scholarly journals Development of a Robust, Simple, and Affordable Human Gait Analysis System Using Bottom-Up Pose Estimation With a Smartphone Camera

2022 ◽  
Vol 12 ◽  
Author(s):  
Aditya Viswakumar ◽  
Venkateswaran Rajagopalan ◽  
Tathagata Ray ◽  
Pranitha Gottipati ◽  
Chandu Parimi
Keyword(s):  
Gait Analysis ◽  
Real Time ◽  
Spinal Cord Injuries ◽  
Video Camera ◽  
Medical Diagnostics ◽  
Human Gait ◽  
Bottom Up ◽  
Flexion Extension ◽  
Analysis System ◽  
Ms Kinect

Gait analysis is used in many fields such as Medical Diagnostics, Osteopathic medicine, Comparative and Sports-related biomechanics, etc. The most commonly used system for capturing gait is the advanced video camera-based passive marker system such as VICON. However, such systems are expensive, and reflective markers on subjects can be intrusive and time-consuming. Moreover, the setup of markers for certain rehabilitation patients, such as people with stroke or spinal cord injuries, could be difficult. Recently, some markerless systems were introduced to overcome the challenges of marker-based systems. However, current markerless systems have low accuracy and pose other challenges in gait analysis with people in long clothing, hiding the gait kinematics. The present work attempts to make an affordable, easy-to-use, accurate gait analysis system while addressing all the mentioned issues. The system in this study uses images from a video taken with a smartphone camera (800 × 600 pixels at an average rate of 30 frames per second). The system uses OpenPose, a 2D real-time multi-person keypoint detection technique. The system learns to associate body parts with individuals in the image using Convolutional Neural Networks (CNNs). This bottom-up system achieves high accuracy and real-time performance, regardless of the number of people in the image. The proposed system is called the “OpenPose based Markerless Gait Analysis System” (OMGait). Ankle, knee, and hip flexion/extension angle values were measured using OMGait in 16 healthy volunteers under different lighting and clothing conditions. The measured kinematic values were compared with a standard video camera based normative dataset and data from a markerless MS Kinect system. The mean absolute error value of the joint angles from the proposed system was less than 90 for different lighting conditions and less than 110 for different clothing conditions compared to the normative dataset. The proposed system is adequate in measuring the kinematic values of the ankle, knee, and hip. It also performs better than the markerless systems like MS Kinect that fail to measure the kinematics of ankle, knee, and hip joints under dark and bright light conditions and in subjects with long robe clothing.

Processing Panorama Video in Real-time

2014 ◽  
Vol 08 (02) ◽  
pp. 209-227 ◽  
Author(s):  
Håkon Kvale Stensland ◽  
Vamsidhar Reddy Gaddam ◽  
Marius Tennøe ◽  
Espen Helgedagsrud ◽  
Mikkel Næss ◽  
...  
Keyword(s):  
Real Time ◽  
Graphics Processing Units ◽  
Low Cost ◽  
Video Camera ◽  
Wide Field ◽  
High Data ◽  
Data Rates ◽  
Camera Arrays ◽  
Analysis System ◽  
Performance Results

There are many scenarios where high resolution, wide field of view video is useful. Such panorama video may be generated using camera arrays where the feeds from multiple cameras pointing at different parts of the captured area are stitched together. However, processing the different steps of a panorama video pipeline in real-time is challenging due to the high data rates and the stringent timeliness requirements. In our research, we use panorama video in a sport analysis system called Bagadus. This system is deployed at Alfheim stadium in Tromsø, and due to live usage, the video events must be generated in real-time. In this paper, we describe our real-time panorama system built using a low-cost CCD HD video camera array. We describe how we have implemented different components and evaluated alternatives. The performance results from experiments ran on commodity hardware with and without co-processors like graphics processing units (GPUs) show that the entire pipeline is able to run in real-time.

Intra-rater and inter-rater reliabilities of real-time acceleration gait analysis system

2014 ◽  
pp. 1-6
Author(s):  
Hiroshi Osaka ◽  
Koichi Shinkoda ◽  
Susumu Watanabe ◽  
Daisuke Fujita ◽  
Kenichi Kobara ◽  
...  
Keyword(s):  
Gait Analysis ◽  
Real Time ◽  
Analysis System

scholarly journals Can an Observational Gait Scale Produce a Result Consistent with Symmetry Indexes Obtained from 3-Dimensional Gait Analysis?: A Concurrent Validity Study

2020 ◽  
Vol 9 (4) ◽  
pp. 926
Author(s):  
Agnieszka Guzik ◽  
Mariusz Drużbicki ◽  
Lidia Perenc ◽  
Justyna Podgórska-Bednarz
Keyword(s):  
Gait Analysis ◽  
Movement Analysis ◽  
Ordinal Scale ◽  
Coefficient Of Determination ◽  
3D Analysis ◽  
3 Dimensional ◽  
Observational Tool ◽  
Gait Parameters ◽  
Flexion Extension ◽  
Analysis System

To investigate whether a simple observational tool may be a substitute to the time-consuming and costly 3-dimensional (3D) analysis, the study applied the Wisconsin Gait Scale (WGS), enabling assessment which is highly consistent with 3D gait parameters in patients after a stroke. The aim of this study was to determine whether, and to what extent, observational information obtained from WGS-based assessment can be applied to predict results of 3D gait analysis for selected symmetry indicators related to spatiotemporal and kinematic gait parameters. Fifty patients at a chronic stage of recovery post-stroke were enrolled in the study. The spatiotemporal and kinematic gait parameters were measured using a movement analysis system. The symmetry index (SI), was calculated for selected gait parameters. The patients’ gait was evaluated by means of the WGS. It was shown that stance % SI, as well as hip and knee flexion-extension range of motion SI can most effectively be substituted by WGS-based estimations (coefficient of determination exceeding 80%). It was shown that information acquired based on the WGS can be used to obtain results comparable to those achieved in 3D assessment for selected SIs of spatiotemporal and kinematic gait parameters. The study confirms that observation of gait using the WGS, which is an ordinal scale, is consistent with the selected aims of 3D assessment. Therefore, the scale can be used as a complementary tool in gait assessment.

FSR and IMU sensors-based human gait phase detection and its correlation with EMG signal for different terrain walk

Sensor Review ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Sachin Negi ◽  
Shiru Sharma ◽  
Neeraj Sharma
Keyword(s):  
Gait Analysis ◽  
Real Time ◽  
Medial Gastrocnemius ◽  
Human Gait ◽  
Phase Detection ◽  
Zero Crossing ◽  
Content Type ◽  
Open Environment ◽  
Emg Signal ◽  
Gait Phase

Purpose The purpose of this paper is to present gait analysis for five different terrains: level ground, ramp ascent, ramp descent, stair ascent and stair descent. Design/methodology/approach Gait analysis has been carried out using a combination of the following sensors: force-sensitive resistor (FSR) sensors fabricated in foot insole to sense foot pressure, a gyroscopic sensor to detect the angular velocity of the shank and MyoWare electromyographic muscle sensors to detect muscle’s activities. All these sensors were integrated around the Arduino nano controller board for signal acquisition and conditioning purposes. In the present scheme, the muscle activities were obtained from the tibialis anterior and medial gastrocnemius muscles using electromyography (EMG) electrodes, and the acquired EMG signals were correlated with the simultaneously attained signals from the FSR and gyroscope sensors. The nRF24L01+ transceivers were used to transfer the acquired data wirelessly to the computer for further analysis. For the acquisition of sensor data, a Python-based graphical user interface has been designed to analyze and display the processed data. In the present paper, the authors got motivated to design and develop a reliable real-time gait phase detection technique that can be used later in designing a control scheme for the powered ankle-foot prosthesis. Findings The effectiveness of the gait phase detection was obtained in an open environment. Both off-line and real-time gait events and gait phase detections were accomplished for the FSR and gyroscopic sensors. Both sensors showed their usefulness for detecting the gait events in real-time, i.e. within 10 ms. The heuristic rules and a zero-crossing based-algorithm for the shank angular rate correctly identified all the gait events for the locomotion in all five terrains. Practical implications This study leads to an understanding of human gait analysis for different types of terrains. A real-time standalone system has been designed and realized, which may find application in the design and development of ankle-foot prosthesis having real-time control feature for the above five terrains. Originality/value The noise-free data from three sensors were collected in the same time frame from both legs using a wireless sensor network between two transmitters and a single receiver. Unlike the data collection using a treadmill in a laboratory environment, this setup is useful for gait analysis in an open environment for different terrains.

241 MARKERLESS VISION-BASED HUMAN GAIT ANALYSIS SYSTEM FOR GAIT REHABILITATION

2010 ◽  
Vol 16 ◽  
pp. S69 ◽  
Author(s):  
D. Ristić-Durrant ◽  
A. Leu ◽  
S. Slavnić ◽  
A. Gräser
Keyword(s):  
Gait Analysis ◽  
Human Gait ◽  
Gait Rehabilitation ◽  
Analysis System ◽  
Human Gait Analysis

scholarly journals Biped Gait Analysis based on Forward Kinematics Modeling using Quaternions Algebra

2020 ◽  
Author(s):  
◽  
J. C. González-Islas ◽  
Keyword(s):  
Gait Analysis ◽  
Sports Medicine ◽  
Assistive Technologies ◽  
Lower Limbs ◽  
Human Gait ◽  
Forward Kinematics ◽  
Mathematical Tool ◽  
Human Beings ◽  
Kinematics Modeling ◽  
Flexion Extension

Gait is the main locomotion way for human beings as an autonomous decision. Due to the increase in people with walking disabilities, the precision in gait analysis for purposes in clinical diagnosis, sports medicine or biomechanical research for the design of assistive technologies is of special relevance. The literature reports notable contributions in technological developments with diverse applications; and in some cases, algorithms for characterization and gait analysis; however, more studies related to gait kinematics are necessary, such as the solution proposed in this work. In this paper, we focus on studying the forward kinematics of the lower limbs in human gait, using in a novel way quaternions algebra as mathematical tool and comparative analysis with classical methods is established. Gait analysis unlike other works is carried out by evaluating the rotational and tilting movements of the pelvis, flexion-extension of the hip and knee; as well as dorsiflexion and plantarflexion of the ankle. Finally, an assessment of normal, mild crouch and severe crouch gaits in the three anatomical planes is performed; and a metric based on the Euclidean norm in the cartesian space is used to evaluate these gaits.

scholarly journals Portable Gait Analysis System with an Integration of Kinect sensor and Inertial Measurement Units

2020 ◽  
Vol 9 (1) ◽  
pp. 73-78
Author(s):  
Pratima Saravanan ◽  
Jiyun Yao ◽  
Jessica Menold
Keyword(s):  
Gait Analysis ◽  
Step Length ◽  
Microsoft Kinect ◽  
Human Gait ◽  
Kinect Sensor ◽  
Inertial Measurement Units ◽  
Combined System ◽  
Inertial Measurement ◽  
Measurement Units ◽  
Analysis System

Clinical gait analysis is used for diagnosing, assessing, and for monitoring a patient by analyzing their kinetics, kinematics and electromyography while walking. Traditionally, gait analysis is performed in a formal laboratory environment making use of several high-resolution cameras, either video or infrared. The subject is asked to walk on a force platform or a treadmill with several markers attached to their body, allowing cameras to capture the joint coordinates across time. The space required for such a laboratory is non-trivial and often the associated costs of such an experimental setup is prohibitively expensive. The current work aims to investigate the coupled use of a Microsoft Kinect and Inertial Measurement Units as a portable and cost-efficient gait analysis system. Past studies on assessing gait using either Kinect or Inertial Measurement Units concluded that they achieve medium reliability individually due to some drawbacks related to each sensor. In this study, we propose that a combined system is efficient in detecting different phases of human gait, and the combination of sensors complement each other by overcoming the individual sensor drawbacks. Preliminary findings indicate that the IMU sensors are efficient in providing gait kinematics such as step length, stride length, velocity, cadence, etc., whereas the Kinect sensor helps in studying the gait asymmetries by comparing the right and left joint, such as hips, knees, and ankle.

Sign in / Sign up

Export Citation Format

Share Document