and observational study, 100 patients with musculoskeletal pain underwent an EOS to obtain whole body coronal and sagittal images. The outcome measures were human posture parameters, which were divided by the standing plane in both EOSs and PAViRs as follows: (1) a coronal view (asymmetric clavicle height, pelvic oblique, bilateral Q angles of the knee, and center of seventh cervical vertebra-central sacral line (C7-CSL)) and (2) a sagittal view (forward head posture). A validation of the PAViR compared to the EOSs revealed that C7-CSL showed a moderate positive correlation with that of the EOS (r = 0.42, p < 0.01). The forward head posture (r = 0.39, p < 0.01), asymmetric clavicle height (r = 0.37, p < 0.01), and pelvic oblique (r = 0.32, p < 0.01) compared to those of the EOS had slightly positive correlations. The PAViR has excellent intra-rater reliability in people with somatic dysfunction. Except for both Q angles, the PAViR has fair-to-moderate validation when compared to EOS diagnostic imaging in the parameter representing coronal and sagittal imbalance. Although the PAViR system is not yet available in the medical field, it has the potential to become a radiation-free, accessible, and cost-effective postural analysis diagnostic tool after the EOS era.

show abstract

Multiple Depth Sensor Setup and Synchronization for Marker-Less 3D Human Foot Tracking in a Hallway

Cited by 4 publications

References 9 publications

Development of a Smart Hallway for Marker-Less Human Foot Tracking and Stride Analysis

Development of a Smart Hallway for Marker-Less Human Foot Tracking and Stride Analysis

Perancangan dan Penerapan Motion Capture Pada Karakter 3D Dalam Video

Validity and Reliability of a Non-Radiographic Postural Analysis Device Based on an RGB-Depth Camera Comparing EOS 3D Imaging: A Prospective Observational Study

Contact Info

Product

Resources

About