Automatic Timed Up-and-Go Sub-Task Segmentation for Parkinson’s Disease Patients Using Video-Based Activity Classification

Li, Tianpeng; Chen, Jiansheng; Hu, Chunhua; Ma, Yu; Wu, Zhiyuan; Wan, Wei; Huang, Yiqing; Jia, Fuming; Gong, Chen; Wan, Sen; Li, Luming

doi:10.1109/tnsre.2018.2875738

Cited by 53 publications

(57 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus far human pose tracking has been explored for various methods of measuring gait and mobility in the older adult population, including automatically acquiring the clinical parameters measured in the timed up-and-go (TUG) test, which is a clinical measure of mobility [26], step monitoring [27], and general gait parameter extraction [28]. Another application which has been extensively researched is the detection of falls [29][30][31].…”

Section: B Human Pose Estimationmentioning

confidence: 99%

Measuring Gait Variables Using Computer Vision to Assess Mobility and Fall Risk in Older Adults With Dementia

Mehdizadeh

Iaboni

et al. 2020

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

Fall risk is high for older adults with dementia. Gait impairment contributes to increased fall risk, and gait changes are common in people with dementia, although the reliable assessment of gait is challenging in this population. This study aimed to develop an automated approach to performing gait assessments based on gait data that is collected frequently and unobtrusively, and analysed using computer vision methods. Recent developments in computer vision have led to the availability of open source human pose estimation algorithms, which automatically estimate the joint locations of a person in an image. In this study, a preexisting pose estimation model was applied to 1066 walking videos collected of 31 older adults with dementia as they walked naturally in a corridor on a specialized dementia unit over a two week period. Using the tracked pose information, gait features were extracted from video recordings of gait bouts and their association with clinical mobility assessment scores and future falls data was examined. A significant association was found between extracted gait features and a clinical mobility assessment and the number of future falls, providing concurrent and predictive validation of this approach.

show abstract

Section: B Human Pose Estimationmentioning

confidence: 99%

Measuring Gait Variables Using Computer Vision to Assess Mobility and Fall Risk in Older Adults With Dementia

Mehdizadeh

Iaboni

et al. 2020

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

show abstract

“…Moreover, it is also true that a great quantity of data collected through sensor systems is inherently noisy, and for this reason, its analysis should consider and handle some degree of uncertainty [32]. In this context, the presented algorithm can be used as an objective labelisation procedure for artificial intelligence methods to provide reliable ground truth data for supervised classification tasks in the field of big data analytics and Human Activity Recognition [33], [34]. This is the first study that aims at comparing human and automated assessments in the identification of the events that divide the different phases of the STS movement, relying on data collected through a force plate.…”

Section: Discussionmentioning

confidence: 99%

Quantitative Comparison of Human and Software Reliability in the Categorization of Sit-to-Stand Motion Pattern

Job

Battista

Stanzani

et al. 2021

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

The Sit-to-Stand (STS) test is used in clinical practice as an indicator of lower-limb functionality decline, especially for older adults. Due to its high variability, there is no standard approach for categorising the STS movement and recognising its motion pattern. This paper presents a comparative analysis between visual assessments and an automated-software for the categorisation of STS, relying on registrations from a force plate. 5 participants (30 ± 6 years) took part in 2 different sessions of visual inspections on 200 STS movements under self-paced and controlled speed conditions. Assessors were asked to identify three specific STS events from the Ground Reaction Force, simultaneously with the software analysis: the start of the trunk movement (Initiation), the beginning of the stable upright stance (Standing) and the sitting movement (Sitting). The absolute agreement between the repeated raters' assessments as well as between the raters' and software's assessment in the first trial, were considered as indexes of human and software performance, respectively. No statistical differences between methods were found for the identification of the Initiation and the Sitting events at self-paced speed and for only the Sitting event at controlled speed. The estimated significant values of maximum discrepancy between visual and automated assessments were 0.200 [0.039; 0.361] s in unconstrained conditions and 0.340 [0.014; 0.666] s for standardised movements. The software assessments displayed an overall good agreement against visual evaluations of the Ground Reaction Force, relying, at the same time, on objective measures.

show abstract

“…First, the subjects are not necessarily asked to perform TUG test even they did in our experiment. We need not try to identify the phases of TUG test as others did [14][15][16] [17]. This makes the method automatic, unobtrusive and easy to deploy at any setting.…”

Section: Discussionmentioning

confidence: 99%

Predicting TUG score from gait characteristics with video analysis and machine learning

Jian¹

2020

Preprint

View full text Add to dashboard Cite

Fall is a leading cause of death which suffers the elderly and society. Timed Up and Go (TUG) test is a common tool for fall risk assessment. In this paper, we propose a method for predicting TUG score from gait characteristics extracted from video with computer vision and machine learning technologies. First, 3D pose is estimated from video captured with 2D and 3D cameras during human motion and then a group of gait characteristics are computed from 3D pose series. After that, copula entropy is used to select those characteristics which are mostly associated with TUG score. Finally, the selected characteristics are fed into the predictive models to predict TUG score. Experiments on real world data demonstrated the effectiveness of the proposed method. As a byproduct, the associations between TUG score and several gait characteristics are discovered, which laid the scientific foundation of the proposed method and make the predictive models such built interpretable to clinical users.

show abstract

Automatic Timed Up-and-Go Sub-Task Segmentation for Parkinson’s Disease Patients Using Video-Based Activity Classification

Cited by 53 publications

References 21 publications

Measuring Gait Variables Using Computer Vision to Assess Mobility and Fall Risk in Older Adults With Dementia

Measuring Gait Variables Using Computer Vision to Assess Mobility and Fall Risk in Older Adults With Dementia

Quantitative Comparison of Human and Software Reliability in the Categorization of Sit-to-Stand Motion Pattern

Predicting TUG score from gait characteristics with video analysis and machine learning

Contact Info

Product

Resources

About