RESUMEN

The accurate identification of dynamic change of limb length discrepancy (LLD) in non-clinical settings is of great significance for monitoring gait function change in people's everyday lives. How to search for advanced techniques to measure LLD changes in non-clinical settings has always been a challenging endeavor in recent related research. In this study, we have proposed a novel approach to accurately measure the dynamic change of LLD outdoors by using deep learning and wearable sensors. The basic idea is that the measurement of dynamic change of LLD was considered as a multiple gait classification task based on LLD change that is clearly associated with its gait pattern. A hybrid deep learning model of convolutional neural network and long short-term memory (CNN-LSTM) was developed to precisely classify LLD gait patterns by discovering the most representative spatial-temporal LLD dynamic change features. Twenty-three healthy subjects were recruited to simulate four levels of LLD by wearing a shoe lift with different heights. The Delsys TrignoTM system was implemented to simultaneously acquire gait data from six sensors positioned on the hip, knee and ankle joint of two lower limbs respectively. The experimental results showed that the developed CNN-LSTM model could reach a higher accuracy of 93.24% and F1-score of 93.48% to classify four different LLD gait patterns when compared with CNN, LSTM, and CNN-gated recurrent unit(CNN-GRU), and gain better recall and precision (more than 92%) to detect each LLD gait pattern accurately. Our model could achieve excellent learning ability to discover the most representative LLD dynamic change features for classifying LLD gait patterns accurately. Our technical solution would help not only to accurately measure LLD dynamic change in non-clinical settings, but also to potentially find out lower limb joints with more abnormal compensatory change caused by LLD.

Asunto(s)

RESUMEN

Parkinson's disease (PD) is one of the cognitive degenerative disorders of the central nervous system that affects the motor system. Gait dysfunction represents the pathology of motor symptom while gait analysis provides clinicians with subclinical information reflecting subtle differences between PD patients and healthy controls (HCs). Currently neurologists usually assess several clinical manifestations of the PD patients and rate the severity level according to some established criteria. This is highly dependent on clinician's expertise which is subjective and ineffective. In the present study we address these issues by proposing a hybrid signal processing and machine learning based gait classification system for gait anomaly detection and severity rating of PD patients. Time series of vertical ground reaction force (VGRF) data are utilized to represent discriminant gait information. First, phase space of the VGRF is reconstructed, in which the properties associated with the nonlinear gait system dynamics are preserved. Then Shannon energy is used to extract the characteristic envelope of the phase space signal. Third, Shannon energy envelope is decomposed into high and low resonance components using dual Q-factor signal decomposition derived from tunable Q-factor wavelet transform. Note that the high Q-factor component consists largely of sustained oscillatory behavior, while the low Q-factor component consists largely of transients and oscillations that are not sustained. Fourth, variational mode decomposition is employed to decompose high and low resonance components into different intrinsic modes and provide representative features. Finally features are fed to five different types of machine learning based classifiers for the anomaly detection and severity rating of PD patients based on Hohen and Yahr (HY) scale. The effectiveness of this strategy is verified using a Physionet gait database consisting of 93 idiopathic PD patients and 73 age-matched asymptomatic HCs. When evaluated with 10-fold cross-validation method for early PD detection and severity rating, the highest classification accuracy is reported to be 98.20% and 96.69%, respectively, by using the support vector machine classifier. Compared with other state-of-the-art methods, the results demonstrate superior performance and support the validity of the proposed method.

RESUMEN

Cueing and feedback training can be effective in maintaining or improving gait in individuals with Parkinson's disease. We previously designed a rehabilitation assist device that can detect and classify a user's gait at only the swing phase of the gait cycle, for the ease of data processing. In this study, we analyzed the impact of various factors in a gait detection algorithm on the gait detection and classification rate (GDCR). We collected acceleration and angular velocity data from 25 participants (1 male and 24 females with an average age of 62 ± 6 years) using our device and analyzed the data using statistical methods. Based on these results, we developed an adaptive GDCR control algorithm using several equations and functions. We tested the algorithm under various virtual exercise scenarios using two control methods, based on acceleration and angular velocity, and found that the acceleration threshold was more effective in controlling the GDCR (average Spearman correlation -0.9996, p < 0.001) than the gyroscopic threshold. Our adaptive control algorithm was more effective in maintaining the target GDCR than the other algorithms (p < 0.001) with an average error of 0.10, while other tested methods showed average errors of 0.16 and 0.28. This algorithm has good scalability and can be adapted for future gait detection and classification applications.

Asunto(s)

RESUMEN

Gait recognition and classification technology is one of the essential technologies for detecting neurodegenerative dysfunction. This paper presents a gait classification model based on a convolutional neural network (CNN) with an efficient channel attention (ECA) module for gait detection applications using surface electromyographic (sEMG) signals. First, the sEMG sensor was used to collect the experimental sample data, and various gaits of different persons were collected to construct the sEMG signal data sets of different gaits. The CNN is used to extract the features of the one-dimensional input sEMG signal to obtain the feature vector, which is input into the ECA module to realize cross-channel interaction. Then, the next part of the convolutional layer is input to learn the signal features further. Finally, the model is output and tested to obtain the results. Comparative experiments show that the accuracy of the ECA-CNN network model can reach 97.75%.

Asunto(s)

RESUMEN

Wearable sensors allow for the objective analysis of gait and motion both in and outside the clinical setting. However, it remains a challenge to apply such systems to highly diverse patient populations, including individuals with lower-limb amputations (LLA) that present with unique gait deviations and rehabilitation goals. This paper presents the development of a novel method using continuous gyroscope data from a single inertial sensor for person-specific classification of gait changes from a physiotherapist-led gait training session. Gyroscope data at the thigh were collected using a wearable gait analysis system for five LLA before, during, and after completing a gait training session. Data from able-bodied participants receiving no intervention were also collected. Models using dynamic time warping (DTW) and Euclidean distance in combination with the nearest neighbor classifier were applied to the gyroscope data to classify the pre- and post-training gait. The model achieved an accuracy of 98.65% ± 0.69 (Euclidean) and 98.98% ± 0.83 (DTW) on pre-training and 95.45% ± 6.20 (Euclidean) and 94.18% ± 5.77 (DTW) on post-training data across the participants whose gait changed significantly during their session. This study provides preliminary evidence that continuous angular velocity data from a single gyroscope could be used to assess changes in amputee gait. This supports future research and the development of wearable gait analysis and feedback systems that are adaptable to a broad range of mobility impairments.

Asunto(s)

RESUMEN

Automated gait classification has traditionally been studied using horse-mounted sensors. However, smartphone-based sensors are more accessible, but the performance of gait classification models using data from such sensors has not been widely known or accessible. In this study, we performed horse gait classification using deep learning models and data from mobile phone sensors located in the rider's pocket. We gathered data from 17 horses and 14 riders. The data were gathered simultaneously from movement sensors in a mobile phone located in the rider's pocket and a gait classification system based on four wearable sensors attached to the horse's limbs. With this efficient approach to acquire labelled data, we trained a Bi-LSTM model for gait classification. The only input to the model was a 50 Hz signal from the phone's accelerometer and gyroscope that was rotated to the horse's frame of reference. We demonstrate that sensor data from mobile phones can be used to classify the five gaits of the Icelandic horse with up to 94.4% accuracy. The result suggests that horse riding activities can be studied at a large scale using mobile phones to gather data on gaits. While our study showed that mobile phone sensors could be effective for gait classification, there are still some limitations that need to be addressed in future research. For example, further studies could explore the effects of different riding styles or equipment on gait classification accuracy or investigate ways to minimize the influence of factors such as phone placement. By addressing these questions, we can continue to improve our understanding of horse gait and its role in horse riding activities.

RESUMEN

BACKGROUND: Ankle-foot orthoses (AFOs) are frequently prescribed in children with cerebral palsy (CP) to improve their gait. Due to the heterogeneous nature of CP and contradictions among previous studies, it is important to evaluate the AFO-specific effects, as well as explore their effects on different gait patterns. RESEARCH QUESTIONS: a) What are the prevalence and specific features of AFOs in children with CP? b) How do AFOs affect gait pathology in children with CP? c) What are the pattern-specific effects of AFOs in children with CP? METHODS: A group of 170 patients with CP underwent a three-dimensional gait analysis with and without AFOs (either carbon fiber, rigid, flexible or hinged). The gait profile score, the gait variable scores of the hip, knee and ankle joints, non-dimensional step length and walking speed were used as outcome measures. The AFO-specific effects on the kinematic and kinetic waveforms were investigated using statistical non-parametric mapping (SnPM). Effects were considered relevant when the minimal clinically important difference (MCID) or the standard errors of measurement, for the parameters or the waveforms respectively, were exceeded. RESULTS: Rigid AFOs were prescribed for more than 80 % of the children. Significant beneficial effects were observed for non-dimensional step length and walking speed. Most changes in gait indices were not considered relevant. The SnPM-analyses on the total group and specific gait patterns revealed that walking with AFOs improved the kinematic and kinetic waveforms. These effects were relevant, and were most obvious for crouch, apparent equinus and the total group. SIGNIFICANCE: The use of AFOs improves gait, whether we inspect a total -and thus heterogeneous- group or focus on specific gait patterns. However, focussing on specific parameters (i.e. general gait indices) does not provide a full picture of the AFO-effects.

Asunto(s)

RESUMEN

Classification of gait disorders in cerebral palsy (CP) remains challenging. The Winters, Gage, and Hicks (WGH) is a commonly used classification system for unilateral CP regarding the gait patterns (lower limb kinematics) solely in the sagittal plane. Due to the high number of unclassified patients, this classification system might fail to depict all gait disorders accurately. As the information on trunk/pelvic movements, frontal and transverse planes, and kinetics are disregarded in WGH, 3D instrumented gait analysis (IGA) for further characterization is necessary. The objective of this study was a detailed analysis of patients with unilateral CP using IGA taking all planes/degrees of freedom into account including pelvic and trunk movements. A total of 89 individuals with unilateral CP matched the inclusion criteria and were classified by WGH. Subtype-specific differences were analyzed. The most remarkable findings, in addition to the established WGH subtype-specific deviations, were pelvic obliquity and pelvic retraction in all WGH types. Furthermore, the unclassified individuals showed altered hip rotation moments and pelvic retraction almost throughout the whole gait cycle. Transversal malalignment and proximal involvement are relevant in all individuals with unilateral CP. Further studies should focus on WGH type-specific rotational malalignment assessment (static vs. dynamic, femoral vs. tibial) including therapeutic effects and potential subtype-specific compensation mechanisms and/or tertiary deviations of the sound limb.

RESUMEN

Walking is an exercise that uses muscles and joints of the human body and is essential for understanding body condition. Analyzing body movements through gait has been studied and applied in human identification, sports science, and medicine. This study investigated a spatiotemporal graph convolutional network model (ST-GCN), using attention techniques applied to pathological-gait classification from the collected skeletal information. The focus of this study was twofold. The first objective was extracting spatiotemporal features from skeletal information presented by joint connections and applying these features to graph convolutional neural networks. The second objective was developing an attention mechanism for spatiotemporal graph convolutional neural networks, to focus on important joints in the current gait. This model establishes a pathological-gait-classification system for diagnosing sarcopenia. Experiments on three datasets, namely NTU RGB+D, pathological gait of GIST, and multimodal-gait symmetry (MMGS), validate that the proposed model outperforms existing models in gait classification.

Asunto(s)

RESUMEN

The majority of human gait modeling is based on hip, foot or thigh acceleration. The regeneration accuracy of these modeling approaches is not very high. This paper presents a harmonic approach to modeling human gait during level walking based on gyroscopic signals for a single thigh-mounted Inertial Measurement Unit (IMU) and the flexion-extension derived from a single thigh-mounted IMU. The thigh angle can be modeled with five significant harmonics, with a regeneration accuracy of over 0.999 correlation and less than 0.5° RMSE per stride cycle. Comparable regeneration accuracies can be achieved with nine significant harmonics for the gyro signal. The fundamental frequency of the harmonic model can be estimated using the stride time, with an error level of 0.0479% (±0.0029%). Six commonly observed stride patterns, and harmonic models of thigh angle and gyro signal for those stride patterns, are presented in this paper. These harmonic models can be used to predict or classify the strides of walking trials, and the results are presented herein. Harmonic models may also be used for activity recognition. It has shown that human gait in level walking can be modeled with a harmonic model of thigh angle or gyro signal, using a single thigh-mounted IMU, to higher accuracies than existing techniques.

Asunto(s)

RESUMEN

Parkinson's disease (PD) is a common neurodegenerative disease, one of the symptoms of which is a gait disorder, which decreases gait speed and cadence. Recently, augmented feedback training has been considered to achieve effective physical rehabilitation. Therefore, we have devised a numerical modeling process and algorithm for gait detection and classification (GDC) that actively utilizes augmented feedback training. The numerical model converted each joint angle into a magnitude of acceleration (MoA) and a Z-axis angular velocity (ZAV) parameter. Subsequently, we confirmed the validity of both the GDC numerical modeling and algorithm. As a result, a higher gait detection and classification rate (GDCR) could be observed at a higher gait speed and lower acceleration threshold (AT) and gyroscopic threshold (GT). However, the pattern of the GDCR was ambiguous if the patient was affected by a gait disorder compared to a normal user. To utilize the relationships between the GDCR, AT, GT, and gait speed, we controlled the GDCR by using AT and GT as inputs, which we found to be a reasonable methodology. Moreover, the GDC algorithm could distinguish between normal people and people who suffered from gait disorders. Consequently, the GDC method could be used for rehabilitation and gait evaluation.

Asunto(s)

RESUMEN

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.

RESUMEN

BACKGROUND: Pathological gaits of children may lead to terrible diseases, such as osteoarthritis or scoliosis. By monitoring the gait pattern of a child, proper therapeutic measures can be recommended to avoid the terrible consequence. However, low-cost systems for pathological gait recognition of children automatically have not been on market yet. Our goal was to design a low-cost gait-recognition system for children with only pressure information. METHODS: In this study, we design a pathological gait-recognition system (PGRS) with an 8 × 8 pressure-sensor array. An intelligent gait-recognition method (IGRM) based on machine learning and pure plantar pressure information is also proposed in static and dynamic sections to realize high accuracy and good real-time performance. To verifying the recognition effect, a total of 17 children were recruited in the experiments wearing PGRS to recognize three pathological gaits (toe-in, toe-out, and flat) and normal gait. Children are asked to walk naturally on level ground in the dynamic section or stand naturally and comfortably in the static section. The evaluation of the performance of recognition results included stratified tenfold cross-validation with recall, precision, and a time cost as metrics. RESULTS: The experimental results show that all of the IGRMs have been identified with a practically applicable degree of average accuracy either in the dynamic or static section. Experimental results indicate that the IGRM has 92.41% and 97.79% intra-subject recognition accuracy, and 85.78% and 78.81% inter-subject recognition accuracy, respectively, in the static and dynamic sections. And we find methods in the static section have less recognition accuracy due to the unnatural gesture of children when standing. CONCLUSIONS: In this study, a low-cost PGRS has been verified and realize feasibility, highly average precision, and good real-time performance of gait recognition. The experimental results reveal the potential for the computer supervision of non-pathological and pathological gaits in the plantar-pressure patterns of children and for providing feedback in the application of gait-abnormality rectification.

Asunto(s)

RESUMEN

To develop a daily monitoring system for early detection of fall risk of elderly people during walking, this study presents a highly accurate micro-Doppler radar (MDR)-based gait classification method for the young and elderly adults. Our method utilizes a time-series of velocity corresponding to leg motion during walking extracted from the MDR spectrogram (time-velocity distribution) in an experimental study involving 300 participants. The extracted time-series was inputted to a long short-term memory recurrent neural network to classify the gaits of young and elderly participant groups. We achieved a classification accuracy of 94.9%, which is significantly higher than that of a previously presented velocity-parameter-based classification method.

Asunto(s)

RESUMEN

Objectively assessing horse movement symmetry as an adjunctive to the routine lameness evaluation is on the rise with several commercially available systems on the market. Prerequisites for quantifying such symmetries include knowledge of the gait and gait events, such as hoof to ground contact patterns over consecutive strides. Extracting this information in a robust and reliable way is essential to accurately calculate many kinematic variables commonly used in the field. In this study, optical motion capture was used to measure 222 horses of various breeds, performing a total of 82 664 steps in walk and trot under different conditions, including soft, hard and treadmill surfaces as well as moving on a straight line and in circles. Features were extracted from the pelvis and withers vertical movement and from pelvic rotations. The features were then used in a quadratic discriminant analysis to classify gait and to detect if the left/right hind limb was in contact with the ground on a step by step basis. The predictive model achieved 99.98% accuracy on the test data of 120 horses and 21 845 steps, all measured under clinical conditions. One of the benefits of the proposed method is that it does not require the use of limb kinematics making it especially suited for clinical applications where ease of use and minimal error intervention are a priority. Future research could investigate the extension of this functionality to classify other gaits and validating the use of the algorithm for inertial measurement units.

Asunto(s)

RESUMEN

BACKGROUND: Crouch or flexed-knee gait is one of the most common pathological gait patterns in cerebral palsy (CP). Differences exist in definitions used; the degree of knee flexion, inclusion of hip or ankle position, and timing in the gait cycle. This ambiguity may be responsible for variations in prevalence rates and difficulty comparing data across studies. RESEARCH QUESTION: What are the kinematic parameters used to define crouch or flexed-knee gait in CP gait? A secondary aim was to examine the quality of data reporting, focusing on the sample characteristics, inclusion/exclusion criteria and the choice of limb included for analysis. METHODS: Articles included in this review reported on a specified cohort of adults or children with crouch or flexed-knee gait assessed with 3-dimensional gait analysis. A customised data extraction and quality assessment table was designed specific to the research question. RESULTS: The majority (75 %) of included studies used the term crouch gait. Where the pattern was defined, 80 % of crouch papers and 94 % of flexed-knee gait papers based this solely on knee position. Kinematic parameters were clearly defined when they provided objective values of knee flexion, supported this with rationale and provided a reference point in the gait cycle. Only 22 % of crouch papers and 19 % of flexed-knee gait papers provided this information. The majority of studies (67 % crouch; 90 % flexed-knee) specified which limb(s) were included for analysis with the majority including both limbs. Objective values of knee flexion ranged from 8 o to 30 o. SIGNIFICANCE: This review highlights that crouch and flexed knee are synonymous and ambiguity exists in the kinematic definition making it difficult to make compare data amongst study cohorts. Future research should provide detailed definitions including the threshold value of knee flexion, how it was derived, the timing in the gait cycle and the limb(s) included in analysis.

Asunto(s)

RESUMEN

Activity recognition is one of the most active areas of research in ubiquitous computing. In particular, gait activity recognition is useful to identify various risk factors in people's health that are directly related to their physical activity. One of the issues in activity recognition, and gait in particular, is that often datasets are unbalanced (i.e., the distribution of classes is not uniform), and due to this disparity, the models tend to categorize into the class with more instances. In the present study, two methods for classifying gait activities using accelerometer and gyroscope data from a large-scale public dataset were evaluated and compared. The gait activities in this dataset are: (i) going down an incline, (ii) going up an incline, (iii) walking on level ground, (iv) going down stairs, and (v) going up stairs. The proposed methods are based on conventional (shallow) and deep learning techniques. In addition, data were evaluated from three data treatments: original unbalanced data, sampled data, and augmented data. The latter was based on the generation of synthetic data according to segmented gait data. The best results were obtained with classifiers built with augmented data, with F-measure results of 0.812 (σ = 0.078) for the shallow learning approach, and of 0.927 (σ = 0.033) for the deep learning approach. In addition, the data augmentation strategy proposed to deal with the unbalanced problem resulted in increased classification performance using both techniques.

Asunto(s)

RESUMEN

Human movements are characterized by highly non-linear and multi-dimensional interactions within the motor system. Therefore, the future of human movement analysis requires procedures that enhance the classification of movement patterns into relevant groups and support practitioners in their decisions. In this regard, the use of data-driven techniques seems to be particularly suitable to generate classification models. Recently, an increasing emphasis on machine-learning applications has led to a significant contribution, e.g., in increasing the classification performance. In order to ensure the generalizability of the machine-learning models, different data preprocessing steps are usually carried out to process the measured raw data before the classifications. In the past, various methods have been used for each of these preprocessing steps. However, there are hardly any standard procedures or rather systematic comparisons of these different methods and their impact on the classification performance. Therefore, the aim of this analysis is to compare different combinations of commonly applied data preprocessing steps and test their effects on the classification performance of gait patterns. A publicly available dataset on intra-individual changes of gait patterns was used for this analysis. Forty-two healthy participants performed 6 sessions of 15 gait trials for 1 day. For each trial, two force plates recorded the three-dimensional ground reaction forces (GRFs). The data was preprocessed with the following steps: GRF filtering, time derivative, time normalization, data reduction, weight normalization and data scaling. Subsequently, combinations of all methods from each preprocessing step were analyzed by comparing their prediction performance in a six-session classification using Support Vector Machines, Random Forest Classifiers, Multi-Layer Perceptrons, and Convolutional Neural Networks. The results indicate that filtering GRF data and a supervised data reduction (e.g., using Principal Components Analysis) lead to increased prediction performance of the machine-learning classifiers. Interestingly, the weight normalization and the number of data points (above a certain minimum) in the time normalization does not have a substantial effect. In conclusion, the present results provide first domain-specific recommendations for commonly applied data preprocessing methods and might help to build more comparable and more robust classification models based on machine learning that are suitable for a practical application.

RESUMEN

BACKGROUND: Quantitative gait analysis produces a vast amount of data, which can be difficult to analyze. Automated gait classification based on machine learning techniques bear the potential to support clinicians in comprehending these complex data. Even though these techniques are already frequently used in the scientific community, there is no clear consensus on how the data need to be preprocessed and arranged to assure optimal classification accuracy outcomes. RESEARCH QUESTION: Is there an optimal data aggregation and preprocessing workflow to optimize classification accuracy outcomes? METHODS: Based on our previous work on automated classification of ground reaction force (GRF) data, a sequential setup was followed: firstly, several aggregation methods - early fusion and late fusion - were compared, and secondly, based on the best aggregation method identified, the expressiveness of different combinations of signal representations was investigated. The employed dataset included data from 910 subjects, with four gait disorder classes and one healthy control group. The machine learning pipeline comprised principle component analysis (PCA), z-standardization and a support vector machine (SVM). RESULTS: The late fusion aggregation, i.e., utilizing majority voting on the classifier's predictions, performed best. In addition, the use of derived signal representations (relative changes and signal differences) seems to be advantageous as well. SIGNIFICANCE: Our results indicate that great caution is needed when data preprocessing and aggregation methods are selected, as these can have an impact on classification accuracies. These results shall serve future studies as a guideline for the choice of data aggregation and preprocessing techniques to be employed.

Asunto(s)

RESUMEN

Human gait recognition is one of the most promising biometric technologies, especially for unobtrusive video surveillance and human identification from a distance. Aiming at improving recognition rate, in this paper we study gait recognition using deep learning and propose a novel method based on convolutional Long Short-Term Memory (Conv-LSTM). First, we present a variation of Gait Energy Images, i.e. frame-by-frame GEI (ff-GEI), to expand the volume of available Gait Energy Images (GEI) data and relax the constraints of gait cycle segmentation required by existing gait recognition methods. Second, we demonstrate the effectiveness of ff-GEI by analyzing the cross-covariance of one person's gait data. Then, making use of the temporality of our human gait, we design a novel gait recognition model using Conv-LSTM. Finally, the proposed method is evaluated extensively based on the CASIA Dataset B for cross-view gait recognition, furthermore the OU-ISIR Large Population Dataset is employed to verify its generalization ability. Our experimental results show that the proposed method outperforms other algorithms based on these two datasets. The results indicate that the proposed ff-GEI model using Conv-LSTM, coupled with the new gait representation, can effectively solve the problems related to cross-view gait recognition.

Asunto(s)