Human Detection Research Articles

Experimental implementation of skeleton tracking for collision avoidance in collaborative robotics

Collaborative robotic manipulators can stop in case of a collision, according to the ISO/TS 15066 and ISO 10218-1 standards. However, in a human-robot collaboration scenario where the robot and the human share the workspace, a better solution with concerns to production and operator safety would be to perceive in advance the presence of an obstacle and be able to avoid it, thereby completing the task without halting the robot. In this paper, an obstacle avoidance algorithm is tested using a sensor system for real-time human detection; the operator represents a potential dynamic obstacle that can interfere with the robot motion. The sensor system consists of three RGB-D cameras. A custom software framework has been developed in Python exploiting machine learning tools for human skeleton detection. The coordinates of the human body joints relative to the manipulator base are used as input to the obstacle avoidance algorithm. The use of multiple sensors makes it possible to limit the occlusion problem; in addition, the choice of non-wearable sensors goes in the direction of better operator comfort. A series of experimental tests were performed to verify the accuracy of skeleton detection and the ability of the system to avoid obstacles in real time. The human motion caption system, in particular, was validated through a comparison with a commercial system based on wearable IMU sensors widely used and validated in motion capture. There is an NRMSE of 3.23%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$3.23\\%$$\\end{document} for the RGB-D camera-based skeleton detection system, against an NRMSE of 12.23%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$12.23\\%$$\\end{document} for the IMU wearable sensor system. Test results confirm that the system is able to avoid collisions with the human body under various conditions, static or dynamic, ensuring a minimum safety distance to any part of the manipulator. In 44 tests in which the operator moves around the robot with possible collisions (at a speed typical of manufacturing operations), the minimum operator-robot distance averaged 208mm\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$208\\,\ extrm{mm}$$\\end{document}, being 200mm\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$200\\,\ extrm{mm}$$\\end{document} the limit safety distance set by algorithm.

Production and evaluation of a new set of recombinant antigens for the serological diagnosis of human cysticercosis

Human cysticercosis caused by Taenia soliun (T. soliun) is endemic in certain areas of Latin America, Asia and Sub-Saharan Africa. Neurocysticercosis (NCC) is mainly diagnosed by neuroimaging, which, in most cases, is unavailable in endemic areas. Due to their high sensitivity and specificity, serological tests such as enzyme-linked immunosorbent assay (ELISA) and Western blot (WB) based on the glycosylated fraction of the cyst CS50 are widely used for the detection of the anti-cysticercus IgG antibodies despite their significant cost and the need of cysticercus material. Given their cost-effectivess and simplicity, immunoassays based on recombinant proteins could provide new alternatives for human cysticercosis diagnosis: such tests would be aimed at screening those people living in remote areas who need further examination. To date, however, no test using recombinant antigens is commercially available.Herein, five recombinant proteins (R14, R18, R93.1, R914.1, and R915.2) were produced, three of which (R93.1, R914.1, and R915.2) were newly identified from the cyst fluid. Evaluation of the diagnostic performance of these recombinant antigens by ELISA was done using sera from 200 epileptic and non-epileptic individuals in comparison with the WB-CS50 as the reference serological method.Recombinant proteins-based ELISA showed a level of diagnostic performance that is inferior than the reference serological method, but similar to that of the native antigen ELISA for human cysticercosis (commonly used for screening). Further optimization of expression conditions is still needed in order to improve proteins solubility and enhance diagnostic performance for human cysticercosis detection. However, this preliminary evaluation of the recombinant antigens has shown their potential valuable use for screening cysticercosis in patients with epilepsy attending dispensaries in remote areas. Future studies should be conducted to evaluate our recombinant antigens in a large group of patients with different stages of NCC, and in correlation with imaging findings.

Sensitive strain sensors with wide-range detection and high stability for intelligent human motion monitoring

Miniaturized wearable electronic devices with strain sensors as core sensing elements hold significant applications in health monitoring and human-machine interaction. However, it remains a challenge to develop strain sensors with optimal response linearity, a wide detection range, and stability. In this study, to satisfy the above requirements, we construct high-performance wearable strain sensors (rGO-CNTOH@PSE) by a strategy of hybridizing conductive fillers with stretchable substrates. In detail, a synergistic conductive network is developed by adopting OH-containing carbon nanotube (CNTOH) and reduced graphene oxide (rGO) fillers with an appropriate mass ratio. After the network is integrated into a porous silicone elastomer substrate formed by the salt templating method, the developed strain sensor exhibits distinct resolution, consistent repeatability, and superior response linearity across a wide strain detection range of 0.3–303.03 %. Furthermore, the sensor also maintains good response stability over 15000 cycles of strain. We also demonstrate that this strain sensor showing outstanding exceptional detection performance has the capability for full-range human motion detection. A wireless smart electronic glove is developed based on the sensor, which can accurately recognize gesture movements and control a bionic robotic hand to replicate human hand actions, offering the potential for replacing manual tasks (such as, grasping in hazardous environments) in the future.

Convolutional Block Attention Module-Multimodal Feature-Fusion Action Recognition: Enabling Miner Unsafe Action Recognition.

The unsafe action of miners is one of the main causes of mine accidents. Research on underground miner unsafe action recognition based on computer vision enables relatively accurate real-time recognition of unsafe action among underground miners. A dataset called unsafe actions of underground miners (UAUM) was constructed and included ten categories of such actions. Underground images were enhanced using spatial- and frequency-domain enhancement algorithms. A combination of the YOLOX object detection algorithm and the Lite-HRNet human key-point detection algorithm was utilized to obtain skeleton modal data. The CBAM-PoseC3D model, a skeleton modal action-recognition model incorporating the CBAM attention module, was proposed and combined with the RGB modal feature-extraction model CBAM-SlowOnly. Ultimately, this formed the Convolutional Block Attention Module-Multimodal Feature-Fusion Action Recognition (CBAM-MFFAR) model for recognizing unsafe actions of underground miners. The improved CBAM-MFFAR model achieved a recognition accuracy of 95.8% on the NTU60 RGB+D public dataset under the X-Sub benchmark. Compared to the CBAM-PoseC3D, PoseC3D, 2S-AGCN, and ST-GCN models, the recognition accuracy was improved by 2%, 2.7%, 7.3%, and 14.3%, respectively. On the UAUM dataset, the CBAM-MFFAR model achieved a recognition accuracy of 94.6%, with improvements of 2.6%, 4%, 12%, and 17.3% compared to the CBAM-PoseC3D, PoseC3D, 2S-AGCN, and ST-GCN models, respectively. In field validation at mining sites, the CBAM-MFFAR model accurately recognized similar and multiple unsafe actions among underground miners.

Violence Detection Using Wi-Fi and 5G/6G Sensing Technologies: A Review

Violence, a pervasive societal concern, demands innovative approaches for its early detection and prevention. This review paper explores the intersection of violence detection and wireless fidelity (Wi-Fi), alongside fifth-generation (5G) and sixth-generation (6G) mobile technologies. Wi-Fi sensing, initially employed for human activity detection, has also demonstrated versatility across a number of other important applications. The significance of leveraging Wi-Fi sensing for violence detection is investigated, underscoring its ability to enhance security protocols and minimise response time. Moreover, through the development and use of machine learning algorithms to analyse and interpret intricate channel state information (CSI) features, the accuracy of violence detection can be improved. Furthermore, this investigation delves into the rapidly developing domain of mobile sensing, examining its contribution to the advancement of violence detection functionalities. The potential convergence of 5G and forthcoming 6G sensing technologies increases the effectiveness of violence detection. Through an analysis of Wi-Fi and mobile sensing technologies, this review paper highlights the transformative capacity that their integration may have on approaches to violence prevention and response.

A real-time human bone fracture detection and classification from multi-modal images using deep learning technique

A real-time human bone fracture detection and classification from multi-modal images using deep learning technique

TCFormer: Visual Recognition via Token Clustering Transformer.

Transformers are widely used in computer vision areas and have achieved remarkable success. Most state-of-the-art approaches split images into regular grids and represent each grid region with a vision token. However, fixed token distribution disregards the semantic meaning of different image regions, resulting in sub-optimal performance. To address this issue, we propose the Token Clustering Transformer (TCFormer), which generates dynamic vision tokens based on semantic meaning. Our dynamic tokens possess two crucial characteristics: (1) Representing image regions with similar semantic meanings using the same vision token, even if those regions are not adjacent, and (2) concentrating on regions with valuable details and represent them using fine tokens. Through extensive experimentation across various applications, including image classification, human pose estimation, semantic segmentation, and object detection, we demonstrate the effectiveness of our TCFormer. The code and models for this work are available at https://github.com/zengwang430521/TCFormer.

Recent Advances in Self-Powered Wearable Flexible Sensors for Human Gaits Analysis.

The rapid progress of flexible electronics has met the growing need for detecting human movement information in exoskeleton auxiliary equipment. This study provides a review of recent advancements in the design and fabrication of flexible electronics used for human motion detection. Firstly, a comprehensive introduction is provided on various self-powered wearable flexible sensors employed in detecting human movement information. Subsequently, the algorithms utilized to provide feedback on human movement are presented, followed by a thorough discussion of their methods and effectiveness. Finally, the review concludes with perspectives on the current challenges and opportunities in implementing self-powered wearable flexible sensors in exoskeleton technology.

On-Device Semi-Supervised Activity Detection: A New Privacy-Aware Personalized Health Monitoring Approach.

This paper presents an on-device semi-supervised human activity detection system that can learn and predict human activity patterns in real time. The clinical objective is to monitor and detect the unhealthy sedentary lifestyle of a user. The proposed semi-supervised learning (SSL) framework uses sparsely labelled user activity events acquired from Inertial Measurement Unit sensors installed as wearable devices. The proposed cluster-based learning model in this approach is trained with data from the same target user, thus preserving data privacy while providing personalized activity detection services. Two different cluster labelling strategies, namely, population-based and distance-based strategies, are employed to achieve the desired classification performance. The proposed system is shown to be highly accurate and computationally efficient for different algorithmic parameters, which is relevant in the context of limited computing resources on typical wearable devices. Extensive experimentation and simulation study have been conducted on multi-user human activity data from the public domain in order to analyze the trade-off between classification accuracy and computation complexity of the proposed learning paradigm with different algorithmic hyper-parameters. With 4.17 h of training time for 8000 activity episodes, the proposed SSL approach consumes at most 20 KB of CPU memory space, while providing a maximum accuracy of 90% and 100% classification rates.

Random forest based robust human activity detection system using hybrid feature

Human Activity Recognition is analyzing surveillance videos of a person’s activity. Tracking and identifying activities is essential in various applications like fight detection, mob lynching, etc. Human activity recognition may be the primary or secondary goal of a significant problem target. Surveillance for fight detection, crowd violence, public attacks, mob lynching, public robbery, etc, are few to list. The researchers are getting done in this direction, and algorithms are being proposed for automatic activity recognition. These are typically restricted to the recordings made by stationary cameras, though. For automated Human Activity Recognition, a novel skeleton-based feature called ‘Orientation Invariant Skeleton Feature (OISF)’ was introduced in the earlier work. This work uses a hybrid feature, which is a combination of ‘OISF’ features (proposed by Neelam Dwivedi et al) and ‘FV1’ features (proposed by S Kumar et al) for human activity detection systems. The hybrid features used in this paper have a low dependence on changes in camera orientation, according to experimental results. The accuracy obtained is higher than that of earlier studies using existing features and is roughly 99.50% with the ViHASi dataset and 97.25% with the KTH dataset. This demonstrates that the proposed study is suitable for commercial use.

Ultrasensitive electrospinning fibrous strain sensor with synergistic conductive network for human motion monitoring and human-computer interaction

With the rapid development of wearable electronic skin technology, flexible strain sensors have shown great application prospects in the fields of human motion and physiological signal detection, medical diagnostics, and human-computer interaction owing to their outstanding sensing performance. This paper reports a strain sensor with synergistic conductive network, consisting of stable carbon nanotube dispersion (CNT) layer and brittle MXene layer by dip-coating and electrostatic self-assembly method, and breathable three-dimensional (3D) flexible substrate of thermoplastic polyurethane (TPU) fibrous membrane prepared through electrospinning technology. The MXene/CNT@PDA-TPU (MC@p-TPU) flexible strain sensor had excellent air permeability, wide operating range (0–450 %), high sensitivity (Gauge Factor, GFmax = 8089.7), ultra-low detection limit (0.05 %), rapid response and recovery times (40 ms/60 ms), and excellent cycle stability and durability (10,000 cycles). Given its superior strain sensing capabilities, this sensor can be applied in physiological signals detection, human motion pattern recognition, and driving exoskeleton robots. In addition, MC@p-TPU fibrous membrane also exhibited excellent photothermal conversion performance and can be used as a wearable photo-heater, which has far-reaching application potential in the photothermal therapy of human joint diseases.

Research on prevention and control tracking system based on 3D face recognition

In order to improve the tracking effect of prevention and control, this paper combines three-dimensional face recognition technology and posture recognition method to build a prevention and control tracking system, and designs a single-stage human target detection and posture estimation network based on thermal infrared images. By using infrared recognition methods, the face and human body shape can be directly recognized, overcoming the problem of traditional visual recognition methods being easily occluded. The network can simultaneously complete two tasks of human target detection and pose estimation in a multi-task manner. Moreover, this paper uses the knowledge distillation strategy to train a lightweight model to further reduce the amount of model parameters to improve the inference speed. In addition, this paper uses a single-stage human target detection and posture estimation network to judge the effect of prevention and control tracking. Through the prevention and control tracking effect test, it can be seen that the prevention and control tracking system based on 3D face recognition proposed in this paper can effectively improve the prevention and control tracking effect.

REALTIME IMPLEMENTATION OF SHOULDER POSTURE DETECTION WITH COMPUTER VISION

The development of health technology is currently growing rapidly along with the needs of health workers for medical information. Computer Vision is one of the technologies used in the medical world, including the human shoulder posture detection system using the MediaPipe library. This system automatically calculates the logic of posture measurements based on the basis of manual measurements with anthropometric tools, so that health workers can easily get precise and accurate information about the results of shoulder posture detection. The system created with the Python programming language allows real-time shoulder posture detection and avoids human error. This research successfully created a human shoulder posture detection system using MediaPipe on computer vision technology to make it easier for medical personnel to get real-time measurement results.

Crack-based hydrogel strain sensors with high sensitivity and wide linear range

Recently, owing to their high sensitivity, spider-inspired crack strain sensors have received considerable attention. However, their short linear range leads to severe limitations in their application in sports health monitoring. Herein, we fabricated a cracked hydrogel strain sensor with a wide linear range using κ-carrageenan and polyacrylamide. This crack hydrogel strain sensor has a wide linear range (ε = 250 %) and excellent linearity (R2 ≈ 0.999) while ensuring high sensitivity (gauge factor GF = 2.2). Moreover, this sensor is sensitive to small vibration signals. We compared it with a traditional hydrogel strain sensor and analyzed how crack appeared. Finally, we presented the application of this sensor in human health monitoring and detection of multiaxial strains.

Electrochemiluminescence of Ultrasmall Silica Nanoparticles from Size Modulation and Multipath Surface State Adjustment for Ultrasensitive HIV-DNA Fragment Detection.

Here, ultrasmall SiO2 nanoparticles (u-SiO2 NPs, <5 nm) with obvious electrochemiluminescence (ECL) phenomenon, which was absent for conventional silica nanoparticles (c-SiO2 NPs), were reported. In a finite ultrasmall volume, the u-SiO2 NPs exhibited increasing ground state energy and higher optical absorption strength due to the electron-hole confinement model and favored catalyzing the reaction through the rapid diffusion of bulk charge, resulting in apparent ECL emission. Then, Zn2+-induced u-SiO2 nanoaggregates (Zn/u-SiO2-Ov nAGG) were synthesized and exhibited improved ECL performance via multipath surface state adjustment of u-SiO2 from several aspects, including aggregation-induced ECL, the generation of oxygen vacancy (Ov), and more positive surface charge. In addition, an ECL biosensor was constructed for ultrasensitive human immunodeficiency virus-related deoxyribonucleic acid detection from 100 aM to 1 nM with a low limit of 50.48 aM, combining the ECL luminescence of Zn/u-SiO2-Ov nAGG with three-dimensional DNA nanomachine-mediated multioutput amplification for enhanced accuracy and sensitivity compared to the single-output method. Therefore, exploring the ECL of ultrasmall nanoparticles via the adjustment of size and surface state provided a valuable indication to a wider investigation and application of novel ECL materials for clinical diagnostic.

Lightweight, robust and conductive MXene/SiO2 nanofiber aerogels for excellent sensing and thermal management properties

Flexible pressure sensors embody outstanding mechanical and sensing performance, particularly in the fields of personal health monitoring and artificial intelligence, while catering to multifunctional applications resilient against harsh weather conditions. Among these, Ti3C2Tx MXene-based aerogel materials with high surface area and excellent conductivity have attracted a lot of attention. However, there are big challenges in improving the mechanical properties at low densities and designing multi-level pore structures. Herein, the prepared silane monomers (MP) are firstly synthesized by 3-(Trimethoxysilyl) propyl methacrylate (MPTES) and polyethylene glycol diacrylate (PEGDA), then polydopamine-modified silicon dioxide (PDA-SiO2) nanofibers employed with MXene nanosheets form covalent cross-linking nanofiber aerogels. The multi-level stable structure improves both mechanical strength and elasticity. The assembled MXene/MP/PDA-SiO2 pressure sensors exhibit a high sensitivity of −0.83 kPa−1, a rapid response time of 48 ms, a minimum 1 % strain detection limit, and reliable stability over 10,000 cycles. Furthermore, these sensors can be used for human motion detection and health diagnostics, and show good personal thermal management performance. This work holds a promising candidate for the next generation of multifunctional flexible electronic devices.

A gait phase recognition method for obstacle crossing based on multi-sensor fusion

The analysis of human motion patterns and gait phase detection holds significant importance for both human motion analysis and precise control of exoskeleton devices. Presently, research on gait during obstacle crossing primarily focuses on the medical rehabilitation domain, with limited studies concerning gait phase analysis during obstacle crossing. This study conducts a detailed analysis of gait data during obstacle crossing and proposes a CNN-PCA-LSTM algorithm that fuses multi-sensor data to accurately identify gait phases when crossing obstacles in the horizontal direction. A wearable multi-sensor data acquisition system was designed, utilizing flexible capacitive pressure sensors to collect pressure data from the soles of both feet and IMUs to gather foot motion data. Kinematic simulation analyses of human obstacle-crossing motions were performed using Anybody software to determine various gait phases, validating the efficacy of the simulation model. Subsequently, one-dimensional and two-dimensional convolutional neural networks were separately employed to extract features from sole pressure data and foot motion data. Principal Component Analysis (PCA) was utilized to reduce the dimensionality of these feature datasets, which were then inputted into LSTM networks. Finally, the Softmax function was employed for the classification and recognition of gait phases when crossing obstacles in the horizontal direction. The experimental results indicate that employing the CNN-PCA-LSTM algorithm integrating multiple sensor data achieves a recognition accuracy of 97.91 % for identifying gait phases during horizontal obstacle crossing.

An Automated Framework for Human Emotion Detection From Multichannel EEG Signals

An Automated Framework for Human Emotion Detection From Multichannel EEG Signals

Self-attention CNN based indoor human events detection with UWB radar

In the era of smart homes and healthcare automation, the ability to accurately monitor and detect indoor human activities is paramount. Ultra-wideband (UWB) radar has emerged as a promising means for event detection, given its non-invasive nature and easy deployment in diverse environments. However, despite the advances in radar-based event detection, challenges remain, such as distinguishing between similar events like falls and rapid sitting. To address these challenges, for the first time, we propose an impulse radio-ultrawideband (IR-UWB) radar system to collect over ten thousand radar echo signals of eight similar actions from different angles and design a self-attention-based low-complexity convolutional neural network (CNN) model for event classification. The model leverages global correlations in radar signal spectrograms to efficiently extract features. A comparative simulation study is conducted to evaluate the detection accuracy of the proposed model and some of the existing methods based on different dataset sizes and CNN configurations. Moreover, the influence of different self-attention structures on precision and model parameter count is analyzed. Our findings reveal that the proposed self-attention-based CNN model significantly outperforms other traditional machine learning techniques while maintaining a low level computational complexity.

Development of ternary hybrid composites of transition metal and noble metal-based heterostructures: Ultrasensitive simultaneous electrochemical detection of bisphenol A and bisphenol S in food samples

Bisphenols threaten human health and sensitive detection is crucial. The present study aims to develop ternary composites of copper metal-organic framework (Cu-MOF) with AuAg microstructures. The composite structure was formed by a galvanic displacement reaction and confirmed using SEM. A binder-free catalyst was used to study the electrochemical redox reaction of bisphenol A (BPA) and bisphenol S (BPS); an irreversible cyclic voltammetric signal at +0.70 V and + 0.91 V (vs. Ag/AgCl), in the dynamic range of 20 nM to 2.0 mM, and 10 nM to 1.0 mM, with limits of detection of 2.9 nM, and 3.2 nM (S/N = 3) was obtained. Practical analysis was applied to frozen tomatoes, tuna fish, milk powder, PET bottles, raw milk, and urine samples with a recovery rate of 94.00–100.80% (n = 3). Voltammetric results were validated using HPLC detection with high precision. The sensor is a promising alternative platform for measuring BPA in food samples.