Automatic Classification of Gait Impairments Using a Markerless 2D Video-Based System

Gait Impairment Analysis Using Silhouette Sinogram Signals and Assisted Knowledge Learning

The analysis of body motion is a valuable tool in the assessment and diagnosis of gait impairments, particularly those related to neurological disorders. In this study, we propose a novel automated system leveraging artificial intelligence for efficiently analyzing gait impairment from video-recorded images. The proposed methodology encompasses three key aspects. First, we generate a novel one-dimensional representation of each silhouette image, termed a silhouette sinogram, by computing the distance and angle between the centroid and each detected boundary points. This process enables us to effectively utilize relative variations in motion at different angles to detect gait patterns. Second, a one-dimensional convolutional neural network (1D CNN) model is developed and trained by incorporating the consecutive silhouette sinogram signals of silhouette frames to capture spatiotemporal information via assisted knowledge learning. This process allows the network to capture a broader context and temporal dependencies within the gait cycle, enabling a more accurate diagnosis of gait abnormalities. This study conducts training and an evaluation utilizing the publicly accessible INIT GAIT database. Finally, two evaluation schemes are employed: one leveraging individual silhouette frames and the other operating at the subject level, utilizing a majority voting technique. The outcomes of the proposed method showed superior enhancements in gait impairment recognition, with overall F1-scores of 100%, 90.62%, and 77.32% when evaluated based on sinogram signals, and 100%, 100%, and 83.33% when evaluated based on the subject level, for cases involving two, four, and six gait abnormalities, respectively. In conclusion, by comparing the observed locomotor function to a conventional gait pattern often seen in healthy individuals, the recommended approach allows for a quantitative and non-invasive evaluation of locomotion.

Empowering Lower Limb Disorder Identification through PoseNet and Artificial Intelligence

A novel approach is presented in this study for the classification of lower limb disorders, with a specific emphasis on the knee, hip, and ankle. The research employs gait analysis and the extraction of PoseNet features from video data in order to effectively identify and categorize these disorders. The PoseNet algorithm facilitates the extraction of key body joint movements and positions from videos in a non-invasive and user-friendly manner, thereby offering a comprehensive representation of lower limb movements. The features that are extracted are subsequently standardized and employed as inputs for a range of machine learning algorithms, such as Random Forest, Extra Tree Classifier, Multilayer Perceptron, Artificial Neural Networks, and Convolutional Neural Networks. The models undergo training and testing processes using a dataset consisting of 174 real patients and normal individuals collected at the Tehsil Headquarter Hospital Sadiq Abad. The evaluation of their performance is conducted through the utilization of K-fold cross-validation. The findings exhibit a notable level of accuracy and precision in the classification of various lower limb disorders. Notably, the Artificial Neural Networks model achieves the highest accuracy rate of 98.84%. The proposed methodology exhibits potential in enhancing the diagnosis and treatment planning of lower limb disorders. It presents a non-invasive and efficient method of analyzing gait patterns and identifying particular conditions.

[A two-dimensional video based quantification method and clinical application research of motion disorders]

The increasing prevalence of the aging population, and inadequate and uneven distribution of medical resources, have led to a growing demand for telemedicine services. Gait disturbance is a primary symptom of neurological disorders such as Parkinson's disease (PD). This study proposed a novel approach for the quantitative assessment and analysis of gait disturbance from two-dimensional (2D) videos captured using smartphones. The approach used a convolutional pose machine to extract human body joints and a gait phase segmentation algorithm based on node motion characteristics to identify the gait phase. Moreover, it extracted features of the upper and lower limbs. A height ratio-based spatial feature extraction method was proposed that effectively captures spatial information. The proposed method underwent validation via error analysis, correction compensation, and accuracy verification using the motion capture system. Specifically, the proposed method achieved an extracted step length error of less than 3 cm. The proposed method underwent clinical validation, recruiting 64 patients with Parkinson's disease and 46 healthy controls of the same age group. Various gait indicators were statistically analyzed using three classic classification methods, with the random forest method achieving a classification accuracy of 91%. This method provides an objective, convenient, and intelligent solution for telemedicine focused on movement disorders in neurological diseases.

Measurement of Functional Use in Upper Extremity Prosthetic Devices Using Wearable Sensors and Machine Learning

Trials for therapies after an upper limb amputation (ULA) require a focus on the real-world use of the upper limb prosthesis. In this paper, we extend a novel method for identifying upper extremity functional and nonfunctional use to a new patient population: upper limb amputees. We videotaped five amputees and 10 controls performing a series of minimally structured activities while wearing sensors on both wrists that measured linear acceleration and angular velocity. The video data was annotated to provide ground truth for annotating the sensor data. Two different analysis methods were used: one that used fixed-size data chunks to create features to train a Random Forest classifier and one that used variable-size data chunks. For the amputees, the fixed-size data chunk method yielded good results, with 82.7% median accuracy (range of 79.3-85.8) on the 10-fold cross-validation intra-subject test and 69.8% in the leave-one-out inter-subject test (range of 61.4-72.8). The variable-size data method did not improve classifier accuracy compared to the fixed-size method. Our method shows promise for inexpensive and objective quantification of functional upper extremity (UE) use in amputees and furthers the case for use of this method in assessing the impact of UE rehabilitative treatments.

User Profiling to Enhance Clinical Assessment and Human-Robot Interaction: A Feasibility Study

Socially Assistive Robots (SARs) are designed to support us in our daily life as a companion, and assistance but also to support the caregivers' work. SARs should show personalized and human-like behavior to improve their acceptance and, consequently, their use. Additionally, they should be trustworthy by caregivers and professionals to be used as support for their work (e.g. objective assessment, decision support tools). In this context the aim of the paper is dual. Firstly, this paper aims to present and discuss the robot behavioral model based on sensing, perception, decision support, and interaction modules. The novel idea behind the proposed model is to extract and use the same multimodal features set for two purposes: (i) to profile the user, so to be used by the caregiver as a decision support tool for the assessment and monitoring of the patient; (ii) to fine-tune the human-robot interaction if they can be correlated to the social cues. Secondly, this paper aims to test in a real environment the proposed model using a SAR robot, namely ASTRO. Particularly, it measures the body posture, the gait cycle, and the handgrip strength during the walking support task. Those collected data were analyzed to assess the clinical profile and to fine-tune the physical interaction. Ten older people (65.2 ± 15.6 years) were enrolled for this study and were asked to walk with ASTRO at their normal speed for 10 m. The obtained results underline a good estimation (p < 0.05) of gait parameters, handgrip strength, and angular excursion of the torso with respect to most used instruments. Additionally, the sensory outputs were combined in the perceptual model to profile the user using non-classical and unsupervised techniques for dimensionality reduction namely T-distributed Stochastic Neighbor Embedding (t-SNE) and non-classic multidimensional scaling (nMDS). Indeed, these methods can group the participants according to their residual walking abilities.

Walking Speed Classification from Marker-Free Video Images in Two-Dimension Using Optimum Data and a Deep Learning Method

Walking speed is considered a reliable assessment tool for any movement-related functional activities of an individual (i.e., patients and healthy controls) by caregivers and clinicians. Traditional video surveillance gait monitoring in clinics and aged care homes may employ modern artificial intelligence techniques to utilize walking speed as a screening indicator of various physical outcomes or accidents in individuals. Specifically, ratio-based body measurements of walking individuals are extracted from marker-free and two-dimensional video images to create a walk pattern suitable for walking speed classification using deep learning based artificial intelligence techniques. However, the development of successful and highly predictive deep learning architecture depends on the optimal use of extracted data because redundant data may overburden the deep learning architecture and hinder the classification performance. The aim of this study was to investigate the optimal combination of ratio-based body measurements needed for presenting potential information to define and predict a walk pattern in terms of speed with high classification accuracy using a deep learning-based walking speed classification model. To this end, the performance of different combinations of five ratio-based body measurements was evaluated through a correlation analysis and a deep learning-based walking speed classification test. The results show that a combination of three ratio-based body measurements can potentially define and predict a walk pattern in terms of speed with classification accuracies greater than 92% using a bidirectional long short-term memory deep learning method.

mVEGAS - mobile smartphone-based spatiotemporal gait analysis in healthy and ataxic gait disorders

BACKGROUND

Quantitative gait assessment is increasingly applied in fall risk stratification, diagnosis, and disease monitoring of neuro-geriatric gait disorders. Its broad application, however, demands for low-cost and mobile solutions that facilitate high-quality assessment outside laboratory settings. The aim of this study was to present and evaluate the concurrent validity of a mobile and low-cost gait assessment tool (mVEGAS) that combines body-fixed inertial sensors and a smartphone-based video capture for spatiotemporal identification of gait sequences.

METHODS

Initially, we examined potential interferences of wearing mVEGAS with walking performance in a cohort of 20 young healthy individuals (31.1 ± 10.1 years; 8 females). Subsequently, we assessed the concurrent validity of mVEGAS as compared to a pressure-sensitive gait carpet (GAITRite) in a cohort of 26 healthy individuals (55.8 ± 14.3 years; 10 females) and 26 patients (55.7 ± 14.0; 14 females) with moderate to severe degrees of cerebellar gait ataxia. All participants were instructed to walk at preferred, slow, and fast walking speed and standard average and variability gait measures including velocity, stride length, stride time, base of support, swing and double support phase were examined for agreement between the two systems by absolute error and intraclass correlation coefficients (ICC).

RESULTS

Wearing mVEGAS did only marginally interfere with normal walking behavior. mVEGAS-derived average and variability gait measures exhibited good to excellent concurrent validity in healthy individuals (ICCs ranging between 0.645 and 1.000) and patients with gait ataxia (ICCs ranging between 0.788 and 1.000) SIGNIFICANCE: mVEGAS may facilitate high-quality and long-term gait monitoring in different non-specialized environments such as medical practices, nursing homes or community centers.

A Riemannian Deep Learning Representation to Describe Gait Parkinsonian Locomotor Patterns

Parkinson is the second most common neurodegenerative disease, mainly related to progressive locomotor alterations caused by dopamine deficiency. The gait kinematic is a principal disease biomarker that associates patterns like the step length, flexed posture, and bradykinesia with disease progression. Nonetheless, these patterns are analyzed from invasive setups that only capture coarse dynamics at advanced disease stages. This work introduces a very compact and robust deep representation that effectively learns a Riemannian manifold to describe locomotor parkinsonian patterns. Contrary to traditional deep strategies, the presented framework fully explores data geometry from input mean covariance matrices representing video sequences. These symmetric positive definite (SPD) matrices lie in a Riemannian manifold. Then such matrices are projected to the SPD net, which learns a bank of SPD matrices from a non-linear training, that may be exploited in a hierarchical composition from a set of layers. In a final layer, a projection in a Euclidean space allows learning the discriminatory patterns of PD w.r.t control population. In a retrospective study with a total of 22 patients (11 Parkinson's and 11 controls), the proposed approach achieves a remarkable classification between Parkinson's and control video sequences, correctly labeling all Parkinson's patients, and outperforming typical 3D convolutional representations. Clinical relevance- The study of gait parkinsonian descrip-tors computed from a Riemannian geometry, built from a deep representation.

Diagnostic value of a vision-based intelligent gait analyzer in screening for gait abnormalities

BACKGROUND

Early detection of gait abnormalities is critical for preventing severe injuries in future falls. The timed up and go (TUG) test is a commonly used clinical gait screening test; however, the interpretation of its results is limited to the TUG total time.

RESEARCH QUESTION

What is diagnostic accuracy of the low-cost, markerless, automated gait analyzer, with the aid of vision-based artificial intelligence technology, which extract gait spatiotemporal features and screen for abnormal walking patterns through video recordings of the TUG test?

METHODS

Our dataset contained retrospective data from outpatients from the Department of Neurology or Rehabilitation of two tertiary hospitals in Shanghai. A panel of three expert neurologists specialized in movement disorders reviewed the gait performance in each TUG video, and labeled them separately, with the most commonly assigned label being used as the reference standard. The gait analyzer performed the AlphaPose algorithm to track the human joint position and calculated the spatiotemporal parameters by filtering and double-threshold signal detection. Gait spatiotemporal features and expert labels were input into machine learning models, and the accuracy of each model was tested with leave-one-out cross-validation (LOOCV).

RESULTS

A total of 284 participants were recruited. Among these, 100 were labeled as having abnormal gait performance by experts. The Naive Bayes classifier achieved the best performance with a full-data accuracy of 90.14% and a LOOCV accuracy of 89.08% for screening abnormal gait performance.

SIGNIFICANCE

This study is the first to investigate the accuracy of a vision-based intelligent gait analyzer for screening abnormal clinical gait performance. By virtue of a pose estimation algorithm and machine learning models, our intelligent gait analyzer can detect abnormal walking patterns approximate to judgements made by experienced neurologists, which is expected to be a supplementary gait assessment protocol for basic-level doctors in the future.

Visualising and quantifying relevant parkinsonian gait patterns using 3D convolutional network

Parkinson's disease (PD) lacks a definitive diagnosis, with the observation of motion patterns being the main method of characterizing disease progression and planning patient treatments. Among PD observations, gait motion patterns, such as step length, flexed posture, and bradykinesia, support the characterization of disease progression. However, this analysis is usually performed with marker-based protocols, which affect the gait and localized segment patterns during locomotion. This work introduces a 3D convolutional gait representation for automatic PD classification that identifies the spatio-temporal patterns used for classification. This approach allows us to obtain an explainable model that classifies markerless sequences and describes the main learned spatio-temporal regions associated with abnormal patterns in a particular video. Initially, a spatio-temporal convolutional network is trained from a set of raw videos and optical flow fields. Then, a PD prediction is obtained from the motion patterns learned by the trained model. Finally, saliency maps, which highlight abnormal motion patterns, are obtained by retro-propagating the output prediction up to the input volume through two different stages: an embedded back-tracking and a pseudo-deconvolution process. From a total of 176 videos from 22 patients, the resulting salient maps highlight lower limb patterns possibly related to step length and speed. In control subjects, the saliency maps highlight the head and trunk posture. The proposed approach achieved an average accuracy score of 94.89%.

Remote Gait Type Classification System Using Markerless 2D Video

Several pathologies can alter the way people walk, i.e., their gait. Gait analysis can be used to detect such alterations and, therefore, help diagnose certain pathologies or assess people's health and recovery. Simple vision-based systems have a considerable potential in this area, as they allow the capture of gait in unconstrained environments, such as at home or in a clinic, while the required computations can be done remotely. State-of-the-art vision-based systems for gait analysis use deep learning strategies, thus requiring a large amount of data for training. However, to the best of our knowledge, the largest publicly available pathological gait dataset contains only 10 subjects, simulating five types of gait. This paper presents a new dataset, GAIT-IT, captured from 21 subjects simulating five types of gait, at two severity levels. The dataset is recorded in a professional studio, making the sequences free of background camouflage, variations in illumination and other visual artifacts. The dataset is used to train a novel automatic gait analysis system. Compared to the state-of-the-art, the proposed system achieves a drastic reduction in the number of trainable parameters, memory requirements and execution times, while the classification accuracy is on par with the state-of-the-art. Recognizing the importance of remote healthcare, the proposed automatic gait analysis system is integrated with a prototype web application. This prototype is presently hosted in a private network, and after further tests and development it will allow people to upload a video of them walking and execute a web service that classifies their gait. The web application has a user-friendly interface usable by healthcare professionals or by laypersons. The application also makes an association between the identified type of gait and potential gait pathologies that exhibit the identified characteristics.

A Systematic Review of Machine Learning Based Gait characteristics in Parkinson's disease

OBJECTIVE

Parkinson's disease is a pervasive neuro disorder that affects people's quality of life throughout the world. The unsatisfactory results of clinical rating scales open the door for more research. PD treatment using current biomarkers seems a difficult task. So automatic evaluation at an early stage may enhance the quality and time-period of life.

METHODS

Grading of Recommendations Assessment, Development, and Evaluation (GRADE) and Population, intervention, comparison, and outcome (PICO) search methodology schemes are followed to search the data and eligible studies for this survey. Approximate 1500 articles were extracted using related search strings. After the stepwise mapping and elimination of studies, 94 papers are found suitable for the present review.

RESULTS

After the quality assessment of extracted studies, nine inhibitors are identified to analyze people's gait with Parkinson's disease, where four are critical. This review also differentiates the various machine learning classification techniques with their PD analysis characteristics in previous studies. The extracted research gaps are described as future perspectives. Results can help practitioners understand the PD gait as a valuable biomarker for detection, quantification, and classification.

CONCLUSION

Due to less cost and easy recording of gait, gait-based techniques are becoming popular in PD detection. By encapsulating the gait-based studies, it gives an in-depth knowledge of PD, different measures that affect gait detection and classification.

A Spatiotemporal Deep Learning Approach for Automatic Pathological Gait Classification

Human motion analysis provides useful information for the diagnosis and recovery assessment of people suffering from pathologies, such as those affecting the way of walking, i.e., gait. With recent developments in deep learning, state-of-the-art performance can now be achieved using a single 2D-RGB-camera-based gait analysis system, offering an objective assessment of gait-related pathologies. Such systems provide a valuable complement/alternative to the current standard practice of subjective assessment. Most 2D-RGB-camera-based gait analysis approaches rely on compact gait representations, such as the gait energy image, which summarize the characteristics of a walking sequence into one single image. However, such compact representations do not fully capture the temporal information and dependencies between successive gait movements. This limitation is addressed by proposing a spatiotemporal deep learning approach that uses a selection of key frames to represent a gait cycle. Convolutional and recurrent deep neural networks were combined, processing each gait cycle as a collection of silhouette key frames, allowing the system to learn temporal patterns among the spatial features extracted at individual time instants. Trained with gait sequences from the GAIT-IT dataset, the proposed system is able to improve gait pathology classification accuracy, outperforming state-of-the-art solutions and achieving improved generalization on cross-dataset tests.

Fall Detection of Elderly People Using the Manifold of Positive Semidefinite Matrices

Falls are one of the most critical health care risks for elderly people, being, in some adverse circumstances, an indirect cause of death. Furthermore, demographic forecasts for the future show a growing elderly population worldwide. In this context, models for automatic fall detection and prediction are of paramount relevance, especially AI applications that use ambient, sensors or computer vision. In this paper, we present an approach for fall detection using computer vision techniques. Video sequences of a person in a closed environment are used as inputs to our algorithm. In our approach, we first apply the V2V-PoseNet model to detect 2D body skeleton in every frame. Specifically, our approach involves four steps: (1) the body skeleton is detected by V2V-PoseNet in each frame; (2) joints of skeleton are first mapped into the Riemannian manifold of positive semidefinite matrices of fixed-rank 2 to build time-parameterized trajectories; (3) a temporal warping is performed on the trajectories, providing a (dis-)similarity measure between them; (4) finally, a pairwise proximity function SVM is used to classify them into fall or non-fall, incorporating the (dis-)similarity measure into the kernel function. We evaluated our approach on two publicly available datasets URFD and Charfi. The results of the proposed approach are competitive with respect to state-of-the-art methods, while only involving 2D body skeletons.

Recent Approaches on Classification and Feature Extraction of EEG Signal: A Review

Objective:

Electroencephalography (EEG) has an influential role in neuroscience and commercial applications. Most of the tools available for EEG signal analysis use machine learning to extract the required information. So, the study of robust techniques for feature extraction and classification is an important thing to understand the practical use of EEG. The paper aims that if there is any special tool for a particular task. Which feature domain or classifier has a significant role in EEG signal analysis?

Approach:

It presents a detailed report of the current trend for bio-electrical signals classification focusing on various classifiers’ advantages and disadvantages. This study includes literature from 2000 to 2021 with a brief description of EEG signal origin and advancement in classification techniques.

Results:

Randomly used classifiers for EEG signal can be categorized into five classes, namely Linear Classifiers, Nearest Neighbor Classifiers, Nonlinear Bayesian Classifiers, Neural Networks, and Combinations of Classifiers. Approximately 40% of studies use Support Vector Machine, Nearest Neighbor, and their combination with others. For specific tasks, particular classifiers are recommended in the survey. Features can be defined into four categories, namely TDFs, FDFs, TFDFs, and statistical features, where 39% of studies used TFDFs. Multi-domains features are preferred when the required information cannot be obtained from one domain.

Significance:

The paper summarizes the recent approaches for feature extraction and classification of EEG signals. It describes the brain waves with their classification, related behavior, and task with the physiological correlation. The comparative analysis of different classifiers, toolbox, the channel used, accuracy, and the number of subjects from various studies can help the practitioners choose a suitable classifier. Furthermore, future directions can cope up with the relevant problems and can lead to accurate classification.

Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification

Human body measurement data related to walking can characterize functional movement and thereby become an important tool for health assessment. Single-camera-captured two-dimensional (2D) image sequences of marker-less walking individuals might be a simple approach for estimating human body measurement data which could be used in walking speed-related health assessment. Conventional body measurement data of 2D images are dependent on body-worn garments (used as segmental markers) and are susceptible to changes in the distance between the participant and camera in indoor and outdoor settings. In this study, we propose five ratio-based body measurement data that can be extracted from 2D images and can be used to classify three walking speeds (i.e., slow, normal, and fast) using a deep learning-based bidirectional long short-term memory classification model. The results showed that average classification accuracies of 88.08% and 79.18% could be achieved in indoor and outdoor environments, respectively. Additionally, the proposed ratio-based body measurement data are independent of body-worn garments and not susceptible to changes in the distance between the walking individual and camera. As a simple but efficient technique, the proposed walking speed classification has great potential to be employed in clinics and aged care homes.

Testing the Performance of an Innovative Markerless Technique for Quantitative and Qualitative Gait Analysis

Gait abnormalities such as high stride and step frequency/cadence (SF-stride/second, CAD-step/second), stride variability (SV) and low harmony may increase the risk of injuries and be a sentinel of medical conditions. This research aims to present a new markerless video-based technology for quantitative and qualitative gait analysis. 86 healthy individuals (mead age 32 years) performed a 90 s test on treadmill at self-selected walking speed. We measured SF and CAD by a photoelectric sensors system; then, we calculated average ± standard deviation (SD) and within-subject coefficient of variation (CV) of SF as an index of SV. We also recorded a 60 fps video of the patient. With a custom-designed web-based video analysis software, we performed a spectral analysis of the brightness over time for each pixel of the image, that reinstituted the frequency contents of the videos. The two main frequency contents (F1 and F2) from this analysis should reflect the forcing/dominant variables, i.e., SF and CAD. Then, a harmony index (HI) was calculated, that should reflect the proportion of the pixels of the image that move consistently with F1 or its supraharmonics. The higher the HI value, the less variable the gait. The correspondence SF-F1 and CAD-F2 was evaluated with both paired t-Test and correlation and the relationship between SV and HI with correlation. SF and CAD were not significantly different from and highly correlated with F1 (0.893 ± 0.080 Hz vs. 0.895 ± 0.084 Hz, p < 0.001, r² = 0.99) and F2 (1.787 ± 0.163 Hz vs. 1.791 ± 0.165 Hz, p < 0.001, r² = 0.97). The SV was 1.84% ± 0.66% and it was significantly and moderately correlated with HI (0.082 ± 0.028, p < 0.001, r² = 0.13). The innovative video-based technique of global, markerless gait analysis proposed in our study accurately identifies the main frequency contents and the variability of gait in healthy individuals, thus providing a time-efficient, low-cost means to quantitatively and qualitatively study human locomotion.

Towards understanding spatio-temporal parkinsonian patterns from salient regions of a 3D convolutional network

Gait motion patterns such as step length, flexed posture, absent arm swing and bradykinesia, constitute the main source of information to describe and quantify Parkinson disease. Nevertheless, such quantification is commonly developed under marker based protocols, losing natural motion gestures, and only taking into account a limited description of the locomotion process. This work introduces a 3D convolutional gait representation, that uses markerless video sequences to automatically predict parkinsonian behaviours. A remarkable contribution herein presented is the quantification of spatio-temporal salient maps, that stand out body regions related with Parkinson disease, and result from activations that mainly contribute on the classification task. For doing so, a convolutional architecture is trained from a set of walking videos, recorded from parkinsonian and control subjects. Then, a prediction of disease is obtained according to motion patterns computed by convolutional learned scheme. Salience motion patterns are obtained by retro-propagating the output softmax network prediction over the video space. From a total of 22 patients, and a total of 176 video sequences, the proposed approach achieved an average accuracy score of 88%. Interestingly enough, the recovered salience maps focus the attention on relevant parkinsonian biomarkers such as the head motion and trunk posture, that namely is excluded on classical gait analysis.Clinical relevance- Salient spatio-temporal regions can potentially support and complement the diagnosis and the following of Parkinson's disease. Also, such complex relationships could potentially evolve in further understanding of this pathology.

Low-Rank and Sparse Recovery of Human Gait Data

Due to occlusion or detached markers, information can often be lost while capturing human motion with optical tracking systems. Based on three natural properties of human gait movement, this study presents two different approaches to recover corrupted motion data. These properties are used to define a reconstruction model combining low-rank matrix completion of the measured data with a group-sparsity prior on the marker trajectories mapped in the frequency domain. Unlike most existing approaches, the proposed methodology is fully unsupervised and does not need training data or kinematic information of the user. We evaluated our methods on four different gait datasets with various gap lengths and compared their performance with a state-of-the-art approach using principal component analysis (PCA). Our results showed recovering missing data more precisely, with a reduction of at least 2 mm in mean reconstruction error compared to the literature method. When a small number of marker trajectories is available, our findings showed a reduction of more than 14 mm for the mean reconstruction error compared to the literature approach.

Assessment of Parkinsonian gait in older adults with dementia via human pose tracking in video data

Background

Parkinsonism is common in people with dementia, and is associated with neurodegenerative and vascular changes in the brain, or with exposure to antipsychotic or other dopamine antagonist medications. The detection of parkinsonian changes to gait may provide an opportunity to intervene and address reversible causes. In this study, we investigate the use of a vision-based system as an unobtrusive means to assess severity of parkinsonism in gait.

Methods

Videos of walking bouts of natural gait were collected in a specialized dementia unit using a Microsoft Kinect sensor and onboard color camera, and were processed to extract sixteen 3D and eight 2D gait features. Univariate regression to gait quality, as rated on the Unified Parkinson’s Disease Rating Scale (UPDRS) and Simpson-Angus Scale (SAS), was used to identify gait features significantly correlated to these clinical scores for inclusion in multivariate models. Multivariate ordinal logistic regression was subsequently performed and the relative contribution of each gait feature for regression to UPDRS-gait and SAS-gait scores was assessed.

Results

Four hundred one walking bouts from 14 older adults with dementia were included in the analysis. Multivariate ordinal logistic regression models incorporating selected 2D or 3D gait features attained similar accuracies: the UPDRS-gait regression models achieved accuracies of 61.4 and 62.1% for 2D and 3D features, respectively. Similarly, the SAS-gait models achieved accuracies of 47.4 and 48.5% with 2D or 3D gait features, respectively.

Conclusions

Gait features extracted from both 2D and 3D videos are correlated to UPDRS-gait and SAS-gait scores of parkinsonism severity in gait. Vision-based systems have the potential to be used as tools for longitudinal monitoring of parkinsonism in residential settings.

Bringing spatiotemporal gait analysis into clinical practice: Instrument validation and pilot study of a commercial sensorized carpet

BACKGROUND AND OBJECTIVE

We illustrate a low-cost platform easing the estimation of spatio-temporal parameters (GA-STP) ready for large-scale deployment in fall prevention.

METHODS

We used a commercial sensorized carpet with a limited cost and a very coarse resolution. An instrument validation test was accomplished: the Wilcoxon test for paired samples and the correlation test with Spearman method were used to compare the values computed by the platform with reference ones. Hierarchical clustering using Ward's method and ROC curves have been used to assess the performance in a pilot study enrolling patients.

RESULTS

Validation shows no significant difference between computed and reference values of gait speed (ρ-value:0.99; p-value:2.2E-16), step number (ρ-value:0.91; p-value:5.8E-16) and stride-length (ρ-value:0.92; p-value:7.5E-9). The clinical pilot study confirms that the platform may also be used to track the improvements occurring during a rehabilitation program.

CONCLUSIONS

We believe that the use of a commercial carpet makes the solution proposed ready to be deployed on a large scale for effectively bringing GA into the clinical practice.

People Walking Classification Using Automotive Radar

Automotive radars are able to guarantee high performances at the expenses of a relatively low cost, and recently their application has been extended to several fields in addition to the original one. In this paper we consider the use of this kind of radars to discriminate different types of people’s movements in a real context. To this end, we exploit two different maps obtained from radar, that is, a spectrogram and a range-Doppler map. Through the application of dimensionality reduction methods, such as principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) algorithm, and the use of machine learning techniques we prove that is possible to classify with a very good precision people’s way of walking even employing commercial devices specifically designed for other purposes.