Computer Vision and Abnormal Patient Gait: A Comparison of Methods

Jasmin Hundal1, Benson A. Babu2, *
1 Department of Internal Medicine, University of Connecticut, Hartford, CT, USA
2 Department of Internal Medicine, Hospital Medicine, Plainview Medicine Centre, Northwell Health, Plainview, NY, USA

© 2020 Hundal and Babu.

open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: ( This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

* Address correspondence to this author at the Department of Internal Medicine, Hospital Medicine, Plainview Medicine Centre, Northwell Health, Plainview, NY, USA; Tel: 516-491-3713; E-mail:


Abnormal gait, falls and its associated complications have high morbidity and mortality. Computer vision detects, predicts gait abnormalities, assesses fall risk, and serves as a clinical decision support tool for physicians. This paper performs a systematic review of computer vision, machine learning techniques to analyse abnormal gait. This literature outlines the use of different machine learning and poses estimation algorithms in gait analysis that includes partial affinity fields, pictorial structures model, hierarchical models, sequential-prediction-framework-based approaches, convolutional pose machines, gait energy image, 2-Directional 2-dimensional principles component analysis ((2D) 2PCA) and 2G (2D) 2PCA) Enhanced Gait Energy Image (EGEI), SVM, ANN, K-Star, Random Forest, KNN, to perform the image classification of the features extracted inpatient gait abnormalities.

Keywords: Gait analysis, Computer vision, Machine learning, Gait energy image, Gait abnormalities, Low-cost sensors.


Abnormalities with patient gait fall and associated complications have high morbidity and mortality [1]. Falls, its high costs to the healthcare system is largely preventable. Preventable complications include hip fractures, medical deconditioning, myocardial infarction, and pulmonary emboli. These complications are devastating in the elderly population [2]. Advances in algorithms and low-cost sensors in the healthcare market prevent falls and complications [3].

Computer vision assesses fall risk, provides physicians with an opportunity to outline an early treatment plan, thus limiting any morbidity and mortality. Computer vision is also used to assess gait in disorders like dementia, depression, intellectual disability, musculoskeletal disorders, and stroke [4-7]. These conditions are managed in the fields of neurology, physical medicine rehabilitation, rheumatology, and orthopae-dics [8]. Computer vision assesses postural abnormalities; its parameters’ provide strength and an endurance plan for patients during their treatment course [9].

Clinicians' provide a subjective assessment of gait. As a result, subjectivity impacts diagnosis and treatment decisions; thus, patient outcomes [10]. Computer vision strengthens physicians' decisions, provides an in-depth quantitative analy-

sis of one's stride and its potential for recovery [11]. Thus, gait analysis is essential; numerous bodies of research explore this topic at length [12].

This article performs a complete systematic review of computer vision, its machine learning methods in gait assessment. This article focuses on:

  • What are the machine learning models used in estimating gait?
  • How can computer vision assist with gait assessment?

1.1. Gait Analysis

Gait analysis uses several approaches, including medical imaging technique, acoustic tracking system, magnetic system, goniometric measurement system, electromyography, foot planter presser sensor, force shoes, force plate mechanism, inertial system, optical system and utilities portable devices.

1.2. Computer Vision

Human vision refers to gazing at the world to understand it. Computer vision is similar as it uses a machine, a camera, to obtain information. We use the following features for classifying a computer vision’s applications [13]:

  • Gauging: It relates to tolerance checking and dimensional characteristic measurement.
  • Sorting: It recognizes and identifies parts.
  • Inspection: It detects, identifies, and classifies parts.

Within the past decade, they have conducted extensive research on video-based human motion capture. Various techniques in machine learning and computer vision are proposed for pose estimation and 3D human motion tracking [14]. A video-based technique is used to carry out joint kinematics, while gait is ongoing, as developed by the work of Corazza et al. [15].

1.3. Machine Learning

As deep learning approaches emerge, DNN-based techniques are the standard in vision tasks such as human motion tracking, pose estimation [16], human activity recognition [17], and face recognition [18]. Deep CNN architecture consists of layers between both input and output; model complex non-linear relationships in data. DNN models for 3D human pose estimation focus on a single view, with a complex background setting [14, 19]. Machine learning models using Logistic Regression [20], Artificial Neural Networks (ANN) [21], K-Star [22], Random Forest [23], K-nearest neighbors (KNN) [24] and Support Vector Machines (SVM) [25] can identify and classify patterns of gait, thus provide valuable insight into medical conditions [16].

1.3.1. Post Estimation

An individual’s trunk, joints, and other body parts are detected using the human pose estimation method [26]. The pose estimation technique detects body parts using images from a video or an image detector; it describes the anatomic details [27]. These images are processed into an algorithm. Key skeletal points serve as coordinates, generated by using the pose estimation method. Human pose estimation is important; it predicts human posture, behaviour by gait recognition, character tracking, action, and behaviour recognition [28]. Similarly, the method: Part affinity field is another ground-breaking computer vision technique, able to detect multiple 2D people poses in the wild with high accuracy [29].

Pictorial structures mode [30-32] expresses spatial relationships within body parts labelled as kinematic-priors-based, tree-structured graphic models. This model couples connected limbs, thus make up the classic articulated pose estimation technique. These methods make mistakes such as counting image data twice; this happens because connections between variables of the tree-structured model did not capture correctly. These errors occur on high-quality limb images used in the pictorial structure model [33].

Hierarchical models [34, 35] signify how the parts relate at various sizes and scales in a hierarchical tree structure. Based on assumptions, the image structure easily detects, discri-minates the location of small hard-to-locate parts within the entire limb system.

Interactions introduce loops and augment the tree structure with edges; it captures: long-range, occlusion, symmetry, and incorporates into non-tree models [36, 37]. The inference is required in methods for learning and test time. As a result, spatial relationships’ provide fast, efficient inference, with a parametric form; but, a trade-off with other models occurs.

Sequential-prediction-framework-based approaches [38] use complicated relationships between variables: it learns from an implicit spatial model, trains an inference procedure to achieve a performance output [39, 40].

Recently, the articulated pose estimation method [41, 42] combined with a convolutional architecture gained popularity in the computer vision community. This method [43] uses convolutional architecture to carry out a regression of the Cartesian coordinates [44]. It regresses an image to a confidence map and opts in for graphical models using spatial probability priors' heuristic initialization or energy functions designed by hand. This removes outliers on the regressed confidence maps; it also uses a dedicated network model for a precise refinement [45, 46]. This input to the regressed confidence maps combined with convolutional networks does not require hand-designed priors, has great receptive domains for learning, and attains a high level of performance within the entire precision region. Furthermore, it should not be carefully initialized and needs a dedicated precision refinement. A network module with a large receptive field is used in the work for capturing implicit spatial models [47], considered joint training’s advantages; the model we reviewed is trained globally because of convolutions differentiable attributes [42].

A deep network with the features of being able to use error feedback for training is seen in the work of [48]. It also uses Cartesian representation, as seen in that it is incapable of preserving spatial improbability, and that reduces the high precision regime’s accuracy [49].

The task of articulated pose estimation using Convolu-tional Pose Machines (CPMs) has been carried out. CPM inherit pose machine architecture’s benefits [38], integrating learning and inference tightly, the learning of long-range dependencies between multi-part cues and image implicitly, and a modular sequential design. It combines these with the benefits convolutional architecture provides. CPMs also include advantages such as the capability of handling large training datasets efficiently, a differentiable architecture that makes joint training with backpropagation possible, and the ability to learn spatial and image context's feature repre-sentations directly from data. Series of convolutional networks, 2D maps for each part's location make up CPMs.

CPMs [50] are robust and have high accuracy in the detection of human pose estimations’ data-sets, such as the Leeds Sports Pose (LSP) data-set [51], Human Pose data-set [52], and Max-Planck-Institute Informatics (MPII). The time required to train CPMs are extensive, and its detection speed is low. This makes it difficult to apply real-time tasks. Based on human pose estimation's standard datasets, excellent detection outputs are found in the Stacked Hourglass [53] of a similar duration. The new modes using the enhanced Stacked Hourglass include the 2017 models such as Learning Feature [54], Self-Adversarial Training [55], and multi-context [56], and the 2018 excellent models’ further improved accuracy. Certain metrics contained in these models, increase the time required for training, thereby limiting model use. To date, the model does not have a satisfactory accuracy.

The ability to extract the low-level feature is enhanced, using the more convoluted network structures, and deeper network layers of the enhanced CPM model [57]; and afterward, apply a system to fine-tune it. The enhanced CPM is proven to include an excellent image detection effect and high image classification accuracy, and a good human pose estimation model for designing a new network and apply a system of fine-tuning to increase the human pose estimation’s efficiency.

1.3.2. Gender Recognition

Gait Energy Image (GEI) is a combination of gait with a new spatiotemporal method for force representation to mark human walking behaviour for individual recognition [58]. The findings show the efficiency of combining gait and GEI approach for individual recognition, and the competitiveness of its performance [58, 59]. The GEI approach is used for studying individual recognition. The researchers used various tech-niques, methods to present the GEI approach as biased attributed in their survey. It is clear from the findings of their research that the system’s performance in real-time improved; hence, its application in real-word is possible [60]. It further used automated approaches to combine psychological methods for improving accuracy quality to classify human gait-based genders. According to their research, compared to other parts of the body, the major body parts for the gender recognition process include the chest, back, hair, and head. Even though the application process contains several impediments because of the differences in how humans appear, they include change of shoes and clothes, or when they lift objects, the gait classification is possible in a controlled environment.

The classification of human behaviour using 2-Directional 2-dimensional principles component analysis ((2D) 2PCA) and 2G (2D) 2PCA) Enhanced Gait Energy Image (EGEI) is proposed in the work [61]. The outcomes of the experiment revealed the simplicity of the algorithm and its capacity for realizing a higher classification accuracy within a short period. The system uses gait classification based on the silhouette, recommends books to visitors according to their age or gender, and in real-time [62]. The Support Vector Machine (SVM) has 77.5% accuracy in classification [63]; it combines the Denoised Energy Image (DEI) and GEI approach in pre-processing to present gender recognition’s initial design, outcomes, the training, and extraction of feature from the walking movements experiment. This method may provide high real-time accuracy.

The method of integrating information from the multi-view gait at the feature level is proposed [64], and it increases the effectiveness of the performance for the gender classification based on multi-view gait. Gait for human recognition was conducted [65]. Gait image’s features that are founded on information theory sets are referred to as image feature information gait. Gait information features are information set theory-based gait image features that are described by this research team. The concept of the information set was applied on the frames in a gait cycle, and two elements referred to as Gait Information Image with Sigmoid Feature (GIISF) extracted and Gait Information Image with Energy Feature (GII-EF) to derive the proposed Gait Information Image (GII). The identification of the gait was made using Nearest Neighbour (NN) for the classification. The robust feature-level fusion of directional vectors such as forward and backward diagonal, vertical, and horizontal vectors are used by this research team [66] to study gender recognition. First, they construct for each image sequence: 1) Gait Energy Image (GEI), followed by 2) Gradient Gait Energy Image (GGEI), which is achieved using neighbourhood gradient computation [67]. After that, differences in all the four directions were utilized as discriminative gait features. Afterward, SVM used in the classification process, while the largest multi-view CASIA-B (Chinese Academy of Sciences) datasets were used to test the model. The investigators report that their study outcomes were beneficial.

According to the literature review, the current most universal gait-based approaches to gender classification include GEI and GII approaches. As a result, this research focuses on contrasting GII approaches with GEI approaches to present a gait-based gender classification in real-time [68]. The one with the highest accuracy is beneficial for future ongoing research studies.


2.1. Search Criteria

The systematic review aimed at reviewing published papers, as well as academic journals, in a step-by-step manner. It also intends to perform a systematic peer-review on academic-based journals. It will use online search engines such as IEEExplore1, PubMed2, Google Scholar3, Cochrane4, CINAHL, Medline5, Web of Science6, DBLP7, and Embase8 to search for literature. The primary keywords used for the search are Computer vision, Artificial Intelligence, Machine learning, deep learning, CNN, Abnormal gait analysis, gait analysis, Stroke, Parkinson's disease, and Movement disorders.

2.2. Justification of the Selection

The preliminary research produced one hundred articles. We considered only 10 of them in this literature review. Out of the 10 articles, only 5 of them were selected related to this report’s topic. This literature review set an interval duration from 2009 and 2019 to analyze; this ensures up-to-date works of literature used for the review. However, at times, some earlier journals were selected.


3.1. Findings and Analysis

The key findings from the journals are provided in Table 1.

Table 1. Key findings.
System Suggested Year Computer Vision technology Machine Learning Technique The Abnormality Identified Using the Gait Analysis Reference
Automatic Health Problem Detection 2018 Videos captured using digital cameras DNN Parkinson’s disease
Pose Stroke
orthopedic problems
A vision-based proposal for classification of normal and abnormal gait 2016 RGB Camera KNN and SVM Dementia
Computer Vision-Based Gait Analysis 2018 Smart Phone KNN Senility
Extracting Body Landmarks from Videos 2019 Videos Suggested future work for classification or regression algorithms Parkinson disease [4]
System to support the Discrimination of Neuro-degenerative Diseases 2009 Videos SVM, Random Forest, and KStar Amyotrophic lateral sclerosis, Parkinson's disease, and Huntington's disease [5]
Several measures were identified in the gait analysis to study the abnormality of the patients, some of which are in Table 2.
Table 2. The measures identified in the gait analysis to study the abnormality of the patients [69, 70].
Patient Abnormality Gait Measures
Slow walking Gait speed
Frequency of steps
Muscle weakness Muscle force
Crouch Gait Ankle joint angle
Unstable gait Gait stability measure
Double support time
High stepped gait Step height
Pelvis drop Hip flexion


According to this brief literature review, several machine learning algorithms are used in the classification, which includes SVM, K-Star, Random Forest, KNN, and DNN. The images and videos are widely used in the literature to capture the human walk while performing the gait analysis. Therefore, the use of high technologies of computer vision, such as smartphone cameras, surveillance cameras, among others, is rapidly emerging. Limitations to this brief review include its deficiency to perform in-depth research on the gait analysis, its functions, and at length comparison of studies.

Future research databases with real-time data, as opposed to single gait data and less geographic and demographic restrictions, are needed [6]. Improvement in accuracy in gait patterns recognition affected by variations in clothing needs further research [6]. Multiview covariate data sequences are needed, giving multiple view angles resulting in less error rate [6]. Segmentation of gait in unconstrained, background conditions that lead to adaptive background modelling also needs refined research to correct these issues [6]. Lastly, optimization of feature selection and reduction of feature space is also needed for future research [6].



Not applicable.




The author declares no conflict of interest, financial or otherwise.


Declared none.


[1] Spaniolas K E A. Ground Level Falls Are Associated With Significant Mortality in Elderly Patients. J Trau Injur Infec Criti Care 2010; 69(4): 821-5.
[2] Mehrizi R, Peng X, Tang Z, Xu X, Metaxas D, Li K. Toward marker-free 3D pose estimation in lifting: A deep multi-view solution In 2018, 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) 2018.
[3] Nieto-Hidalgo M, Ferrández-Pastor FJ, Valdivieso-Sarabia RJ, Mora-Pascual J, García-Chamizo JM. A vision based proposal for classification of normal and abnormal gait using RGB camera. J Biomed Inform 2016; 63: 82-9.
[4] Fleyeh H, Westin J. Extracting body landmarks from videos for parkinson gait analysis. 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS) 2019.
[5] Zheng H, Yang M, Wang H, McClean S. Machine learning and statistical approaches to support the discrimination of neuro-degenerative diseases based on gait analysis. Intelligent patient management 2009.
[6] Singh J P, Jain Sanjeev, Singh U. Vision Based Gait Recognition: A Survery IEEE Access 2018; 6: 70497-527.
[7] Mahoney FI, Barthel DW. Functional evaluation: the Barthel index. Md State Med J 1965; 14: 61-5.
[8] Pirker W, Katzenschlager R. Gait disorders in adults and the elderly : A clinical guide. Wien Klin Wochenschr 2017; 129(3-4): 81-95.
[9] Haynes CA, Lockhart TE. Evaluation of gait and slip parameters for adults with intellectual disability. J Biomech 2012; 45(14): 2337-41.
[10] Verghese J, Lipton RB, Hall CB, Kuslansky G, Katz MJ, Buschke H. Abnormality of gait as a predictor of non-Alzheimer’s dementia. N Engl J Med 2002; 347(22): 1761-8.
[11] Brandler TC, Wang C, Oh-Park M, Holtzer R, Verghese J. Depressive symptoms and gait dysfunction in the elderly. Am J Geriatr Psychiatry 2012; 20(5): 425-32.
[12] Lee S-S, Choi ST, Choi S-I. Classification of gait type based on deep learning using various sensors with smart insole. Sensors (Basel) 2019; 19(8): 1757.
[13] Mehrizi R, Xi P, Zhang S, Liao R, Li K. Automatic health problem detection from gait videos using deep neural networks. arXiv preprint arXiv 2019; 1906.01480
[14] Muro-de-la-Herran A, Garcia-Zapirain B, Mendez-Zorrilla A. Gait analysis methods: an overview of wearable and non-wearable systems, highlighting clinical applications. Sensors (Basel) 2014; 14(2): 3362-94.
[15] Nieto-Hidalgo M, Ferrández-Pastor FJ, Valdivieso-Sarabia RJ, Mora-Pascual J, García-Chamizo JM. Vision based extraction of dynamic gait features focused on feet movement using RGB camera 2015.
[16] Akhtaruzzaman M, Akramin AS, Khan MR. Gait analysis: Systems, technologies, and importance. J Mech Med Biol 2016; 16(7)1630003
[17] Neethu N, Anoop B. Role of Computer Vision in Automatic Inspection Systems. Int J Comput Appl 2015; 123(13)
[18] Zhou X, Zhu M, Leonardos S, Derpanis KG, Daniilidis K. Sparseness meets deepness: 3D human pose estimation from monocular video. Proceedings of the IEEE conference on computer vision and pattern recognition 4966-75.2016;
[19] Corazza S, Mündermann L, Chaudhari AM, Demattio T, Cobelli C, Andriacchi TP. A markerless motion capture system to study musculoskeletal biomechanics: Visual hull and simulated annealing approach. Ann Biomed Eng 2006; 34(6): 1019-29.
[20] Iranmanesh SM, Kazemi H, Soleymani S, Dabouei A, Nasrabadi NM. Deep sketch-photo face recognition assisted by facial attributes. 2018 IEEE 9th International Conference on Biometrics Theory Applications and Systems (BTAS) 2018; 1-10.
[21] Yang J, Nguyen MN, San PP, Li XL, Krishnaswamy S. Deep convolutional neural networks on multichannel time series for human activity recognition. Twenty-Fourth International Joint Conference on Artificial Intelligence 2015.
[22] Pavlakos G, Zhou X, Derpanis KG, Daniilidis K. Coarse-to-fine volumetric prediction for single-image 3D human pose. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017.
[23] Chen S, Lach J, Lo B, Yang G-Z. Toward pervasive gait analysis with wearable sensors: A systematic review. IEEE J Biomed Health Inform 2016; 20(6): 1521-37.
[24] Chinmilli P, Redkar S, Zhang W, Sugar T. A review on wearable inertial tracking based human gait analysis and control strategies of lower-limb exoskeletons. Int Robot Autom J 2017; 3(7): 00080.
[25] Jiang W, Josse J, Lavielle M. Lavielle and TraumaBase Group, “Logistic regression with missing covariates: Parameter estimation, model selection and prediction within a joint-modeling framework Computat Statist Data Analys 2019; 106907
[26] Khorasani A, Yazdi MRS. Development of a dynamic surface roughness monitoring system based on artificial neural networks (ANN) in milling operation. Int J Adv Manuf Technol 2017; 93(1-4): 141-51.
[27] Kapur B, Ahluwalia N, Sathyaraj R. Comparative study on marks prediction using data mining and classification algorithms. Int J Adv Res Comp Sci 2017; 8(3)
[28] Thanh Noi P, Kappas M. Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 imagery. Sensors (Basel) 2017; 18(1): 18.
[29] Hu L-Y, Huang M-W, Ke S-W, Tsai C-F. The distance function effect on k-nearest neighbor classification for medical datasets. Springerplus 2016; 5(1): 1304.
[30] Tezel G, Buyukyildiz M. Monthly evaporation forecasting using artificial neural networks and support vector machines. Theor Appl Climatol 2016; 124(2): 69-80.
[31] Wang L, Zang J, Zhang Q, Niu Z, Hua G, Zheng N. Action recognition by an attention-aware temporal weighted convolutional neural network. Sensors (Basel) 2018; 18(7): 1979.
[32] Mehta D, Sridhar S, Sotnychenko O, et al. Vnect: Real-time 3d human pose estimation with a single rgb camera. ACM Trans Graph 2017; 36(4): 1-14. [TOG].
[33] Andriluka M, Roth S, Schiele B. Pictorial structures revisited: People detection and articulated pose estimation IEEE 2009.
[34] Othmezouri G, Sakata I, Schiele B, Andriluka M, Roth S. Monocular 3D pose estimation and tracking by detection. Patent 8,958,600 2015.
[35] Pishchulin L, Andriluka M, Gehler P, Schiele B. “Poselet conditioned pictorial structures,” in Pishchulin, Leonid; Andriluka, Mykhaylo; Gehler, Peter; Schiele 2013.
[36] Kiefel M, Gehler PV. Human pose estimation with fields of parts. European Conference on Computer Vision 2014.
[37] Tian Y, Zitnick CL, Narasimhan SG. Exploring the spatial hierarchy of mixture models for human pose estimation Patent 8,958,600 2012.
[38] Sun M, Savarese S. Articulated part-based model for joint object detection and pose estimation 2011 Int Conf Comp Vis 2011.
[39] Dantone M, Gall J, Leistner C, Gool LV. Human pose estimation using body parts dependent joint regressors Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2013.
[40] Karlinsky L, Ullman S. Using linking features in learning non-parametric part models. European Conference on Computer Vision Berlin, Heidelberg. 2012.2012.
[41] Ramakrishna V, Munoz D, Hebert M, Bagnell JA, Sheikh Y. Pose machines: Articulated pose estimation via inference machines. European Conference on Computer Vision 2014.
[42] Pinheiro PH, Collobert R. Recurrent convolutional neural networks for scene labeling 31st International Conference on Machine Learning (ICML) 2014.
[43] Ross S, Munoz D, Hebert M, Bagnell J A. Learning message-passing inference machines for structured prediction CVPR 2011 2011.
[44] Tompson JJ, Jain A, LeCun Y, Bregler C. Joint training of a convolutional network and a graphical model for human pose estimation In Advances in neural information processing systems 2014.
[45] Tu Z, Bai X. Auto-context and its application to high-level vision tasks and 3D brain image segmentation. IEEE Trans Pattern Anal Mach Intell 2010; 32(10): 1744-57.
[46] Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems 2012.
[47] Pishchulin L, Insafutdinov E, Tang S, et al. Deepcut: Joint subset partition and labeling for multi person pose estimation Proceedings of the IEEE conference on computer vision and pattern recognition 2016.
[48] Tompson J, Goroshin R, Jain A, LeCun Y, Bregler C. Efficient object localization using convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015.
[49] Pfister T, Charles J, Zisserman A. Flowing convnets for human pose estimation in videos. Proceedings of the IEEE International Conference on Computer Vision 2015.
[50] Carreira J, Agrawal P, Fragkiadaki K, Malik J. Human pose estimation with iterative error feedback. Proceedings of the IEEE conference on computer vision and pattern recognition 2016.
[51] Toshev A, Szegedy C. Deeppose: Human pose estimation via deep neural networks Proceedings of the IEEE conference on computer vision and pattern recognition 2014.
[52] Qiang B, Zhang S, Zhan Y, Xie W, Zhao T. Improved convolutional pose machines for human pose estimation using image sensor data. Sensors (Basel) 2019; 19(3): 718.
[53] Wei S-E, Ramakrishna V, Kanade T, Sheikh Y. Convolutional pose machines. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition 2016.
[54] Lifshitz I, Fetaya E, Ullman S. Human pose estimation using deep consensus voting. European Conference on Computer Vision 246-60.
[55] Belagiannis V, Zisserman A. Recurrent human pose estimation. In 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017) 2017.
[56] Newell A, Yang K, Deng J. Stacked hourglass networks for human pose estimation European conference on computer vision 2016.
[57] Yang W, Li S, Ouyang W, Li H, Wang X. Learning feature pyramids for human pose estimation. In proceedings of the IEEE international conference on computer vision 2017.
[58] Chou C-J, Chien J-T, Chen H-T. Self adversarial training for human pose estimation In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2018.
[59] Chu X, Yang W, Ouyang W, Ma C, Yuille AL, Wang X. Multi-context attention for human pose estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2017.
[60] Han J, Bhanu B. Gait energy image representation: comparative performance evaluation on USF HumanID database. Proc Joint Int’l Workshop VS-PETS 2003.
[61] Chang P-C, Tien M-C, Wu J-L, Hu C-S. Real-time gender classification from human gait for arbitrary view angles In 2009 11th IEEE International Symposium on Multimedia 2009.
[62] Yu S, Tan T, Huang K, Jia K, Wu X. A study on gait-based gender classification. IEEE Trans Image Process 2009; 18(8): 1905-10.
[63] Chunli L, Kejun W. A behavior classification based on enhanced gait energy image. 2010 International Conference on Networking and Digital Society 2: 589-92.2010;
[64] Mikawa M, Izumi S, Tanaka K. Book recommendation signage system using silhouette-based gait classification In 2011 10th International Conference on Machine Learning and Applications and Workshops 2011; 1: 416-9.
[65] Juang L-H, Lin S-A, Wu M-N. Gender recognition studying by gait energy image classification. 2012 International Symposium on Computer, Consumer and Control 2012.
[66] Zhang D, Wang Y. Using multiple views for gait-based gender classification In The 26th Chinese Control and Decision Conference (2014 CCDC) 2014.
[67] Arora P, Hanmandlu M, Srivastava S. Gait based authentication using gait information image features. Pattern Recognit Lett 2015; 68: 336-42.
[68] Guru VM, Kamalesh V, Dinesh R. Human gait recognition using four directional variations of gradient gait energy image 2016 International Conference on Computing, Communication and Automation (ICCCA) 2016.
[69] Alamgir H, Muazzam S, Nasrullah M. Unintentional falls mortality among elderly in the United States: Time for action Injury 2012; 43(12): 2065-71.
[70] Cao Z, Simon T, Wei S-E, Sheikh Y. Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields arXivorg no. arXiv:1611.08050, 2017