Amin Ahmadi

Automatic Activity Classification and Movement Assessment During a Sports Training Session Using Wearable Inertial Sensors

Motion analysis technologies have been widely used to monitor the potential for injury and enhance athlete performance. However, most of these technologies are expensive, can only be used in laboratory environments and examine only a few trials of each movement action. In this paper, we present a novel ambulatory motion analysis framework using wearable inertial sensors to accurately assess all of an athletes activities in an outdoor training environment. We firstly present a system that automatically classifies a large range of training activities using the Discrete Wavelet Transform (DWT) in conjunction with a Random forest classifier. The classifier is capable of successfully classifying various activities with up to 98% accuracy. Secondly, a computationally efficient gradient descent algorithm is used to estimate the relative orientations of the wearable inertial sensors mounted on the thigh and shank of a subject, from which the flexion-extension knee angle is calculated. Finally, a curve shift registration technique is applied to both generate normative data and determine if a subjects movement technique differed to the normative data in order to identify potential injury related factors. It is envisaged that the proposed framework could be utilized for accurate and automatic sports activity classification and reliable movement technique evaluation in various unconstrained environments.

Toward Automatic Activity Classification and Movement Assessment During a Sports Training Session

Motion analysis technologies have been widely used to monitor the potential for injury and enhance athlete performance. However, most of these technologies are expensive, can only be used in laboratory environments, and examine only a few trials of each movement action. In this paper, we present a novel ambulatory motion analysis framework using wearable inertial sensors to accurately assess all of an athletes activities in real training environment. We first present a system that automatically classifies a large range of training activities using the discrete wavelet transform (DWT) in conjunction with a random forest classifier. The classifier is capable of successfully classifying various activities with up to 98% accuracy. Second, a computationally efficient gradient descent algorithm is used to estimate the relative orientations of the wearable inertial sensors mounted on the shank, thigh, and pelvis of a subject, from which the flexion-extension knee and hip angles are calculated. These angles, along with sacrum impact accelerations, are automatically extracted for each stride during jogging. Finally, normative data are generated and used to determine if a subjects movement technique differed to the normative data in order to identify potential injury-related factors. For the joint angle data, this is achieved using a curve-shift registration technique. It is envisaged that the proposed framework could be utilized for accurate and automatic sports activity classification and reliable movement technique evaluation in various unconstrained environments for both injury management and performance enhancement.

Kinect vs. Low-cost Inertial Sensing for Gesture Recognition

In this paper, we investigate efficient recognition of human gestures / movements from multimedia and multimodal data, including the Microsoft Kinect and translational and rotational acceleration and velocity from wearable inertial sensors. We firstly present a system that automatically classifies a large range of activities (17 different gestures) using a random forest decision tree. Our system can achieve near real time recognition by appropriately selecting the sensors that led to the greatest contributing factor for a particular task. Features extracted from multimodal sensor data were used to train and evaluate a customized classifier. This novel technique is capable of successfully classifying various gestures with up to 91 % overall accuracy on a publicly available data set. Secondly we investigate a wide range of different motion capture modalities and compare their results in terms of gesture recognition accuracy using our proposed approach. We conclude that gesture recognition can be effectively performed by considering an approach that overcomes many of the limitations associated with the Kinect and potentially paves the way for low-cost gesture recognition in unconstrained environments.

Automatically detecting asymmetric running using time and frequency domain features

Human motion analysis technologies have been widely employed to identify injury determining factors and provide objective and quantitative feedback to athletes to help prevent injury. However, most of these technologies are: expensive, restricted to laboratory environments, and can require significant post processing. This reduces their ecological validity, adoption and usefulness. In this paper, we present a novel wearable inertial sensor framework to accurately distinguish between symmetrical and asymmetrical running patterns in an unconstrained environment. The framework can automatically classify symmetry/asymmetry using Short Time Fourier Transform (STFT) and other time domain features in conjunction with a customized Random Forest classifier. The accuracy of the designed framework is up to 94% using 3-D accelerometer and 3-D gyroscope data from a sensor node attached on the upper back of a subject. The upper back inertial sensors data were then down-sampled by a factor of 4 to simulate utilizing low-cost inertial sensors whilst also facilitating a decrease of the computational cost to achieve near real-time application. We conclude that the proposed framework can potentially pave the way for employing low-cost sensors, such as those used in smartphones, attached on the upper back to provide injury related and performance feedback in real-time in unconstrained environments.

A framework for comprehensive analysis of a swing in sports using low-cost inertial sensors

We present a novel framework to monitor the three-dimensional trajectory (orientation and position) of a golf swing using miniaturized inertial sensors. Firstly we employed a highly accurate and computationally efficient revised gradient descent algorithm to obtain the orientation of a golf club. Secondly, we designed a series of digital filters to determine the backward and forward segments of the swing, enabling us to calculate drift-free linear velocity along with the relative 3D position of the golf club during the entire swing. Finally, the calculated motion trajectory was verified against a ground truth VICON system using Iterative Closest Point (ICP) in conjunction with Principal Component Analysis (PCA). The computationally efficient framework present here achieves a high level of accuracy (r = 0.9885, p <; 0.0001) for such a low-cost system. This framework can be utilized for reliable movement technique evaluation and can provide near real-time feedback for athletes in various unconstrained environments. It is envisaged that the proposed framework is applicable to other racket based sports (e.g. tennis, cricket and hurling).

3D Human Gait Reconstruction and Monitoring Using Body-Worn Inertial Sensors and Kinematic Modeling

In this paper, we present a novel low-cost computationally efficient method to accurately assess human gait by monitoring the 3D trajectory of the lower limb, both left and right legs outside the lab in any unconstrained environment. Our method utilizes a network of miniaturized wireless inertial sensors, coupled with a suite of real-time analysis algorithms and can operate in any unconstrained environment. First, we adopt a modified computationally efficient, highly accurate, and near real-time gradient descent algorithm to compute the direction of the gyroscope measurement error as a quaternion derivative in order to obtain the 3D orientation of each of the six segments. Second, by utilizing the foot sensor, we successfully detect the stance phase of the human gait cycle, which allows us to obtain drift-free velocity and the 3D position of the left and right feet during functional phases of a gait cycle. Third, by setting the foot segment as the root node we calculate the 3D orientation and position of the other two segments as well as the left and right ankle, knee, and hip joints. We then employ a customized kinematic model adjustment technique to ensure that the motion is coherent with human biomechanical behavior of the leg. Pearsons correlation coefficient (r) and significant difference test results (F) were used to quantify the relationship between the calculated and measured movements for all joints in the sagittal plane. The correlation between the calculated and the reference was found to have similar trends for all six joints (r > 0.94, p <; 0.005).

A Multi-Modal 3D Capturing Platform for Learning and Preservation of Traditional Sports and Games

We present a demonstration of a multi-modal 3D capturing platform coupled to a motion comparison system. This work is focused on the preservation of Traditional Sports and Games, namely the Gaelic sports from Ireland and Basque sports from France and Spain. Users can learn, compare and compete in the performance of sporting gestures and compare themselves to real athletes. Our online gesture database provides a way to preserve and display a wide range of sporting gestures. The capturing devices utilised are Kinect 2 sensors and wearable inertial sensors, where the number required varies based on the requested scenario. The fusion of these two capture modalities, coupled to our inverse kinematic algorithm, allow us to synthesize a fluid and reliable 3D model of the user gestures over time. Our novel comparison algorithms provide the user with a performance score and a set of comparison curves (i.e. joint angles and angular velocities), providing a precise and valuable feedback for coaches and players.

Human gait monitoring using body-worn inertial sensors and kinematic modelling

In this paper, we present a low-cost computationally efficient method to accurately assess Gait by monitoring the 3D trajectory of the lower limb (i.e. 3 segments - foot, tibia and thigh, and 2 joints - ankle and knee). Our method utilises a network of miniaturized wireless inertial sensors, coupled with a suite of sophisticated real-time analysis algorithms and can operate in any unconstrained environment. Firstly, we adopt a modified computationally-efficient, highly accurate and realtime gradient descent algorithm to obtain the 3D orientation of each of the 3 segments. Secondly, by utilising the foot sensor, we successfully detect the stance phase of the human gait cycle, which allows us to obtain drift-free velocity and the 3D position of the foot during functional phases of a gait cycle (i.e. heel strike to heel strike). Thirdly, by setting the foot segment as the root node we calculate the 3D orientation and position of the other 2 segments as well as the ankle and knee joints. Finally, we employ a customised kinematic model adjustment technique to ensure that the motion is coherent with human biomechanical behaviour of the leg. Our method is low-cost, is robust to measurement drift and can accurately monitor human gait outside the lab in any unconstrained environment.

Activity recognition of local muscular endurance (LME) exercises using an inertial sensor

In this paper, we propose an algorithmic approach for a motion analysis framework to automatically recognize local muscular endurance (LME) exercises and to count their repetitions using a wrist-worn inertial sensor. LME exercises are prescribed for cardiovascular disease rehabilitation. As a technical solution, we propose activity recognition based on machine learning. We developed an algorithm to automatically segment the captured data from all participants. Relevant time and frequency domain features were extracted using a sliding window technique. Principal component analysis (PCA) was applied for dimensionality reduction of the extracted features. We trained 15 binary classifiers using support vector machine (SVM) to recognize individual LME exercises, achieving overall accuracy of more than 98%. We applied grid search technique to obtain the optimal SVM hyperplane parameters. The learning curves (mean ± stdev) for each model is investigated to verify that the models were not over-fitted and performed well on any new test data. Also, we devised a method to count the repetitions of the upper body exercises.

Preservation and Gamification of Traditional Sports

This chapter reviews an example of preservation and gamification scenario applied to traditional sports. In the first section, we describe a preservation technique to capture intangible content. It includes character modelling, motion recording, and animation processing. The second section is focused on the gamification aspect. It describes an interactive scenario integrated in a platform that includes a multimodal capturing system, a motion comparison and analysis, and a semantic-based feedback system.