A New Dataset of People Flow in an Industrial Site with UWB and Motion Capture Systems

Robust IMU-Based Mitigation of Human Body Shadowing in UWB Indoor Positioning

Ultra-wideband (UWB) indoor positioning systems have the potential to achieve sub-decimeter-level accuracy. However, the ranging performance degrades significantly under non-line-of-sight (NLoS) conditions. The detection and mitigation of NLoS conditions is a complex problem and has been the subject of many works over the past decades. When localizing pedestrians, human body shadowing (HBS) is a particular and specific cause of NLoS. In this paper, we present an HBS mitigation strategy based on the orientation of the body and tag relative to the UWB anchors. Our HBS mitigation strategy involves a robust range error model that interacts with a tracking algorithm. The model consists of a bank of Gaussian Mixture Models (GMMs), from which an appropriate GMM is selected based on the relative body-tag-anchor orientation. The relative orientation is estimated by means of an inertial measurement unit (IMU) attached to the tag and a candidate position provided by the tracking algorithm. The selected GMM is used as a likelihood function for the tracking algorithm to improve localization accuracy. Our proposed approach was realized for two tracking algorithms. We validated the implemented algorithms on dynamic UWB ranging measurements, which were performed in an industrial lab environment. The proposed algorithms outperform other state-of-the-art algorithms, achieving a 37% reduction of the p75 error.

Examination of the Accuracy of Movement Tracking Systems for Monitoring Exercise for Musculoskeletal Rehabilitation

When patients perform musculoskeletal rehabilitation exercises, it is of great importance to observe the correctness of their performance. The aim of this study is to increase the accuracy of recognizing human movements during exercise. The process of monitoring and evaluating musculoskeletal rehabilitation exercises was modeled using various tracking systems, and the necessary algorithms for processing information for each of the tracking systems were formalized. An approach to classifying exercises using machine learning methods is presented. Experimental studies were conducted to identify the most accurate tracking systems (virtual reality trackers, motion capture, and computer vision). A comparison of machine learning models is carried out to solve the problem of classifying musculoskeletal rehabilitation exercises, and 96% accuracy is obtained when using multilayer dense neural networks. With the use of computer vision technologies and the processing of a full set of body points, the accuracy of classification achieved is 100%. The hypotheses on the ranking of tracking systems based on the accuracy of positioning of human target points, the presence of restrictions on application in the field of musculoskeletal rehabilitation, and the potential to classify exercises are fully confirmed.

Using Worker Position Data for Human-Driven Decision Support in Labour-Intensive Manufacturing

This paper provides a novel methodology for human-driven decision support for capacity allocation in labour-intensive manufacturing systems. In such systems (where output depends solely on human labour) it is essential that any changes aimed at improving productivity are informed by the workers' actual working practices, rather than attempting to implement strategies based on an idealised representation of a theoretical production process. This paper reports how worker position data (obtained by localisation sensors) can be used as input to process mining algorithms to generate a data-driven process model to understand how manufacturing tasks are actually performed and how this model can then be used to build a discrete event simulation to investigate the performance of capacity allocation adjustments made to the original working practice observed in the data. The proposed methodology is demonstrated using a real-world dataset generated by a manual assembly line involving six workers performing six manufacturing tasks. It is found that, with small capacity adjustments, one can reduce the completion time by 7% (i.e., without requiring any additional workers), and with an additional worker a 16% reduction in completion time can be achieved by increasing the capacity of the bottleneck tasks which take relatively longer time than others.

The State-of-the-Art Sensing Techniques in Human Activity Recognition: A Survey

Human activity recognition (HAR) has become an intensive research topic in the past decade because of the pervasive user scenarios and the overwhelming development of advanced algorithms and novel sensing approaches. Previous HAR-related sensing surveys were primarily focused on either a specific branch such as wearable sensing and video-based sensing or a full-stack presentation of both sensing and data processing techniques, resulting in weak focus on HAR-related sensing techniques. This work tries to present a thorough, in-depth survey on the state-of-the-art sensing modalities in HAR tasks to supply a solid understanding of the variant sensing principles for younger researchers of the community. First, we categorized the HAR-related sensing modalities into five classes: mechanical kinematic sensing, field-based sensing, wave-based sensing, physiological sensing, and hybrid/others. Specific sensing modalities are then presented in each category, and a thorough description of the sensing tricks and the latest related works were given. We also discussed the strengths and weaknesses of each modality across the categorization so that newcomers could have a better overview of the characteristics of each sensing modality for HAR tasks and choose the proper approaches for their specific application. Finally, we summarized the presented sensing techniques with a comparison concerning selected performance metrics and proposed a few outlooks on the future sensing techniques used for HAR tasks.

Hybrid Approach for Indoor Localization Using Received Signal Strength of Dual-Band Wi-Fi

In this paper, we propose a hybrid localization algorithm to boost the accuracy of range-based localization by improving the ranging accuracy under indoor non-line-of-sight (NLOS) conditions. We replaced the ranging part of the rule-based localization method with a deep regression model that uses data-driven learning with dual-band received signal strength (RSS). The ranging error caused by the NLOS conditions was effectively reduced by using the deep regression method. As a consequence, the positioning error could be reduced under NLOS conditions. The performance of the proposed method was verified through a ray-tracing-based simulation for indoor spaces. The proposed scheme showed a reduction in the positioning error of at least 22.3% in terms of the median root mean square error compared to the existing methods. In addition, we verified that the proposed method was robust to changes in the indoor structure.

Distance Measurements in UWB-Radio Localization Systems Corrected with a Feedforward Neural Network Model

An ultra-wideband (UWB) localization system is an alternative in a GPS-denied environment. However, a distance measurement with UWB modules using a two-way communication protocol induces an orientation-dependent error. Previous research studied this error by looking at parameters such as the received power and the channel response signal. In this paper, the neural network (NN) method for correcting the orientation-induced distance error without the need to calculate the signal strength, obtain the channel response or know any parameters of the antenna and the UWB modules is presented. The NN method utilizes only the measured distance and the tag orientation, and implements an NN model obtained by machine learning, using measurements at different distances and orientations of the two UWB modules. The verification of the experimental setup with 12 anchors and a tag shows that with the proposed NN method, 5 cm better root mean square error values (RMSEs) are obtained for the measured distance between the anchors and the tag compared to the calibration method that did not include orientation information. With the least-square estimator, 14 cm RMSE in 3D is obtained with the NN model corrected distances, with a 9 cm improvement compared to when raw distances are used. The method produces better results without the need to obtain the UWB module’s diagnostics parameters that are required to calculate the received signal strength or channel response, and in this way maintain the minimum packet size for the ranging protocol.