scholarly journals 3D Reconstruction of Pedestrian Trajectory with Moving Direction Learning and Optimal Gait Recognition

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Binbin Wang ◽  
Tingli Su ◽  
Xuebo Jin ◽  
Jianlei Kong ◽  
Yuting Bai
Keyword(s):  
Learning Algorithm ◽  
Gait Recognition ◽  
Vertical Direction ◽  
Recognition Algorithm ◽  
Measurement Unit ◽  
Complex Environments ◽  
Position Change ◽  
Vertical Movements ◽  
Moving Direction ◽  
Optimal Gait

An inertial measurement unit-based pedestrian navigation system that relies on the intelligent learning algorithm is useful for various applications, especially under some severe conditions, such as the tracking of firefighters and miners. Due to the complexity of the indoor environment, signal occlusion problems could lead to the failure of certain positioning methods. In complex environments, such as those involving fire rescue and emergency rescue, the barometric altimeter fails because of the influence of air pressure and temperature. This paper used an optimal gait recognition algorithm to improve the accuracy of gait detection. Then a learning-based moving direction determination method was proposed. With the Kalman filter and a zero-velocity update algorithm, different gaits could be accurately recognized, such as going upstairs, downstairs, and walking flat. According to the recognition results, the position change in the vertical direction could be reasonably corrected. The obtained 3D trajectory involving both horizontal and vertical movements has shown that the accuracy is significantly improved in practical complex environments.

scholarly journals Personalized Human Activity Recognition Based on Integrated Wearable Sensor and Transfer Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 885 ◽  
Author(s):  
Zhongzheng Fu ◽  
Xinrun He ◽  
Enkai Wang ◽  
Jun Huo ◽  
Jian Huang ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Activity Recognition ◽  
Human Activity ◽  
Sensor Node ◽  
Learning Algorithm ◽  
Joint Probability ◽  
Human Activity Recognition ◽  
Sensor Technology ◽  
Measurement Unit ◽  
Wearable Sensor

Human activity recognition (HAR) based on the wearable device has attracted more attention from researchers with sensor technology development in recent years. However, personalized HAR requires high accuracy of recognition, while maintaining the model’s generalization capability is a major challenge in this field. This paper designed a compact wireless wearable sensor node, which combines an air pressure sensor and inertial measurement unit (IMU) to provide multi-modal information for HAR model training. To solve personalized recognition of user activities, we propose a new transfer learning algorithm, which is a joint probability domain adaptive method with improved pseudo-labels (IPL-JPDA). This method adds the improved pseudo-label strategy to the JPDA algorithm to avoid cumulative errors due to inaccurate initial pseudo-labels. In order to verify our equipment and method, we use the newly designed sensor node to collect seven daily activities of 7 subjects. Nine different HAR models are trained by traditional machine learning and transfer learning methods. The experimental results show that the multi-modal data improve the accuracy of the HAR system. The IPL-JPDA algorithm proposed in this paper has the best performance among five HAR models, and the average recognition accuracy of different subjects is 93.2%.

scholarly journals Development of an Automatic Functional Movement Screening System with Inertial Measurement Unit Sensors

2020 ◽  
Vol 11 (1) ◽  
pp. 96
Author(s):  
Wen-Lan Wu ◽  
Meng-Hua Lee ◽  
Hsiu-Tao Hsu ◽  
Wen-Hsien Ho ◽  
Jing-Min Liang
Keyword(s):  
Feature Selection ◽  
Inertial Measurement Unit ◽  
Learning Algorithm ◽  
Kappa Statistic ◽  
Weighted Kappa ◽  
Classification Model ◽  
Measurement Unit ◽  
Functional Movement ◽  
Inertial Measurement ◽  
Movement Screening

Background: In this study, an automatic scoring system for the functional movement screen (FMS) was developed. Methods: Thirty healthy adults fitted with full-body inertial measurement unit sensors completed six FMS exercises. The system recorded kinematics data, and a professional athletic trainer graded each participant. To reduce the number of input variables for the predictive model, ordinal logistic regression was used for subset feature selection. The ensemble learning algorithm AdaBoost.M1 was used to construct classifiers. Accuracy and F score were used for classification model evaluation. The consistency between automatic and manual scoring was assessed using a weighted kappa statistic. Results: When all the features were used, the predict model presented moderate to high accuracy, with kappa values between fair to very good agreement. After feature selection, model accuracy decreased about 10%, with kappa values between poor to moderate agreement. Conclusions: The results indicate that higher prediction accuracy was achieved using the full feature set compared with using the reduced feature set.

scholarly journals Ankle Angle Prediction Using a Footwear Pressure Sensor and a Machine Learning Technique

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3790
Author(s):  
Zachary Choffin ◽  
Nathan Jeong ◽  
Michael Callihan ◽  
Savannah Olmstead ◽  
Edward Sazonov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pressure Sensor ◽  
Learning Algorithm ◽  
Flexible Substrate ◽  
Ankle Injuries ◽  
Sensor System ◽  
Measurement Unit ◽  
K Nearest Neighbor ◽  
Machine Learning Technique ◽  
Learning Technique

Ankle injuries may adversely increase the risk of injury to the joints of the lower extremity and can lead to various impairments in workplaces. The purpose of this study was to predict the ankle angles by developing a footwear pressure sensor and utilizing a machine learning technique. The footwear sensor was composed of six FSRs (force sensing resistors), a microcontroller and a Bluetooth LE chipset in a flexible substrate. Twenty-six subjects were tested in squat and stoop motions, which are common positions utilized when lifting objects from the floor and pose distinct risks to the lifter. The kNN (k-nearest neighbor) machine learning algorithm was used to create a representative model to predict the ankle angles. For the validation, a commercial IMU (inertial measurement unit) sensor system was used. The results showed that the proposed footwear pressure sensor could predict the ankle angles at more than 93% accuracy for squat and 87% accuracy for stoop motions. This study confirmed that the proposed plantar sensor system is a promising tool for the prediction of ankle angles and thus may be used to prevent potential injuries while lifting objects in workplaces.

Design of Gait Recognition System Based on FPGA and DSP

2014 ◽  
Vol 687-691 ◽  
pp. 3861-3868
Author(s):  
Zheng Hong Deng ◽  
Li Tao Jiao ◽  
Li Yan Liu ◽  
Shan Shan Zhao
Keyword(s):  
Monitoring System ◽  
Nearest Neighbor ◽  
Gait Recognition ◽  
Recognition Rate ◽  
Digital Signal ◽  
Recognition System ◽  
Recognition Algorithm ◽  
Zernike Moment ◽  
Intelligent Monitoring ◽  
The One

According to the trend of the intelligent monitoring system, on the basis of the study of gait recognition algorithm, the intelligent monitoring system is designed based on FPGA and DSP; On the one hand, FPGA’s flexibility and fast parallel processing algorithms when designing can be both used to avoid that circuit can not be modified after designed; On the other hand, the advantage of processing the digital signal of DSP is fully taken. In the feature extraction and recognition, Zernike moment is selected, at the same time the system uses the nearest neighbor classification method which is more mature and has good real-time performance. Experiments show that the system has high recognition rate.

scholarly journals UAV Recognition Based on Micro-Doppler Dynamic Attribute-Guided Augmentation Algorithm

2021 ◽  
Vol 13 (6) ◽  
pp. 1205
Author(s):  
Caidan Zhao ◽  
Gege Luo ◽  
Yilin Wang ◽  
Caiyun Chen ◽  
Zhiqiang Wu
Keyword(s):  
Recognition Performance ◽  
Principal Component ◽  
Texture Features ◽  
Training Model ◽  
Recognition Algorithm ◽  
Discrete Wavelet ◽  
Dynamic Feature ◽  
Complex Environments ◽  
Time Frequency ◽  
Model Training

A micro-Doppler signature (m-DS) based on the rotation of drone blades is an effective way to detect and identify small drones. Deep-learning-based recognition algorithms can achieve higher recognition performance, but they needs a large amount of sample data to train models. In addition to the hovering state, the signal samples of small unmanned aerial vehicles (UAVs) should also include flight dynamics, such as vertical, pitch, forward and backward, roll, lateral, and yaw. However, it is difficult to collect all dynamic UAV signal samples under actual flight conditions, and these dynamic flight characteristics will lead to the deviation of the original features, thus affecting the performance of the recognizer. In this paper, we propose a small UAV m-DS recognition algorithm based on dynamic feature enhancement. We extract the combined principal component analysis and discrete wavelet transform (PCA-DWT) time–frequency characteristics and texture features of the UAV’s micro-Doppler signal and use a dynamic attribute-guided augmentation (DAGA) algorithm to expand the feature domain for model training to achieve an adaptive, accurate, and efficient multiclass recognition model in complex environments. After the training model is stable, the average recognition accuracy rate can reach 98% during dynamic flight.

scholarly journals End-Effector Pose Estimation in Complex Environments Using Complementary Enhancement and Adaptive Fusion of Multisensor

2021 ◽  
Vol 2021 ◽  
pp. 1-18
Author(s):  
Mingrui Luo ◽  
En Li ◽  
Rui Guo ◽  
Jiaxin Liu ◽  
Zize Liang
Keyword(s):  
Kalman Filter ◽  
Pose Estimation ◽  
Unscented Kalman Filter ◽  
Rbf Neural Network ◽  
Estimation Error ◽  
Estimation Method ◽  
Original Data ◽  
Measurement Unit ◽  
Complex Environments ◽  
End Effector

Redundant manipulators are suitable for working in narrow and complex environments due to their flexibility. However, a large number of joints and long slender links make it hard to obtain the accurate end-effector pose of the redundant manipulator directly through the encoders. In this paper, a pose estimation method is proposed with the fusion of vision sensors, inertial sensors, and encoders. Firstly, according to the complementary characteristics of each measurement unit in the sensors, the original data is corrected and enhanced. Furthermore, an improved Kalman filter (KF) algorithm is adopted for data fusion by establishing the nonlinear motion prediction of the end-effector and the synchronization update model of the multirate sensors. Finally, the radial basis function (RBF) neural network is used to adaptively adjust the fusion parameters. It is verified in experiments that the proposed method achieves better performances on estimation error and update frequency than the original extended Kalman filter (EKF) and unscented Kalman filter (UKF) algorithm, especially in complex environments.

scholarly journals Obtaining World Coordinate Information of UAV in GNSS Denied Environments

Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2241 ◽  
Author(s):  
Chengbin Chen ◽  
YaoYuan Tian ◽  
Liang Lin ◽  
SiFan Chen ◽  
HanWen Li ◽  
...  
Keyword(s):  
Visual Servoing ◽  
Field Tests ◽  
Visual Navigation ◽  
Sensor Data ◽  
Measurement Unit ◽  
Navigation Systems ◽  
Complex Environments ◽  
External Interference ◽  
Position Information ◽  
Self Powered

GNSS information is vulnerable to external interference and causes failure when unmanned aerial vehicles (UAVs) are in a fully autonomous flight in complex environments such as high-rise parks and dense forests. This paper presents a pan-tilt-based visual servoing (PBVS) method for obtaining world coordinate information. The system is equipped with an inertial measurement unit (IMU), an air pressure sensor, a magnetometer, and a pan-tilt-zoom (PTZ) camera. In this paper, we explain the physical model and the application method of the PBVS system, which can be briefly summarized as follows. We track the operation target with a UAV carrying a camera and output the information about the UAV’s position and the angle between the PTZ and the anchor point. In this way, we can obtain the current absolute position information of the UAV with its absolute altitude collected by the height sensing unit and absolute geographic coordinate information and altitude information of the tracked target. We set up an actual UAV experimental environment. To meet the calculation requirements, some sensor data will be sent to the cloud through the network. Through the field tests, it can be concluded that the systematic deviation of the overall solution is less than the error of GNSS sensor equipment, and it can provide navigation coordinate information for the UAV in complex environments. Compared with traditional visual navigation systems, our scheme has the advantage of obtaining absolute, continuous, accurate, and efficient navigation information at a short distance (within 15 m from the target). This system can be used in scenarios that require autonomous cruise, such as self-powered inspections of UAVs, patrols in parks, etc.

Deep Plane Facelift: An Evaluation of the High-SMAS versus Standard Incision Points

2018 ◽  
Vol 34 (06) ◽  
pp. 646-650
Author(s):  
Chiara Amodeo ◽  
Vishad Nabili ◽  
Gregory Keller ◽  
Jordan Sand
Keyword(s):  
Skin Flap ◽  
Vertical Direction ◽  
Senior Author ◽  
Entry Point ◽  
Face Lift ◽  
Vertical Movements ◽  
Plane Face ◽  
Superficial Musculoaponeurotic System ◽  
Entry Points ◽  
Tissue Movement

AbstractIn surgery of the aging face, operative adjustments of the superficial musculoaponeurotic system (SMAS) enhance facial contours. The senior author has observed that the standard deep plane face lift entry points on the SMAS do not provide as much tissue movement in a vertical direction as high-SMAS deep plane face lift entry points. In this study, tissue movement was measured comparing the conventional SMAS entry point with a high-SMAS entry point for deep plane face lifts. Institutional review board approval was obtained. Fourteen facelift patients were enrolled, 10 female and 4 male. Average age was 63.4 (50–81) years. Tissue movement at three points along the jaw line was measured intraoperatively. Standard SMAS entry point suspension resulted in average vertical movements of 6.4, 10.3, and 13.8 mm and average horizontal movements of 3.5, 5.7, and 6.5 mm. High-SMAS entry point resulted in average vertical movements of 11.8, 17.9, and 24.1 mm and average horizontal movements of 5.8, 9.8, and 9.9 mm. This resulted in a 77.3% increase (p = 0.03) in vertical movement and a 61.4% increase (p = 0.02) in horizontal movement with a high-SMAS entry compared with standard SMAS entry. The high-SMAS entry point for a deep plane facelift resulted in a significant increase in lift for both the horizontal and vertical vector on the facial skin flap when compared with the conventional entry.

Fatigue-Related Changes in Running Gait Patterns Persist in the Days Following a Marathon Race

2020 ◽  
Vol 29 (7) ◽  
pp. 934-941 ◽  
Author(s):  
Christian A. Clermont ◽  
Andrew J. Pohl ◽  
Reed Ferber
Keyword(s):  
Musculoskeletal Pain ◽  
Center Of Mass ◽  
Vertical Direction ◽  
Measurement Unit ◽  
Post Intervention ◽  
Marathon Runners ◽  
Gait Patterns ◽  
Marathon Race ◽  
Track Surface ◽  
Running Biomechanics

Context: The risk of experiencing an overuse running-related injury can increase with atypical running biomechanics associated with neuromuscular fatigue and/or training errors. While it is important to understand the changes in running biomechanics within a fatigue-inducing run, it may be more clinically relevant to assess gait patterns in the days following a marathon to better evaluate the effects of inadequate recovery on injury. Objective: To use center of mass (CoM) acceleration patterns to investigate changes in running patterns prior to (PRE) and at 2 (POST2) and 7 (POST7) days following a marathon race. Design: Pre–post intervention study. Setting: A 200-m oval track surface. Participants: Seventeen recreational marathon runners (10 females, age = 34.2 [5.67] y; 7 males, age = 47.41 [15.32] y). Intervention: Marathon race. Main Outcome Measures: An inertial measurement unit was placed near the CoM to collect triaxial acceleration data during overground running for PRE, POST2, and POST7 sessions. Twenty-two features were extracted from the acceleration waveforms to characterize different aspects of running gait. Lower-limb musculoskeletal pain was also recorded at each session with a visual analog scale. Results: At POST2, runners reported higher self-reported pain and exhibited elevated peak mediolateral acceleration with an increased mediolateral ratio of acceleration root mean square compared with PRE. At POST7, pain was reduced and more similar to PRE, with runners demonstrating increased stride regularity in the vertical direction and decreased peak resultant acceleration. Conclusions: The observed changes in CoM motion at POST2 may be associated with atypical running biomechanics that can translate to greater mediolateral impulses, potentially increasing the risk of injury. This study demonstrates the use of an accelerometer as an effective tool to detect atypical CoM motion for runners due to fatigue, recovery, and musculoskeletal pain in real-world environments.

scholarly journals Recurrent Neural Network for Inertial Gait User Recognition in Smartphones

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 4054 ◽  
Author(s):  
Fernandez-Lopez ◽  
Liu-Jimenez ◽  
Kiyokawa ◽  
Wu
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Inertial Sensors ◽  
Selection Process ◽  
Gait Recognition ◽  
Recognition Algorithm ◽  
Tuning Method ◽  
Random Grid ◽  
Hyperparameter Selection ◽  
User Recognition

In this article, a gait recognition algorithm is presented based on the information obtained from inertial sensors embedded in a smartphone, in particular, the accelerometers and gyroscopes typically embedded on them. The algorithm processes the signal by extracting gait cycles, which are then fed into a Recurrent Neural Network (RNN) to generate feature vectors. To optimize the accuracy of this algorithm, we apply a random grid hyperparameter selection process followed by a hand-tuning method to reach the final hyperparameter configuration. The different configurations are tested on a public database with 744 users and compared with other algorithms that were previously tested on the same database. After reaching the best-performing configuration for our algorithm, we obtain an equal error rate (EER) of 11.48% when training with only 20% of the users. Even better, when using 70% of the users for training, that value drops to 7.55%. The system manages to improve on state-of-the-art methods, but we believe the algorithm could reach a significantly better performance if it was trained with more visits per user. With a large enough database with several visits per user, the algorithm could improve substantially.

Sign in / Sign up

Export Citation Format

Share Document