Optical Motion Analysis System Research Articles

Comparing the Ground Reaction Forces, Toe Clearances, and Stride Lengths of Young and Older Adults Using a Novel Shoe Sensor System

In this study, we developed a lightweight shoe sensor system equipped with four high-capacity, compact triaxial force sensors and an inertial measurement unit. Remarkably, this system enabled measurements of localized three-directional ground reaction forces (GRFs) at each sensor position (heel, first and fifth metatarsal heads, and toe) and estimations of stride length and toe clearance during walking. Compared to conventional optical motion analysis systems, the developed sensor system provided relatively accurate results for stride length and minimum toe clearance. To test the performance of the system, 15 older and 8 young adults were instructed to walk along a straight line while wearing the system. The results reveal that compared to the young adults, older adults exhibited lower localized GRF contributions from the heel and greater localized GRF contribution from the toe and fifth metatarsal locations. Furthermore, the older adults exhibited greater variability in their stride length and smaller toe clearance with greater variability compared to the young adults. These results underscore the effectiveness of the proposed gait analysis system in distinguishing the gait characteristics of young and older adults, potentially replacing traditional motion capture systems and force plates in gait analysis.

Validity of Wearable Gait Analysis System for Measuring Lower-Limb Kinematics during Timed Up and Go Test

Few studies have reported on the validity of a sensor-based lower-limb kinematics evaluation during the timed up and go (TUG) test. This study aimed to determine the validity of a wearable gait sensor system for measuring lower-limb kinematics during the TUG test. Ten young healthy participants were enrolled, and lower-limb kinematics during the TUG test were assessed using a wearable gait sensor system and a standard optical motion analysis system. The angular velocities of the hip, knee, and ankle joints in sit-to-stand and turn-to-sit phases were significantly correlated between the two motion analysis systems (R = 0.612–0.937). The peak angles and ranges of motion of hip, knee, and ankle joints in the walking-out and walking-in phases were also correlated in both systems (R = 0.528–0.924). These results indicate that the wearable gait sensor system is useful for evaluating lower-limb kinematics not only during gait, but also during the TUG test.

Overconstraint Associated With a Modified Lemaire Lateral Extra-Articular Tenodesis Is Decreased by Using an Anterior Femoral Insertion Point in a Cadaveric Model

To investigate tibiofemoral knee kinematics when shifting the femoral insertion point of the modified Lemaire lateral extra-articular tenodesis (LET) anterior to the lateral epicondyle. Six fresh-frozen human knee joints were tested on a test bench in the following states: (1) native, (2) anterolateral insufficient, (3) original Lemaire (oLET; insertion point: 4 mm posterior and 8 mm proximal to the epicondyle), (4) anterior Lemaire (aLET; insertion point: 5 mm anterior and 5 mm proximal to the epicondyle). Internal tibial rotation was statically investigated under an internal tibial torque of 5 Nm in 0°, 30°, 60°, and 90° of flexion. Anterior translation was statically investigated during a simulated Lachman test with an anterior translational force of 98 N. Additionally, the range of internal tibial rotation and anterior translation were dynamically investigated by a simulated pivot-shift test. Tibiofemoral kinematics were measured using an optical 3D motion analysis system. The aLET showed an internal tibial rotation comparable to the native state for all tested flexion angles except 90° (0°: P= .201; 30°: P= .118; 60°: P= .126; 90°: P= .026). The oLET showed an internal tibial rotation below the values of the native state for all tested flexion angles indicating an overconstraint (0°: P= .003; 30°: P= .009; 60°: P= .029; 90°: P= .029). Direct comparisons between aLET and oLET showed a significantly decreased overconstraint at 0° and 30° of flexion (P= .001 and P= .003, respectively) when using the aLET. No differences in anterior translation and internal tibial rotation were found between the oLET and aLET during simulated Lachman andpivot-shift test (P > .05), approximating the native state. An anteriorly shifted LET insertion point restored internal tibial rotation after anterolateral insufficiency to the native state while decreasing the overconstraint of internal tibial rotation induced by an LET using the originally described insertion point for small flexion angles ≤30°. Using an LET insertion point anterior to the epicondyle was recently reported to lower the risk of tunnel interference and has now been shown to restore internal tibial rotation effectively invitro in the course of the present study. Concerns of overconstraining internal tibial rotation are not diminished by this technique, but using an anterior insertion point helps to decrease overconstraint.

SensAA-Design and Verification of a Cloud-Based Wearable Biomechanical Data Acquisition System.

Exoskeletons designed to assist patients with activities of daily living are becoming increasingly popular, but still are subject to research. In order to gather requirements for the design of such systems, long-term gait observation of the patients over the course of multiple days in an environment of daily living are required. In this paper a wearable all-in-one data acquisition system for collecting and storing biomechanical data in everyday life is proposed. The system is designed to be cost efficient and easy to use, using off-the-shelf components and a cloud server system for centralized data storage. The measurement accuracy of the system was verified, by measuring the angle of the human knee joint at walking speeds between 3 and 12 km/h in reference to an optical motion analysis system. The acquired data were uploaded to a cloud database via a smartphone application. Verification results showed that the proposed toolchain works as desired. The system reached an RMSE from 2.9° to 8°, which is below that of most comparable systems. The system provides a powerful, scalable platform for collecting and processing biomechanical data, which can help to automize the generation of an extensive database for human kinematics.

The Difference in the Assessment of Knee Extension/Flexion Angles during Gait between Two Calibration Methods for Wearable Goniometer Sensors.

Frontal and axial knee motion can affect the accuracy of the knee extension/flexion motion measurement using a wearable goniometer. The purpose of this study was to test the hypothesis that calibrating the goniometer on an individual's body would reduce errors in knee flexion angle during gait, compared to bench calibration. Ten young adults (23.2 ± 1.3 years) were enrolled. Knee flexion angles during gait were simultaneously assessed using a wearable goniometer sensor and an optical three-dimensional motion analysis system, and the absolute error (AE) between the two methods was calculated. The mean AE across a gait cycle was 2.4° (0.5°) for the on-body calibration, and the AE was acceptable (<5°) throughout a gait cycle (range: 1.5-3.8°). The mean AE for the on-bench calibration was 4.9° (3.4°) (range: 1.9-13.6°). Statistical parametric mapping (SPM) analysis revealed that the AE of the on-body calibration was significantly smaller than that of the on-bench calibration during 67-82% of the gait cycle. The results indicated that the on-body calibration of a goniometer sensor had acceptable and better validity compared to the on-bench calibration, especially for the swing phase of gait.

Effects of simulated trunk flexion contracture on the margin of stability during obstacle crossing in elderly individuals

BackgroundTrunk flexion contracture is an abnormal posture in elderly individuals with lumbar kyphosis. It is unclear whether this posture affects locomotor stability (margin of stability [MoS]) during obstacle crossing, which is a common trigger for falls in elderly people. Research questionDoes trunk flexion contracture negatively affect MoS during obstacle crossing in elderly people? MethodsTen healthy elderly individuals performed five trials of obstacle crossing using a comfortable speed under two experimental conditions, namely, with (FLEX) or without (NORMAL) a hard lumbar brace to simulate trunk flexion contracture. The obstacle-crossing motion was captured using an optical motion analysis system in order to calculate the MoS in the anteroposterior direction. The MoS at initial contact (IC) and that when the swing foot was above the obstacle (Obs) was compared between FLEX and NORMAL. A greater MoS suggests greater risk of a forward fall. The trunk and lower limb joint angles were measured at Obs. ResultsFLEX significantly increased the MoS at IC, whereas the MoS at Obs did not differ between the two conditions. FLEX demonstrated a crouch posture characterized by an increased flexion angle of stance-side hip and knee joints at the Obs instant. SignificanceForward fall chance might be increased at IC in obstacle crossing with trunk flexion contracture. Meanwhile, the MoS at Obs might be controlled by increasing the crouch posture to offset a forward shift in the CoM position due to the trunk flexion. Because the risk of a stumble on an obstacle and of forward falls should be higher at Obs than at IC, the crouch posture seems to be an effective adaptation that enables elderly people with trunk flexion contracture to safely cross obstacles.

Validity and Reliability of a Wearable Goniometer Sensor Controlled by a Mobile Application for Measuring Knee Flexion/Extension Angle during the Gait Cycle.

Knee kinematics during gait is an important assessment tool in health-promotion and clinical fields. This study aimed to determine the validity and reliability of a wearable goniometer sensor for measuring knee flexion angles throughout the gait cycle. Twenty-two and seventeen participants were enrolled in the validation and reliability study, respectively. The knee flexion angle during gait was assessed using a wearable goniometer sensor and a standard optical motion analysis system. The coefficient of multiple correlation (CMC) between the two measurement systems was 0.992 ± 0.008. Absolute error (AE) was 3.3 ± 1.5° (range: 1.3-6.2°) for the entire gait cycle. An acceptable AE (<5°) was observed during 0-65% and 87-100% of the gait cycle. Discrete analysis revealed a significant correlation between the two systems (R = 0.608-0.904, p ≤ 0.001). The CMC between the two measurement days with a 1-week interval was 0.988 ± 0.024, and the AE was 2.5 ± 1.2° (range: 1.1-4.5°). A good-to-acceptable AE (<5°) was observed throughout the gait cycle. These results indicate that the wearable goniometer sensor is useful for assessing knee flexion angle during the stance phase of the gait cycle.

The Influence of Cell Phone Usage on Dynamic Stability of the Body During Walking.

Dual-task walking and cell phone usage, which is associated with high cognitive load and reduced situational awareness, can increase risk of a collision, a fall event, or death. The objective of this study was to quantify the effect of dual-task cell phone talking, texting, and reading while walking on spatiotemporal gait parameters; minimum foot clearance; and dynamic stability of the lower limb joints, trunk, and head. Nineteen healthy male participants walked on an instrumented treadmill at their self-selected speed as well as walking while simultaneously (1)reading on a cell phone, (2)texting, and (3)talking on a cell phone. Gait analyses were performed using an optical motion analysis system, and dynamic stability was calculated using the Maximum Lyapunov Exponent. Dual-task cell phone usage had a significant destabilizing influence on the lower limb joints during walking. Cell phone talking while walking significantly increased step width and length and decreased minimum foot clearance height (P < .05). The findings suggest that dual-task walking and cell phone conversation may present a greater risk of a fall event than texting or reading. This may be due to the requirements for more rapid information processing and cognitive demand at the expense of motor control of joint stability.

The influence of sedentary behavior on lumbar-pelvic kinematics during squatting and forward bending among physically active students

Prolonged sitting may involve several mechanisms that make it a risk factor for low back pain. The aim of this study was to investigate lumbar-pelvic kinematics and multifidus muscle (MF) activity during squatting and forward bending in relation to the sedentary behavior of physically active students. Sixty-three students were divided into two groups according to the time spent in a sitting position during the day: “high” (>7hours/day); “low” (≤7hours/day). Lumbar-pelvic ratios, ranges of motion, angular velocities, and MF flexion-relaxation phenomenon were investigated. Data were obtained using the optical motion analysis system, and surface electromyography. The results indicated that lumbar-pelvic ratios during both tasks and velocity of lumbar spine during squatting were significantly greater in the “high” than in the “low” sitting group. Muscle activity showed no differences between groups. Prolonged sitting can be considered a factor that slightly, but statistically significantly influences the lumbar-pelvic kinematics in physically active people.

Relationship between Standing Trunk Extension Angle and Medial Elbow Injuries in Young Baseball Pitchers.

Purpose: The purpose of this study was to investigate the relationship between the standing trunk extension angle and medial elbow injuries. Subjects and methods: The study participants were 90 male baseball pitchers (10–12 years) belonging to youth baseball teams. Pitching elbow injuries were evaluated by an orthopedic surgeon using ultrasound scans and physical examination findings. A single optical three-dimensional motion analysis system was used for the trunk extension measurements, with three-dimensional coordinates captured. The overall, upper, and lower trunk angles were then analyzed. Results: Trunk extension angle during standing trunk extension was significantly smaller among participants who were positive for medial elbow injuries on ultrasound scans (positive: 71.4° ± 10.3°; negative: 75.7° ± 9.2°; t = 2.05, p < 0.05). The upper trunk extension angle was significantly smaller than the lower trunk extension angle among participants who were positive for medial elbow injuries on physical examination (upper: 33.0° ± 6.9°; lower: 41.2° ± 8.2°; t = −2.42, p < 0.05). Conclusions: Trunk extension angle during standing trunk extension is associated with medial elbow injuries. Evaluating the trunk extension angle as multiple segments rather than a single rigid body is valuable.

Kinematic and Kinetic Gait Parameters Can Distinguish between Idiopathic and Neurologic Toe-Walking.

The differentiation between mild forms of toe-walking (equinus) in cerebral palsy (CP) and idiopathic toe-walking (ITW) is often clinically challenging. This study aims to define kinematic and kinetic parameters using 3D gait analysis to facilitate and secure the diagnosis of “idiopathic toe-walking”. We conducted a retrospective controlled stratified cohort study. 12 toe-walking subjects per group diagnosed as ITW or CP were included and stratified according to age, gender and maximal dorsiflexion in stance. We collected kinematic and kinetic data using a three-dimensional optical motion analysis system with integrated floor force plates. Pairwise comparison between ITW and CP gait data was performed, and discriminant factor analysis was conducted. Both groups were compared with typically developing peers (TD). We found kinematic and kinetic parameters having a high discriminatory power and sensitivity to distinguish between ITW and CP groups (e.g., knee angle at initial contact (91% sensitivity, 73% specificity) and foot progression angle at midstance (82% sensitivity, 73% specificity)). The strength of this study is a high discriminatory power between ITW and CP toe-walking groups. Described kinematic parameters are easy to examine even without high-tech equipment; therefore, it is directly transferable to everyday praxis.

Assessment of Shoulder Range of Motion Using a Wearable Inertial Sensor Network

Diagnosis and progress monitoring of frozen shoulder rely on correct measurement of active and passive range of motion (ROM) of shoulder. This paper studied the feasibility of a wearable inertial sensor network (WISN) and its associated shoulder ROM estimation algorithm for shoulder ROM assessment. The WISN composed of three inertial modules were placed on the trunk, upper arm, and forearm of human for assessment of shoulder ROM in real time. Each inertial module consists of an ARM-based 32-bit microcontroller, a triaxial accelerometer, a triaxial gyroscope, a triaxial magnetometer, and a controller area network (CAN) transceiver. The measured accelerations, angular velocities, and magnetic signals generated by the human shoulder movements are transmitted to a personal computer via a Bluetooth wireless transmission module. The proposed shoulder ROM estimation algorithm includes the procedures of data collection, signal preprocessing, quaternion-based orientation estimation, and shoulder joint compensation. In order to evaluate shoulder ROM accurately, accelerations, angular velocities, and magnetic signals are integrated into a quaternion-based complementary nonlinear filter for minimizing the cumulative errors caused by the drift of the inertial sensors. Experimental results demonstrate that the WISN with the designed shoulder ROM estimation algorithm, compared to an optical motion analysis system (Vicon), have the average root mean square (RMS) angle errors ranging from 2.53° to 3.56°. In addition, the intra-tester reliability for each shoulder ROM measurement is excellent. The proposed WISN is a valid and reliable tool and can be used anywhere without any external reference device for convenient evaluation of shoulder ROM.

Biomechanical Ambulatory Assessment of 3D Knee Angle Using Novel Inertial Sensor-Based Technique

Three-dimensional (3D) knee angle measurement is one of the key measures in human gait analysis. Inertial sensor capable of measuring joint motion under unconstrained conditions is a practical tool for clinical evaluation and rehabilitation. An inertial measurement unit (IMU) consisting of accelerometer and gyroscope allows orientation measurement in 3D with an additional sensor (i.e., magnetometer). However, ferromagnetic interference negatively affects the performance of magnetometer and thus reduces measurement accuracy. In this study, a technique based on nonlinear autoregressive neural network with exogenous inputs (NARX) is presented to measure 3D segmental orientation during gait without the use of magnetometer. With IMUs attached to the thigh and shank, 3D knee angles in long-distance treadmill walking were computed and validated against an optical motion analysis system as the gold standard. Pseudo-integrator (PI) was also compared to the reference system for benchmarking. The learning capability of NARX was further assessed with the comparison of complementary filter (CF) to the reference system. The proposed NARX model was shown to outperform PI with biases between -3.5° and -0.2°, and root mean square errors between 4.5° and 2.5°. Results demonstrated the capability of NARX in providing accurate estimates of 3D knee joint angle while avoiding interference as encountered in systems incorporating magnetometer, suggesting that NARX is feasible to computing long-term ambulatory measurements of body segment orientation and 3D joint angles.

Pose estimation by extended Kalman filter using noise covariance matrices based on sensor output

This paper presents an extended Kalman filter for pose estimation using noise covariance matrices based on sensor output. Compact and lightweight nine-axis motion sensors are used for motion analysis in widely various fields such as medical welfare and sports. A nine-axis motion sensor includes a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer. Information obtained from the three sensors is useful for estimating joint angles using the Kalman filter. The extended Kalman filter is used widely for state estimation because it can estimate the status with a small computational load. However, determining the process and observation noise covariance matrices in the extended Kalman filter is complicated. The noise covariance matrices in the extended Kalman filter were found for this study based on the sensor output. Postural change appears in the gyroscope output because the rotational motion of the joints produces human movement. Therefore, the process noise covariance matrix was determined based on the gyroscope output. An observation noise covariance matrix was determined based on the accelerometer and magnetometer output because the two sensors’ outputs were used as observation values. During a laboratory experiment, the lower limb joint angles of three participants were measured using an optical 3D motion analysis system and nine-axis motion sensors while participants were walking. The lower limb joint angles estimated using the extended Kalman filter with noise covariance matrices based on sensor output were generally consistent with results obtained from the optical 3D motion analysis system. Furthermore, the lower limb joint angles were measured using nine-axis motion sensors while participants were running in place for about 100 s. The experiment results demonstrated the effectiveness of the proposed method for human pose estimation.

Three-dimensional kinematics analysis of blind football kicking

ABSTRACT The purpose of this study was to identify critical technical points that lead to increased ball speed in a maximal toe kick with no run-up (a ‘static kick’) in blind football. Six visually impaired male players and eight sighted male players participated in the experiment. All participants wore a blindfold to fully remove visual information and performed the static kick. The motion was captured three-dimensionally using an optical motion analysis system. Our results demonstrated that ball speed, maximum linear velocity of the kicking-side thigh, and maximum angular velocity of the kicking-side shank for the sighted player group were significantly greater than those for the visually impaired player group. The sighted players tended to perform the static kick in a similar motion pattern, which was characterised by a backwards rotation of the torso to adequately extend the kicking-side hip joint during the back-swing phase and a stable posture of the lower torso on the frontal plane during the forward-swing phase. This motion pattern is critical to both acceleration of the kicking-side foot and orientation of the foot for a more precise ball contact position.

Using a Single Uniaxial Gyroscope to Detect Lateral Ankle Sprain Hazard

Lateral ankle sprain is very common in sports. Recently, there was a wearable assistive technology that stimulates the peroneal muscles to prevent this injury, but it requires a monitoring system to detect injury hazards and actuate the protection. This study presents the feasibility of a uniaxial gyroscope to monitor the peak ankle inversion velocity during common sporting motion and simulated ankle sprain motion. Ten males performed walking, running, 45-deg cutting, vertical jump-landing, stepping-down from a block, 5 kinds of simulated ankle sprain motion on sprain simulators, and a manual ankle-twisting motion in a biomechanics laboratory. The peak ankle inversion velocity was collected by an optical motion analysis system at 120 Hz. Besides, a uniaxial gyroscope was attached to the heel to collect the peak twisting velocity at 500 Hz. Pearson test showed a strong or high positive correlation between the two parameters. Independent t-test showed no difference between the two parameters in all testing motions except the manual ankle-twisting test which the value was 82% of that from the optical motion capture system and both values are above the threshold, 300 deg/s. We concluded the method is applicable to detect the hazard of lateral ankle sprain injury.

Predicting Center of Gravity Displacement During Walking Using a Single Inertial Sensor and Deep Learning Technique

Center of gravity (CG) trajectory during walking has been used as an important indicator to understand the mechanism of pathological walking. Kinematic method using optical motion analysis system and force plate method using ground reaction force are conventionally used to calculate CG trajectory during gait. However, there is a limitation in that expensive experimental equipment is needed to measure it. The purpose of this study was to develop a long short-term memory (LSTM) network model that could estimate the CG trajectory during gait based on a low-cost portable inertial sensor signal. Twenty healthy adult males (age: 24.2±2.1 years; height: 171.4±5.2 cm; weight: 67.5±7.4 kg) who had no history of musculoskeletal disorders were participated in the study. Based on the optical motion capture system, CG trajectories have been calculated using highly accurate kinematic method. Input variables of the LSTM model consisted of a total of six signals of three-axis acceleration and angular velocity. Data were divided into training/validation/testing data at a ratio of 80/10/10. Performance was evaluated utilizing 10-fold cross-validation. As a result of model estimation, the Pearson correlation coefficient of about 0.9 or more and root mean square error values ranging from 3.9 to 31 mm were obtained in anterior/posterior, proximal/distal, and medial/lateral directions. These results confirmed that the CG trajectory during walking could be estimated by using low cost, small wearable inertial sensor. This novel CG prediction method has potential to evaluate pathological gait by incorporating patient walking data.

Impact of Body Mass Index on Biomechanics of Recreational Runners.

Some recreational runners with obesity successfully train or compete without musculoskeletal injury. Insight into the key kinetic strategies of injury-free heavier runners is necessary to appropriately guide development of safe training programs for this population. To determine key biomechanical strategies of running in individuals with body mass index (BMI) values above and equal to and higher than 30 kg/m2 . This was a case-control study. Runners with obesity (n =18; 42.7 years, 38.9% women) who were matched by sex, age, footstrike type, footwear characteristics, and running speed with healthy runners (n = 36; 41.7 years, 32.5% women). Research laboratory affiliated with an academic medical center. A seven-camera optical motion analysis system was used to capture running kinematics and an instrumented treadmill captured kinetic data. Main outcomes were temporal spatial parameters, joint excursions, peak ground reaction forces (GRFs), joint moments, vertical average loading rate (VALR), impulses, and vertical stiffness (Kvert ). Runners with obesity demonstrated 15% less vertical excursion of the center of mass, 18% wider strides, and 3% longer stance times than nonobese runners (P < .05). Normalized peak GRFs and VALRs were higher in the nonobese group. GRF impulse was higher in the group with obesity compared to the nonobese group (means ± SD; 339.6 ± 55.2 Ns vs. 255.0 ± 45.8 Ns; P = .0001). Kvert was higher in the obese group compared to the nonobese group (238.6 ± 50.3 N/cm vs. 183.1 ± 29.4 N/cm; P = .0001). Peak hip moments were higher in runners with obesity in the sagittal and frontal planes (P < .05). Runners with obesity dampened impact forces and controlled loading rate more than nonobese runners by increasing lower body stiffness and constraining vertical displacement.

A Practical Gait Feedback Method Based on Wearable Inertial Sensors for a Drop Foot Assistance Device

To maximise the efficiency of gait interventions, gait phase and joint kinematics are important for closing the system loop of adaptive robotic control. However, few studies have applied an inertial sensor system including both gait phase detection and joint kinematic measurement. Many algorithms for joint measurement require careful alignment of the inertial measurement unit (IMU) to the body segment. In this paper, we propose a practical gait feedback method, which provides sufficient feedback without requiring precise alignment of the IMUs. The method incorporates a two-layer model to realise simultaneous gait stance and swing phase detection and ankle joint angle measurement. Recognition of gait phases is performed by a high-level probabilistic method using angular rate from the sensor attached to the shank while the ankle angle is calculated using a data fusion algorithm based on the complementary filter and sensor-to-segment calibration. The online performance of the algorithm was experimentally validated when 10 able-bodied participants walked on the treadmill with three different speeds. The outputs were compared to the ones measured by an optical motion analysis system. The results showed that the IMU-based algorithm achieved a good accuracy of the gait phase recognition (above 95%) with a short delay response below 20 ms and accurate angle measurements with root mean square errors below 3.5° compared to the optical reference. It demonstrates that our method can be used to provide gait feedback for the correction of drop foot.

Automation enhancement and accuracy investigation of a portable single‐camera gait analysis system

While optical motion analysis systems can provide high-fidelity gait parameters, they are usually impractical for local clinics and home use, due to high cost, requirement for large space, and lack of portability. In this study, the authors focus on a cost-effective and portable, single-camera gait analysis solution, based on video acquisition with calibration, autonomous detection of frames-of-interest, Kalman-filter + structural-similarity-based marker tracking, and autonomous knee angle calculation. The proposed system is tested using 15 participants, including 10 stroke patients and 5 healthy volunteers. The evaluation of autonomous frames-of-interest detection shows only 0.2% difference between the frame number of the detected frame compared to the frame number of the manually labelled ground truth frame, and thus can replace manual labelling. The system is validated against a gold standard optical motion analysis system, using knee angle accuracy as metric of assessment. The accuracy investigation between the RGB- and the greyscale-video marker tracking schemes shows that the greyscale system suffers from negligible accuracy loss with a significant processing speed advantage. Experimental results demonstrate that the proposed system can automatically estimate the knee angle, with R-squared value larger than 0.95 and Bland-Altman plot results smaller than 3.0127° mean error.