Estimating body segment parameters from three-dimensional human body scans

Body segment parameters are inputs for a range of applications. Participant-specific estimates of body segment parameters are desirable as this requires fewer prior assumptions and can reduce outcome measurement errors. Commonly used methods for estimating participant-specific body segment parameters are either expensive and out of reach (medical imaging), have many underlying assumptions (geometrical modelling) or are based on a specific subset of a population (regression models). Our objective was to develop a participant-specific 3D scanning and body segmentation method that estimates body segment parameters without any assumptions about the geometry of the body, ethnic background, and gender, is low-cost, fast, and can be readily available. Using a Microsoft Kinect Version 2 camera, we developed a 3D surface scanning protocol that enabled the estimation of participant-specific body segment parameters. To evaluate our system, we performed repeated 3D scans of 21 healthy participants (10 male, 11 female). We used open source tools to segment each body scan into 16 segments (head, torso, abdomen, pelvis, left and right hand, forearm, upper arm, foot, shank and thigh) and wrote custom software to estimate each segment’s mass, mass moment of inertia in the three principal orthogonal axes relevant to the center of the segment, longitudinal length, and center of mass. We compared our body segment parameter estimates to those obtained using two comparison methods and found that our system was consistent in estimating total body volume between repeated scans (male p = 0.1194, female p = 0.2240), estimated total body mass without significant differences when compared to our comparison method and a medical scale (male p = 0.8529, female p = 0.6339), and generated consistent and comparable estimates across a range of the body segment parameters of interest. Our work here outlines and provides the code for an inexpensive 3D surface scanning method for estimating a range of participant-specific body segment parameters.

Quantifying avian inertial properties using calibrated computed tomography

ABSTRACT Estimating centre of mass and mass moments of inertia is an important aspect of many studies in biomechanics. Characterising these parameters accurately in three dimensions is challenging with traditional methods requiring dissection or suspension of cadavers. Here, we present a method to quantify the three-dimensional centre of mass and inertia tensor of birds of prey using calibrated computed tomography (CT) scans. The technique was validated using several independent methods, providing body segment mass estimates within approximately 1% of physical dissection measurements and moment of inertia measurements with a 0.993 R2 correlation with conventional trifilar pendulum measurements. Calibrated CT offers a relatively straightforward, non-destructive approach that yields highly detailed mass distribution data that can be used for three-dimensional dynamics modelling in biomechanics. Although demonstrated here with birds, this approach should work equally well with any animal or appendage capable of being CT scanned.

Video-Based Deep Learning Approach for 3D Human Movement Analysis in Institutional Hallways: A Smart Hallway

New artificial intelligence- (AI) based marker-less motion capture models provide a basis for quantitative movement analysis within healthcare and eldercare institutions, increasing clinician access to quantitative movement data and improving decision making. This research modelled, simulated, designed, and implemented a novel marker-less AI motion-analysis approach for institutional hallways, a Smart Hallway. Computer simulations were used to develop a system configuration with four ceiling-mounted cameras. After implementing camera synchronization and calibration methods, OpenPose was used to generate body keypoints for each frame. OpenPose BODY25 generated 2D keypoints, and 3D keypoints were calculated and postprocessed to extract outcome measures. The system was validated by comparing ground-truth body-segment length measurements to calculated body-segment lengths and ground-truth foot events to foot events detected using the system. Body-segment length measurements were within 1.56 (SD = 2.77) cm and foot-event detection was within four frames (67 ms), with an absolute error of three frames (50 ms) from ground-truth foot event labels. This Smart Hallway delivers stride parameters, limb angles, and limb measurements to aid in clinical decision making, providing relevant information without user intervention for data extraction, thereby increasing access to high-quality gait analysis for healthcare and eldercare institutions.

Application of Computer Algorithm in Fault Diagnosis System of RM Equipment

At present, modern mechanical equipment is gradually developing towards large-scale and intelligent, which leads to more and more complex equipment structure. Therefore, people have higher and higher requirements for intelligent fault diagnosis of mechanical equipment, which leads to the application of various algorithms to mechanical equipment. Among them, rotating machinery (hereinafter referred to as RM) mainly relies on rotating action to complete specific functions, such as gearbox, gas turbine, generator and engine, which are often the core components of mechanical equipment. Therefore, the FSGS (hereinafter referred to as FSGS) of RM equipment has become a very key link in system design and maintenance, which requires designers to constantly overcome the original intelligent diagnosis system. Through a variety of deep learning algorithms, we can improve the diagnosis efficiency of automatic monitoring and diagnosis equipment, which can also reduce the loss caused by untimely diagnosis. Firstly, this paper analyzes the types of application of computer algorithms in the fault body segment system of RM equipment. Then, this paper analyzes an algorithm, which can better improve the diagnosis efficiency of the equipment.

Observational Analysis of Lateral Preference in Kumite Initiation: A Starting Point in the Longitudinal Programming of Formative Karate

We used observational methodology to analyze lateral conditioning in the technical-tactical performance of high level 8–9-year-old karatekas, specifically in relation to the guard action that supports the technical action and the body segment with which it is performed. We designed an ad hoc observation instrument to analyze lateral preference in the technical-tactical actions that take place during the kumite. We relied on LINCE software for data registration, and we found good inter-observer reliability, calculated with Cohen's Kappa coefficient. Generalizability Theory supported the homogeneity of the behavior deployed by these combatants. Our results represent a starting point in the longitudinal programming of karate. By relating our results and those of other studies that have addressed lateral performance in formative karate in the kumite modality, we are able to draw a roadmap of a karateka's path towards the equilaterality that is inherent in an elite competitor: (a) the 8-9 year old karateka must overcome a conditioned lateral prevalence by adopting a forward non-dominant leg guard so as to then attack with the dominant body segment; (b) the eqilateral use of the right or left fist must occur later, between the 12–13 year age group and the senior category; and (c) there will then be less decisive lateral conditioning in the execution of offensive leg techniques.

Machine Learning to Improve Orientation Estimation in Sports Situations Challenging for Inertial Sensor Use

In sports, inertial measurement units are often used to measure the orientation of human body segments. A Madgwick (MW) filter can be used to obtain accurate inertial measurement unit (IMU) orientation estimates. This filter combines two different orientation estimates by applying a correction of the (1) gyroscope-based estimate in the direction of the (2) earth frame-based estimate. However, in sports situations that are characterized by relatively large linear accelerations and/or close magnetic sources, such as wheelchair sports, obtaining accurate IMU orientation estimates is challenging. In these situations, applying the MW filter in the regular way, i.e., with the same magnitude of correction at all time frames, may lead to estimation errors. Therefore, in this study, the MW filter was extended with machine learning to distinguish instances in which a small correction magnitude is beneficial from instances in which a large correction magnitude is beneficial, to eventually arrive at accurate body segment orientations in IMU-challenging sports situations. A machine learning algorithm was trained to make this distinction based on raw IMU data. Experiments on wheelchair sports were performed to assess the validity of the extended MW filter, and to compare the extended MW filter with the original MW filter based on comparisons with a motion capture-based reference system. Results indicate that the extended MW filter performs better than the original MW filter in assessing instantaneous trunk inclination (7.6 vs. 11.7° root-mean-squared error, RMSE), especially during the dynamic, IMU-challenging situations with moving athlete and wheelchair. Improvements of up to 45% RMSE were obtained for the extended MW filter compared with the original MW filter. To conclude, the machine learning-based extended MW filter has an acceptable accuracy and performs better than the original MW filter for the assessment of body segment orientation in IMU-challenging sports situations.