Markerless Human Motion Tracking From a Single Camera Using Interval Particle Filtering

Saboune, Jamal; Charpillet, François

doi:10.1142/s021821300700345x

Cited by 8 publications

(8 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Their system contained spatiotemporal variables and stride time error less than 0.02s. The authors in [26] have proposed a Gait analysis system composed by only a single RGB camera. The methodology applied generates a silhouette using particles filtering from a synthetic image.…”

Section: Marker-less Technologiesmentioning

confidence: 99%

Human gait assessment using a 3D marker-less multimodal motion capture system

Rodrigues

Salgado

Catháin

et al. 2019

Multimed Tools Appl

View full text Add to dashboard Cite

Gait analysis is the measurement, processing and systematic interpretation of biomechanical parameters that characterize human locomotion. It supports the identification of movement limitations and development of rehabilitation procedures. Accurate Gait analysis is important in sports analysis, medical field, and rehabilitation. Although Gait analysis is performed in several laboratories in many countries, there are many issues such as: (i) the high cost of precise Motion Capture systems; (ii) the scarcity of qualified personnel to operate them; (iii) expertise required to interpret their results; (iv) space requirements to install and store these systems; as well as difficulties related to the measurement protocols of each system; (vi) limited availability (vii) and the use of markers can be a barrier for some clinical use cases (e.g. patients recovering from orthopedics surgeries). In this work, we present a low cost and more accessible system based on the integration of a Multiple Microsoft Kinect sensors and multiple Shimmer inertial sensors to capture human Gait. The novel multimodal system combines data from inertial and 3D depth cameras and outputs spatiotemporal Gait variables. A comparison of this system with the VICON system (the gold standard in Motion Capture) was performed. Our relatively low-cost marker-less multimodal motion generates a complete 360-degree skeleton view. We compare our system with the VICON via gait spatiotemporal variables: Gait cycle time, stride time, Gait length (distance between two strides), stride length, and velocity. The system was also evaluated with knee and hip joint angles measurement accuracy. The results show high correlation for spatiotemporal variables and joint angles inside the 95% bootstrap prediction when compared with VICON.

show abstract

Section: Marker-less Technologiesmentioning

confidence: 99%

Human gait assessment using a 3D marker-less multimodal motion capture system

Rodrigues

Salgado

Catháin

et al. 2019

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Thus, the ability of the tracker to detect newly appearing objects is still reduced. Saboune et al [20] introduced a modified particle filtering for 3D human motion capture. The proposed Interval Particle Filtering algorithm reduces the number of particles needed and overcomes the particles degeneration problem by introducing constant particles.…”

Section: Particle Filtering and Object Trackingmentioning

confidence: 99%

“…This problem is known as particles degeneration. The Interval Particle Filtering [20] introduced for human motion capture modifies the Condensation algorithm in a way to overcome this problem when using a smaller number of particles. In fact, it preserves the advantages of a particle filter algorithm and adopts the same three steps structure with modifications on the selection and prediction steps:…”

Section: Explorative Particle Filtering (Expf)mentioning

confidence: 99%

People detection and tracking using the Explorative Particle Filtering

Saboune

Laganière

2009

2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops

Self Cite

View full text Add to dashboard Cite

Automatic people detection and tracking is a very essential task of video surveillance systems. It can improve a system's performance in important fields such as security, safety, human activity monitoring etc. In this paper we present a novel approach for people detection and 3D tracking. Our method is based on a human upper body 3D model and a likelihood function to evaluate its presence in a certain region of the scene. We then find the maxima of this function using a modified particle filtering algorithm which we call Explorative Particle Filtering (ExPF). We designed this algorithm in a way to guarantee a multiple objects tracking and a good estimation of their positions when using a small number of particles. Our technique is generic and simple as no dynamic models nor trained features models (color, shape etc.) were used. We also show some tracking results from video surveillance feeds in order to illustrate our approach.

show abstract

“…Certainly setting a camera with a sagittal view and one in the frontal view would improve the reliability and validity of joint angles but this adds to the complexity of calibrating and adjusting the system (Saboune and Charpillet, 2007). One method used, in an attempt to improve reliability in measuring joint angles, is the addition of reflective markers.…”

Section: Introductionmentioning

confidence: 99%

Reliability of sagittal plane hip, knee, and ankle joint angles from a single frame of video data using the GAITRite camera system

Ross¹,

Rice²,

Behren³

et al. 2014

Physiotherapy Theory and Practice

View full text Add to dashboard Cite

The purpose of this study was to establish intra-rater, intra-session, and inter-rater, reliability of sagittal plane hip, knee, and ankle angles with and without reflective markers using the GAITRite walkway and single video camera between student physical therapists and an experienced physical therapist. This study included thirty-two healthy participants age 20-59, stratified by age and gender. Participants performed three successful walks with and without markers applied to anatomical landmarks. GAITRite software was used to digitize sagittal hip, knee, and ankle angles at two phases of gait: (1) initial contact; and (2) mid-stance. Intra-rater reliability was more consistent for the experienced physical therapist, regardless of joint or phase of gait. Intra-session reliability was variable, the experienced physical therapist showed moderate to high reliability (intra-class correlation coefficient (ICC) = 0.50-0.89) and the student physical therapist showed very poor to high reliability (ICC = 0.07-0.85). Inter-rater reliability was highest during mid-stance at the knee with markers (ICC = 0.86) and lowest during mid-stance at the hip without markers (ICC = 0.25). Reliability of a single camera system, especially at the knee joint shows promise. Depending on the specific type of reliability, error can be attributed to the testers (e.g. lack of digitization practice and marker placement), participants (e.g. loose fitting clothing) and camera systems (e.g. frame rate and resolution). However, until the camera technology can be upgraded to a higher frame rate and resolution, and the software can be linked to the GAITRite walkway, the clinical utility for pre/post measures is limited.

show abstract

Markerless Human Motion Tracking From a Single Camera Using Interval Particle Filtering

Cited by 8 publications

References 2 publications

Human gait assessment using a 3D marker-less multimodal motion capture system

Human gait assessment using a 3D marker-less multimodal motion capture system

People detection and tracking using the Explorative Particle Filtering

Reliability of sagittal plane hip, knee, and ankle joint angles from a single frame of video data using the GAITRite camera system

Contact Info

Product

Resources

About