Object recognition and location has always been one of the research hotspots in machine vision.It is of great value and significance to the development and application of current service robots,industrial automation,u...Object recognition and location has always been one of the research hotspots in machine vision.It is of great value and significance to the development and application of current service robots,industrial automation,unmanned driving and other fields.In order to realize the real-time recognition and location of indoor scene objects,this article proposes an improved YOLOv3 neural network model,which combines densely connected networks and residual networks to construct a new YOLOv3 backbone network,which is applied to the detection and recognition of objects in indoor scenes.In this article,RealSense D415 RGB-D camera is used to obtain the RGB map and depth map,the actual distance value is calculated after each pixel in the scene image is mapped to the real scene.Experiment results proved that the detection and recognition accuracy and real-time performance by the new network are obviously improved compared with the previous YOLOV3 neural network model in the same scene.More objects can be detected after the improvement of network which cannot be detected with the YOLOv3 network before the improvement.The running time of objects detection and recognition is reduced to less than half of the original.This improved network has a certain reference value for practical engineering application.展开更多
To improve the accuracy and efficiency of coal-rock interface recognition,this study proposes a model built on the real-time detection algorithm,you only look once(YOLO),and the lightweight bilateral segmentation netw...To improve the accuracy and efficiency of coal-rock interface recognition,this study proposes a model built on the real-time detection algorithm,you only look once(YOLO),and the lightweight bilateral segmentation network.Simultaneously,the regional similarity transformation function and dragonfly algorithm are introduced to enhance the quality of coal-rock images.The comparison with three other models demonstrates the superior edge inference performance of the proposed model,achieving a mean Average Precision(mAP)of 90.2 at the Intersection over Union(IoU)threshold of 0.50(mAP50)and 81.4 across a range of IoU thresholds from 0.50 to 0.95(mAP[50,95]).Furthermore,to maintain high accuracy and real-time recognition capabilities,the proposed model is optimized using the open visual inference and neural network optimization toolkit,resulting in a 144.97%increase in the mean frames per second.Experimental results on four actual coal faces confirm the efficacy of the proposed model,showing a better balance between accuracy and efficiency in coal-rock image recognition,which supports further advancements in coal mining intelligence.展开更多
This study presents a hybrid CNN-Transformer model for real-time recognition of affective tactile biosignals.The proposed framework combines convolutional neural networks(CNNs)to extract spatial and local temporal fea...This study presents a hybrid CNN-Transformer model for real-time recognition of affective tactile biosignals.The proposed framework combines convolutional neural networks(CNNs)to extract spatial and local temporal features with the Transformer encoder that captures long-range dependencies in time-series data through multi-head attention.Model performance was evaluated on two widely used tactile biosignal datasets,HAART and CoST,which contain diverse affective touch gestures recorded from pressure sensor arrays.TheCNN-Transformer model achieved recognition rates of 93.33%on HAART and 80.89%on CoST,outperforming existing methods on both benchmarks.By incorporating temporal windowing,the model enables instantaneous prediction,improving generalization across gestures of varying duration.These results highlight the effectiveness of deep learning for tactile biosignal processing and demonstrate the potential of theCNN-Transformer approach for future applications in wearable sensors,affective computing,and biomedical monitoring.展开更多
The Internet of Things(IoT)and mobile technology have significantly transformed healthcare by enabling real-time monitoring and diagnosis of patients.Recognizing Medical-Related Human Activities(MRHA)is pivotal for he...The Internet of Things(IoT)and mobile technology have significantly transformed healthcare by enabling real-time monitoring and diagnosis of patients.Recognizing Medical-Related Human Activities(MRHA)is pivotal for healthcare systems,particularly for identifying actions critical to patient well-being.However,challenges such as high computational demands,low accuracy,and limited adaptability persist in Human Motion Recognition(HMR).While some studies have integrated HMR with IoT for real-time healthcare applications,limited research has focused on recognizing MRHA as essential for effective patient monitoring.This study proposes a novel HMR method tailored for MRHA detection,leveraging multi-stage deep learning techniques integrated with IoT.The approach employs EfficientNet to extract optimized spatial features from skeleton frame sequences using seven Mobile Inverted Bottleneck Convolutions(MBConv)blocks,followed by Convolutional Long Short Term Memory(ConvLSTM)to capture spatio-temporal patterns.A classification module with global average pooling,a fully connected layer,and a dropout layer generates the final predictions.The model is evaluated on the NTU RGB+D 120 and HMDB51 datasets,focusing on MRHA such as sneezing,falling,walking,sitting,etc.It achieves 94.85%accuracy for cross-subject evaluations and 96.45%for cross-view evaluations on NTU RGB+D 120,along with 89.22%accuracy on HMDB51.Additionally,the system integrates IoT capabilities using a Raspberry Pi and GSM module,delivering real-time alerts via Twilios SMS service to caregivers and patients.This scalable and efficient solution bridges the gap between HMR and IoT,advancing patient monitoring,improving healthcare outcomes,and reducing costs.展开更多
Artificial intelligence,such as deep learning technology,has advanced the study of facial expression recognition since facial expression carries rich emotional information and is significant for many naturalistic situ...Artificial intelligence,such as deep learning technology,has advanced the study of facial expression recognition since facial expression carries rich emotional information and is significant for many naturalistic situations.To pursue a high facial expression recognition accuracy,the network model of deep learning is generally designed to be very deep while the model’s real-time performance is typically constrained and limited.With MobileNetV3,a lightweight model with a good accuracy,a further study is conducted by adding a basic ResNet module to each of its existing modules and an SSH(Single Stage Headless Face Detector)context module to expand the model’s perceptual field.In this article,the enhanced model named Res-MobileNetV3,could alleviate the subpar of real-time performance and compress the size of large network models,which can process information at a rate of up to 33 frames per second.Although the improved model has been verified to be slightly inferior to the current state-of-the-art method in aspect of accuracy rate on the publically available face expression datasets,it can bring a good balance on accuracy,real-time performance,model size and model complexity in practical applications.展开更多
Automated behavior monitoring of macaques offers transformative potential for advancing biomedical research and animal welfare.However,reliably identifying individual macaques in group environments remains a significa...Automated behavior monitoring of macaques offers transformative potential for advancing biomedical research and animal welfare.However,reliably identifying individual macaques in group environments remains a significant challenge.This study introduces ACE-YOLOX,a lightweight facial recognition model tailored for captive macaques.ACE-YOLOX incorporates Efficient Channel Attention(ECA),Complete Intersection over Union loss(CIoU),and Adaptive Spatial Feature Fusion(ASFF)into the YOLOX framework,enhancing prediction accuracy while reducing computational complexity.These integrated approaches enable effective multiscale feature extraction.Using a dataset comprising 179400 labeled facial images from 1196 macaques,ACE-YOLOX surpassed the performance of classical object detection models,demonstrating superior accuracy and real-time processing capabilities.An Android application was also developed to deploy ACE-YOLOX on smartphones,enabling on-device,real-time macaque recognition.Our experimental results highlight the potential of ACE-YOLOX as a non-invasive identification tool,offering an important foundation for future studies in macaque facial expression recognition,cognitive psychology,and social behavior.展开更多
A framework of real time face tracking and recognition is presented, which integrates skin color based tracking and PCA/BPNN (principle component analysis/back propagation neural network) hybrid recognition techni...A framework of real time face tracking and recognition is presented, which integrates skin color based tracking and PCA/BPNN (principle component analysis/back propagation neural network) hybrid recognition techniques. The algorithm is able to track the human face against a complex background and also works well when temporary occlusion occurs. We also obtain a very high recognition rate by averaging a number of samples over a long image sequence. The proposed approach has been successfully tested by many experiments, and can operate at 20 frames/s on an 800 MHz PC.展开更多
Electroacoustic Tomography(EAT)is an imaging technique that detects ultrasound waves induced by electrical pulses,offering a solution for real-time electroporation monitoring.This study presents EAT system using a dua...Electroacoustic Tomography(EAT)is an imaging technique that detects ultrasound waves induced by electrical pulses,offering a solution for real-time electroporation monitoring.This study presents EAT system using a dual-frequency ultrasound array.The broadband nature of electroacoustic signals requires ultrasound detector to cover both the high-frequency range(around 6MHz)signals generated by small targets and the low-frequency range(around 1MHz)signals generated by large targets.In our EAT system,we use the 6 MHz array to detect high-frequency signals from the electrodes,and the 1 MHz array for the electrical field.To test this,we conducted simulations using COMSOL Multiphysics^(®) and MATLAB's k-Wave toolbox,followed by experiments using a custom-built setup with a dual-frequency transducer and real-time data acquisition.The results demonstrated that the dual-frequency EAT system could accurately and simultaneously monitor the electroporation process,effectively showing both the treatment area and electrode placement with the application of 1 kV electric pulses with 100 ns duration.The axial resolution of the 6MHz array for EAT was 0.45 mm,significantly better than the 2mm resolution achieved with the 1MHz array.These findings validate the potential of dual-frequency EAT as a superior method for real-time electroporation monitoring.展开更多
To investigate the energy relief effect of real-time drilling in preventing rockburst in high-stress rock,a series of high-stress real-time drilling uniaxial compression tests were conducted on red sandstone specimens...To investigate the energy relief effect of real-time drilling in preventing rockburst in high-stress rock,a series of high-stress real-time drilling uniaxial compression tests were conducted on red sandstone specimens using the SG4500 drilling rig.Results showed that the mechanical behavior(i.e.peak strength and rockburst intensity)of the rock was weakened under high-stress real-time drilling and exhibited a downward trend as the drilling diameter increased.The real-time drilling energy dissipation index(ERD)was proposed to characterize the energy relief during high-stress real-time drilling.The ERD exhibited a linear increase with the real-time drilling diameter.Furthermore,the elastic strain energy of post-drilling rock showed a linear relationship with the square of stress across different stress levels,which also applied to the peak elastic strain energy and the square of peak stress.This findingreveals the intrinsic link between the weakening effect of peak elastic strain energy and peak strength due to high-stress real-time drilling,confirmingthe consistency between energy relief and pressure relief effects.By establishing relationships among rockburst proneness,peak elastic strain energy,and peak strength,it was demonstrated that high-stress real-time drilling reduces rockburst proneness through energy dissipation.Specifically,both peak elastic strain energy and rockburst proneness decreased with larger drill bit diameters,consistent with reductions in peak strength,rockburst intensity,and fractal dimensions of high-stress real-time drilled rock.These results validate the energy relief mechanism of real-time drilling in mitigating rockburst risks.展开更多
The detection of amino acid enantiomers holds significant importance in biomedical,chemical,food,and other fields.Traditional chiral recognition methods using fluorescent probes primarily rely on fluorescence intensit...The detection of amino acid enantiomers holds significant importance in biomedical,chemical,food,and other fields.Traditional chiral recognition methods using fluorescent probes primarily rely on fluorescence intensity changes,which can compromise accuracy and repeatability.In this study,we report a novel fluorescent probe(R)-Z1 that achieves effective enantioselective recognition of chiral amino acids in water by altering emission wavelengths(>60 nm).This water-soluble probe(R)-Z1 exhibits cyan or yellow-green luminescence upon interaction with amino acid enantiomers,enabling reliable chiral detection of 14 natural amino acids.It also allows for the determination of enantiomeric excess through monitoring changes in luminescent color.Additionally,a logic operation with two inputs and three outputs was constructed based on these optical properties.Notably,amino acid enantiomers were successfully detected via dual-channel analysis at both the food and cellular levels.This study provides a new dynamic luminescence-based tool for the accurate sensing and detection of amino acid enantiomers.展开更多
Accurate and rapid recognition of weathering degree(WD)and groundwater condition(GC)is essential for evaluating rock mass quality and conducting stability analyses in underground engineering.Conventional WD and GC rec...Accurate and rapid recognition of weathering degree(WD)and groundwater condition(GC)is essential for evaluating rock mass quality and conducting stability analyses in underground engineering.Conventional WD and GC recognition methods often rely on subjective evaluation by field experts,supplemented by field sampling and laboratory testing.These methods are frequently complex and timeconsuming,making it challenging to meet the rapidly evolving demands of underground engineering.Therefore,this study proposes a rock non-geometric parameter classification network(RNPC-net)to rapidly achieve the recognition and mapping ofWD and GC of tunnel faces.The hybrid feature extraction module(HFEM)in RNPC-net can fully extract,fuse,and utilize multi-scale features of images,enhancing the network's classification performance.Moreover,the designed adaptive weighting auxiliary classifier(AC)helps the network learn features more efficiently.Experimental results show that RNPC-net achieved classification accuracies of 0.8756 and 0.8710 for WD and GC,respectively,representing an improvement of approximately 2%e10%compared to other methods.Both quantitative and qualitative experiments confirm the effectiveness and superiority of RNPC-net.Furthermore,for WD and GC mapping,RNPC-net outperformed other methods by achieving the highest mean intersection over union(mIOU)across most tunnel faces.The mapping results closely align with measurements provided by field experts.The application of WD and GC mapping results to the rock mass rating(RMR)system achieved a transition from conventional qualitative to quantitative evaluation.This advancement enables more accurate and reliable rock mass quality evaluations,particularly under critical conditions of RMR.展开更多
An image processing and deep learning method for identifying different types of rock images was proposed.Preprocessing,such as rock image acquisition,gray scaling,Gaussian blurring,and feature dimensionality reduction...An image processing and deep learning method for identifying different types of rock images was proposed.Preprocessing,such as rock image acquisition,gray scaling,Gaussian blurring,and feature dimensionality reduction,was conducted to extract useful feature information and recognize and classify rock images using Tensor Flow-based convolutional neural network(CNN)and Py Qt5.A rock image dataset was established and separated into workouts,confirmation sets,and test sets.The framework was subsequently compiled and trained.The categorization approach was evaluated using image data from the validation and test datasets,and key metrics,such as accuracy,precision,and recall,were analyzed.Finally,the classification model conducted a probabilistic analysis of the measured data to determine the equivalent lithological type for each image.The experimental results indicated that the method combining deep learning,Tensor Flow-based CNN,and Py Qt5 to recognize and classify rock images has an accuracy rate of up to 98.8%,and can be successfully utilized for rock image recognition.The system can be extended to geological exploration,mine engineering,and other rock and mineral resource development to more efficiently and accurately recognize rock samples.Moreover,it can match them with the intelligent support design system to effectively improve the reliability and economy of the support scheme.The system can serve as a reference for supporting the design of other mining and underground space projects.展开更多
Objectives This study aimed to design and evaluate a detection system for the accidental dislodgement of head-and-neck medical supplies through hand position recognition and tracking in Intensive Care Unit(ICU)patient...Objectives This study aimed to design and evaluate a detection system for the accidental dislodgement of head-and-neck medical supplies through hand position recognition and tracking in Intensive Care Unit(ICU)patients.Methods We conducted a single-center,prospective,parallel-group feasibility randomized controlled trial.We recruited 80 participants using convenience sampling from the ICU of a hospital in Ningbo City,Zhejiang Province,between March 2025 and June 2025,and they were randomly assigned to either the control group(routine care)or the intervention group(routine care plus image recognition-based detection system).The system continuously tracked patients’hand positions via bedside cameras and generated real-time alarms when hands entered predefined risk zones,notifying on-duty nurses to enable early intervention.System stability was assessed by continuous system uptime;system performance and clinical feasibility were evaluated by the frequencies of risk actions and accidental dislodgement of medical supplies(ADMS).Results All 80 participants completed the intervention,with 40 patients in each group.The baseline characteristics and median observation time of the two groups were balanced(intervention group:48 h/patient vs.control group:49 h/patient).Compared with the control group,the intervention group showed fewer ADMS(2/40 vs.9/40)and detected more risk actions per 100 h(36 vs.25);all system-detected events had corroborating images with complete concordance on manual review,and all nurse-recorded hand-contact events were accurately captured.Conclusions The study demonstrated that the image recognition-based detection system can function stably in clinical settings,providing accurate and continuous surveillance while supporting the early detection of risk actions.By reducing the observation burden and offering real-time cognitive support,the system complements routine nursing care and serves as an additional safety measure in ICU practice.With further optimization and larger multicenter validation,this approach could have the potential to make a significant contribution to the development of smart ICUs and the broader digital transformation of nursing care.展开更多
Discontinuities in rock masses critically impact the stability and safety of underground engineering.Mainstream discontinuities identificationmethods,which rely on normal vector estimation and clustering algorithms,su...Discontinuities in rock masses critically impact the stability and safety of underground engineering.Mainstream discontinuities identificationmethods,which rely on normal vector estimation and clustering algorithms,suffer from accuracy degradation,omission of critical discontinuities when orientation density is unevenly distributed,and need manual intervention.To overcome these limitations,this paper introduces a novel discontinuities identificationmethod based on geometric feature analysis of rock mass.By analyzing spatial distribution variability of point cloud and integrating an adaptive region growing algorithm,the method accurately detects independent discontinuities under complex geological conditions.Given that rock mass orientations typically follow a Fisher distribution,an adaptive hierarchical clustering algorithm based on statistical analysis is employed to automatically determine the optimal number of structural sets,eliminating the need for preset clusters or thresholds inherent in traditional methods.The proposed approach effectively handles diverse rock mass shapes and sizes,leveraging both local and global geometric features to minimize noise interference.Experimental validation on three real-world rock mass models,alongside comparisons with three conventional directional clustering algorithms,demonstrates superior accuracy and robustness in identifying optimal discontinuity sets.The proposed method offers a reliable and efficienttool for discontinuities detection and grouping in underground engineering,significantlyenhancing design and construction outcomes.展开更多
In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,...In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,existing methods face two major challenges:traditional feature engineering suffers from insufficient effective dimensionality in the feature space due to kinematic coupling,making it difficult to distinguish essential differences between maneuvers,while end-to-end deep learning models lack controllability in implicit feature learning and fail to model high-order long-range temporal dependencies.This paper proposes a trajectory feature pre-extraction method based on a Long-range Masked Autoencoder(LMAE),incorporating three key innovations:(1)Random Fragment High-ratio Masking(RFH-Mask),which enforces the model to learn long-range temporal correlations by masking 80%of trajectory data while retaining continuous fragments;(2)Kalman Filter-Guided Objective Function(KFG-OF),integrating trajectory continuity constraints to align the feature space with kinematic principles;and(3)Two-stage Decoupled Architecture,enabling efficient and controllable feature learning through unsupervised pre-training and frozen-feature transfer.Experimental results demonstrate that LMAE significantly improves the average recognition accuracy for 20-class maneuvers compared to traditional end-to-end models,while significantly accelerating convergence speed.The contributions of this work lie in:introducing high-masking-rate autoencoders into low-informationdensity trajectory analysis,proposing a feature engineering framework with enhanced controllability and efficiency,and providing a novel technical pathway for intelligent air combat decision-making systems.展开更多
Drogue recognition and 3D locating is a key problem during the docking phase of the autonomous aerial refueling （AAR）. To solve this problem, a novel and effective method based on monocular vision is presented in th...Drogue recognition and 3D locating is a key problem during the docking phase of the autonomous aerial refueling （AAR）. To solve this problem, a novel and effective method based on monocular vision is presented in this paper. Firstly, by employing computer vision with red-ring-shape feature, a drogue detection and recognition algorithm is proposed to guarantee safety and ensure the robustness to the drogue diversity and the changes in environmental condi- tions, without using a set of infrared light emitting diodes （LEDs） on the parachute part of the dro- gue. Secondly, considering camera lens distortion, a monocular vision measurement algorithm for drogue 3D locating is designed to ensure the accuracy and real-time performance of the system, with the drogue attitude provided. Finally, experiments are conducted to demonstrate the effective- ness of the proposed method. Experimental results show the performances of the entire system in contrast with other methods, which validates that the proposed method can recognize and locate the drogue three dimensionally, rapidly and precisely.展开更多
This paper proposes a data-driven method using a parametric representation of relative rotations to classify human lower-limb locomotion, which is designed for wearable robots. Three Inertial measurement units(IMUs) a...This paper proposes a data-driven method using a parametric representation of relative rotations to classify human lower-limb locomotion, which is designed for wearable robots. Three Inertial measurement units(IMUs) are mounted on the subject's waist,left knee, and right knee, respectively. Features for classification comprise relative rotations, angular velocities, and waist acceleration. Those relative rotations are represented by the exponential coordinates. The rotation matrices are normalized by Karcher mean and then the Support Vector Machine(SVM) method is used to train the data. Experiments are conducted with a time-window size of less than 40 ms. Three SVM classifiers telling 3, 5 and 6 rough lower-limb locomotion types respectively are trained, and the average accuracies are all over 98%. With the combination of those rough SVM classifiers, an easy SVMbased ensembled-system is proposed to classify 16 fine locomotion types, achieving the average accuracy of 98.22%, and its latency is 18 ms when deployed to an onboard computer.展开更多
This paper proposes a supervised classification approach for the real-time pattern recognition of sows in an animal supervision system(asup).Our approach offers the possibility of the foreground subtraction in an asup...This paper proposes a supervised classification approach for the real-time pattern recognition of sows in an animal supervision system(asup).Our approach offers the possibility of the foreground subtraction in an asup’s image processing module where there is lack of statistical information regarding the background.A set of 7 farrowing sessions of sows,during day and night,have been captured(approximately 7 days/sow),which is used for this study.The frames of these recordings have been grabbed with a time shift of 20 s.A collection of 215 frames of 7 different sows with the same lighting condition have been marked and used as the training set.Based on small neighborhoods around a point,a number of image local features are defined,and their separability and performance metrics are compared.For the classification task,a feed-forward neural network(NN)is studied and a realistic configuration in terms of an acceptable level of accuracy and computation time is chosen.The results show that the dense neighborhood feature(d.3×3)is the smallest local set of features with an acceptable level of separability,while it has no negative effect on the complexity of NN.The results also confirm that a significant amount of the desired pattern is accurately detected,even in situations where a portion of the body of a sow is covered by the crate’s elements.The performance of the proposed feature set coupled with our chosen configuration reached the rate of 8.5 fps.The true positive rate(TPR)of the classifier is 84.6%,while the false negative rate(FNR)is only about 3%.A comparison between linear logistic regression and NN shows the highly non-linear nature of our proposed set of features.展开更多
The wearable lower limb exoskeleton is a typical human-in-loop human–robot coupled system,which conducts natural and close cooperation with the human by recognizing human locomotion timely.Requiring subject-specific ...The wearable lower limb exoskeleton is a typical human-in-loop human–robot coupled system,which conducts natural and close cooperation with the human by recognizing human locomotion timely.Requiring subject-specific training is the main challenge of the existing approaches,and most methods have the problem of insufficient recognition.This paper proposes an integral subject-adaptive real-time Locomotion Mode Recognition(LMR)method based on GA-CNN for a lower limb exoskeleton system.The LMR method is a combination of Convolutional Neural Networks(CNN)and Genetic Algorithm(GA)-based multi-sensor information selection.To improve network performance,the hyper-parameters are optimized by Bayesian optimization.An exoskeleton prototype system with multi-type sensors and novel sensing-shoes is used to verify the proposed method.Twelve locomotion modes,which composed an integral locomotion system for the daily application of the exoskeleton,can be recognized by the proposed method.According to a series of experiments,the recognizer shows strong comprehensive abilities including high accuracy,low delay,and sufficient adaption to different subjects.展开更多
Over the past decade, automatic traffic accident recognition has become a prominent objective in the area of machine vision and pattern recognition because of its immense application potential in developing autonomous...Over the past decade, automatic traffic accident recognition has become a prominent objective in the area of machine vision and pattern recognition because of its immense application potential in developing autonomous Intelligent Transportation Systems (ITS). In this paper, we present a new framework toward a real-time automated recognition of traffic accident based on the Histogram of Flow Gradient (HFG) and statistical logistic regression analysis. First, optical flow is estimated and the HFG is constructed from video shots. Then vehicle patterns are clustered based on the HFG-features. By using logistic regression analysis to fit data to logistic curves, the classifier model is generated. Finally, the trajectory of the vehicle by which the accident was occasioned, is determined and recorded. The experimental results on real video sequences demonstrate the efficiency and the applicability of the framework and show it is of higher robustness and can comfortably provide latency guarantees to real-time surveillance and traffic monitoring applications.展开更多
基金supported by Henan Province Science and Technology Project under Grant No.182102210065.
文摘Object recognition and location has always been one of the research hotspots in machine vision.It is of great value and significance to the development and application of current service robots,industrial automation,unmanned driving and other fields.In order to realize the real-time recognition and location of indoor scene objects,this article proposes an improved YOLOv3 neural network model,which combines densely connected networks and residual networks to construct a new YOLOv3 backbone network,which is applied to the detection and recognition of objects in indoor scenes.In this article,RealSense D415 RGB-D camera is used to obtain the RGB map and depth map,the actual distance value is calculated after each pixel in the scene image is mapped to the real scene.Experiment results proved that the detection and recognition accuracy and real-time performance by the new network are obviously improved compared with the previous YOLOV3 neural network model in the same scene.More objects can be detected after the improvement of network which cannot be detected with the YOLOv3 network before the improvement.The running time of objects detection and recognition is reduced to less than half of the original.This improved network has a certain reference value for practical engineering application.
基金funded by the National Natural Science Foundation of China(Grant Nos.U21A20153 and 52074258)the Key Research and Development Project of Hubei Province,China(Grant No.2021BCA133)+1 种基金the Outstanding Youth Fund Program of the Natural Science Foundation of Hubei Province,China(Grant No.2022CFA084)the Wuhan Knowledge Innovation Supporting project(Grant No.2022010801010162).
文摘To improve the accuracy and efficiency of coal-rock interface recognition,this study proposes a model built on the real-time detection algorithm,you only look once(YOLO),and the lightweight bilateral segmentation network.Simultaneously,the regional similarity transformation function and dragonfly algorithm are introduced to enhance the quality of coal-rock images.The comparison with three other models demonstrates the superior edge inference performance of the proposed model,achieving a mean Average Precision(mAP)of 90.2 at the Intersection over Union(IoU)threshold of 0.50(mAP50)and 81.4 across a range of IoU thresholds from 0.50 to 0.95(mAP[50,95]).Furthermore,to maintain high accuracy and real-time recognition capabilities,the proposed model is optimized using the open visual inference and neural network optimization toolkit,resulting in a 144.97%increase in the mean frames per second.Experimental results on four actual coal faces confirm the efficacy of the proposed model,showing a better balance between accuracy and efficiency in coal-rock image recognition,which supports further advancements in coal mining intelligence.
文摘This study presents a hybrid CNN-Transformer model for real-time recognition of affective tactile biosignals.The proposed framework combines convolutional neural networks(CNNs)to extract spatial and local temporal features with the Transformer encoder that captures long-range dependencies in time-series data through multi-head attention.Model performance was evaluated on two widely used tactile biosignal datasets,HAART and CoST,which contain diverse affective touch gestures recorded from pressure sensor arrays.TheCNN-Transformer model achieved recognition rates of 93.33%on HAART and 80.89%on CoST,outperforming existing methods on both benchmarks.By incorporating temporal windowing,the model enables instantaneous prediction,improving generalization across gestures of varying duration.These results highlight the effectiveness of deep learning for tactile biosignal processing and demonstrate the potential of theCNN-Transformer approach for future applications in wearable sensors,affective computing,and biomedical monitoring.
基金funded by the ICT Division of theMinistry of Posts,Telecommunications,and Information Technology of Bangladesh under Grant Number 56.00.0000.052.33.005.21-7(Tracking No.22FS15306)support from the University of Rajshahi.
文摘The Internet of Things(IoT)and mobile technology have significantly transformed healthcare by enabling real-time monitoring and diagnosis of patients.Recognizing Medical-Related Human Activities(MRHA)is pivotal for healthcare systems,particularly for identifying actions critical to patient well-being.However,challenges such as high computational demands,low accuracy,and limited adaptability persist in Human Motion Recognition(HMR).While some studies have integrated HMR with IoT for real-time healthcare applications,limited research has focused on recognizing MRHA as essential for effective patient monitoring.This study proposes a novel HMR method tailored for MRHA detection,leveraging multi-stage deep learning techniques integrated with IoT.The approach employs EfficientNet to extract optimized spatial features from skeleton frame sequences using seven Mobile Inverted Bottleneck Convolutions(MBConv)blocks,followed by Convolutional Long Short Term Memory(ConvLSTM)to capture spatio-temporal patterns.A classification module with global average pooling,a fully connected layer,and a dropout layer generates the final predictions.The model is evaluated on the NTU RGB+D 120 and HMDB51 datasets,focusing on MRHA such as sneezing,falling,walking,sitting,etc.It achieves 94.85%accuracy for cross-subject evaluations and 96.45%for cross-view evaluations on NTU RGB+D 120,along with 89.22%accuracy on HMDB51.Additionally,the system integrates IoT capabilities using a Raspberry Pi and GSM module,delivering real-time alerts via Twilios SMS service to caregivers and patients.This scalable and efficient solution bridges the gap between HMR and IoT,advancing patient monitoring,improving healthcare outcomes,and reducing costs.
基金supported by China Academy of Railway Sciences Corporation Limited(No.2021YJ127).
文摘Artificial intelligence,such as deep learning technology,has advanced the study of facial expression recognition since facial expression carries rich emotional information and is significant for many naturalistic situations.To pursue a high facial expression recognition accuracy,the network model of deep learning is generally designed to be very deep while the model’s real-time performance is typically constrained and limited.With MobileNetV3,a lightweight model with a good accuracy,a further study is conducted by adding a basic ResNet module to each of its existing modules and an SSH(Single Stage Headless Face Detector)context module to expand the model’s perceptual field.In this article,the enhanced model named Res-MobileNetV3,could alleviate the subpar of real-time performance and compress the size of large network models,which can process information at a rate of up to 33 frames per second.Although the improved model has been verified to be slightly inferior to the current state-of-the-art method in aspect of accuracy rate on the publically available face expression datasets,it can bring a good balance on accuracy,real-time performance,model size and model complexity in practical applications.
基金supported by the grants from Yunnan Province(202305AH340006,202305AH340007)CAS Light of West China Program(xbzg-zdsys-202213)。
文摘Automated behavior monitoring of macaques offers transformative potential for advancing biomedical research and animal welfare.However,reliably identifying individual macaques in group environments remains a significant challenge.This study introduces ACE-YOLOX,a lightweight facial recognition model tailored for captive macaques.ACE-YOLOX incorporates Efficient Channel Attention(ECA),Complete Intersection over Union loss(CIoU),and Adaptive Spatial Feature Fusion(ASFF)into the YOLOX framework,enhancing prediction accuracy while reducing computational complexity.These integrated approaches enable effective multiscale feature extraction.Using a dataset comprising 179400 labeled facial images from 1196 macaques,ACE-YOLOX surpassed the performance of classical object detection models,demonstrating superior accuracy and real-time processing capabilities.An Android application was also developed to deploy ACE-YOLOX on smartphones,enabling on-device,real-time macaque recognition.Our experimental results highlight the potential of ACE-YOLOX as a non-invasive identification tool,offering an important foundation for future studies in macaque facial expression recognition,cognitive psychology,and social behavior.
文摘A framework of real time face tracking and recognition is presented, which integrates skin color based tracking and PCA/BPNN (principle component analysis/back propagation neural network) hybrid recognition techniques. The algorithm is able to track the human face against a complex background and also works well when temporary occlusion occurs. We also obtain a very high recognition rate by averaging a number of samples over a long image sequence. The proposed approach has been successfully tested by many experiments, and can operate at 20 frames/s on an 800 MHz PC.
基金supported by the National Institute of Health(R37CA240806,U01CA288351,and R50CA283816)support from UCI Chao Family Comprehensive Cancer Center(P30CA062203).
文摘Electroacoustic Tomography(EAT)is an imaging technique that detects ultrasound waves induced by electrical pulses,offering a solution for real-time electroporation monitoring.This study presents EAT system using a dual-frequency ultrasound array.The broadband nature of electroacoustic signals requires ultrasound detector to cover both the high-frequency range(around 6MHz)signals generated by small targets and the low-frequency range(around 1MHz)signals generated by large targets.In our EAT system,we use the 6 MHz array to detect high-frequency signals from the electrodes,and the 1 MHz array for the electrical field.To test this,we conducted simulations using COMSOL Multiphysics^(®) and MATLAB's k-Wave toolbox,followed by experiments using a custom-built setup with a dual-frequency transducer and real-time data acquisition.The results demonstrated that the dual-frequency EAT system could accurately and simultaneously monitor the electroporation process,effectively showing both the treatment area and electrode placement with the application of 1 kV electric pulses with 100 ns duration.The axial resolution of the 6MHz array for EAT was 0.45 mm,significantly better than the 2mm resolution achieved with the 1MHz array.These findings validate the potential of dual-frequency EAT as a superior method for real-time electroporation monitoring.
基金supported by the National Natural Science Foundation of China(Grant No.42077244)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(Grant No.KYCX24_0434).
文摘To investigate the energy relief effect of real-time drilling in preventing rockburst in high-stress rock,a series of high-stress real-time drilling uniaxial compression tests were conducted on red sandstone specimens using the SG4500 drilling rig.Results showed that the mechanical behavior(i.e.peak strength and rockburst intensity)of the rock was weakened under high-stress real-time drilling and exhibited a downward trend as the drilling diameter increased.The real-time drilling energy dissipation index(ERD)was proposed to characterize the energy relief during high-stress real-time drilling.The ERD exhibited a linear increase with the real-time drilling diameter.Furthermore,the elastic strain energy of post-drilling rock showed a linear relationship with the square of stress across different stress levels,which also applied to the peak elastic strain energy and the square of peak stress.This findingreveals the intrinsic link between the weakening effect of peak elastic strain energy and peak strength due to high-stress real-time drilling,confirmingthe consistency between energy relief and pressure relief effects.By establishing relationships among rockburst proneness,peak elastic strain energy,and peak strength,it was demonstrated that high-stress real-time drilling reduces rockburst proneness through energy dissipation.Specifically,both peak elastic strain energy and rockburst proneness decreased with larger drill bit diameters,consistent with reductions in peak strength,rockburst intensity,and fractal dimensions of high-stress real-time drilled rock.These results validate the energy relief mechanism of real-time drilling in mitigating rockburst risks.
基金the financial support from the National Natural Science Foundation of China(Nos.22377097,22307036,22074114)Natural Science Foundation of Hubei Province of China(Nos.2020CFB623,2021CFB556)Engineering Research Center of Phosphorus Resources Development and Utilization of Ministry of Education(No.LCX202305)。
文摘The detection of amino acid enantiomers holds significant importance in biomedical,chemical,food,and other fields.Traditional chiral recognition methods using fluorescent probes primarily rely on fluorescence intensity changes,which can compromise accuracy and repeatability.In this study,we report a novel fluorescent probe(R)-Z1 that achieves effective enantioselective recognition of chiral amino acids in water by altering emission wavelengths(>60 nm).This water-soluble probe(R)-Z1 exhibits cyan or yellow-green luminescence upon interaction with amino acid enantiomers,enabling reliable chiral detection of 14 natural amino acids.It also allows for the determination of enantiomeric excess through monitoring changes in luminescent color.Additionally,a logic operation with two inputs and three outputs was constructed based on these optical properties.Notably,amino acid enantiomers were successfully detected via dual-channel analysis at both the food and cellular levels.This study provides a new dynamic luminescence-based tool for the accurate sensing and detection of amino acid enantiomers.
基金supported by the National Natural Science Foundation of China(Grant Nos.42077242 and 42171407)the Graduate Innovation Fund of Jilin University.
文摘Accurate and rapid recognition of weathering degree(WD)and groundwater condition(GC)is essential for evaluating rock mass quality and conducting stability analyses in underground engineering.Conventional WD and GC recognition methods often rely on subjective evaluation by field experts,supplemented by field sampling and laboratory testing.These methods are frequently complex and timeconsuming,making it challenging to meet the rapidly evolving demands of underground engineering.Therefore,this study proposes a rock non-geometric parameter classification network(RNPC-net)to rapidly achieve the recognition and mapping ofWD and GC of tunnel faces.The hybrid feature extraction module(HFEM)in RNPC-net can fully extract,fuse,and utilize multi-scale features of images,enhancing the network's classification performance.Moreover,the designed adaptive weighting auxiliary classifier(AC)helps the network learn features more efficiently.Experimental results show that RNPC-net achieved classification accuracies of 0.8756 and 0.8710 for WD and GC,respectively,representing an improvement of approximately 2%e10%compared to other methods.Both quantitative and qualitative experiments confirm the effectiveness and superiority of RNPC-net.Furthermore,for WD and GC mapping,RNPC-net outperformed other methods by achieving the highest mean intersection over union(mIOU)across most tunnel faces.The mapping results closely align with measurements provided by field experts.The application of WD and GC mapping results to the rock mass rating(RMR)system achieved a transition from conventional qualitative to quantitative evaluation.This advancement enables more accurate and reliable rock mass quality evaluations,particularly under critical conditions of RMR.
基金financially supported by the National Science and Technology Major Project——Deep Earth Probe and Mineral Resources Exploration(No.2024ZD1003701)the National Key R&D Program of China(No.2022YFC2905004)。
文摘An image processing and deep learning method for identifying different types of rock images was proposed.Preprocessing,such as rock image acquisition,gray scaling,Gaussian blurring,and feature dimensionality reduction,was conducted to extract useful feature information and recognize and classify rock images using Tensor Flow-based convolutional neural network(CNN)and Py Qt5.A rock image dataset was established and separated into workouts,confirmation sets,and test sets.The framework was subsequently compiled and trained.The categorization approach was evaluated using image data from the validation and test datasets,and key metrics,such as accuracy,precision,and recall,were analyzed.Finally,the classification model conducted a probabilistic analysis of the measured data to determine the equivalent lithological type for each image.The experimental results indicated that the method combining deep learning,Tensor Flow-based CNN,and Py Qt5 to recognize and classify rock images has an accuracy rate of up to 98.8%,and can be successfully utilized for rock image recognition.The system can be extended to geological exploration,mine engineering,and other rock and mineral resource development to more efficiently and accurately recognize rock samples.Moreover,it can match them with the intelligent support design system to effectively improve the reliability and economy of the support scheme.The system can serve as a reference for supporting the design of other mining and underground space projects.
文摘Objectives This study aimed to design and evaluate a detection system for the accidental dislodgement of head-and-neck medical supplies through hand position recognition and tracking in Intensive Care Unit(ICU)patients.Methods We conducted a single-center,prospective,parallel-group feasibility randomized controlled trial.We recruited 80 participants using convenience sampling from the ICU of a hospital in Ningbo City,Zhejiang Province,between March 2025 and June 2025,and they were randomly assigned to either the control group(routine care)or the intervention group(routine care plus image recognition-based detection system).The system continuously tracked patients’hand positions via bedside cameras and generated real-time alarms when hands entered predefined risk zones,notifying on-duty nurses to enable early intervention.System stability was assessed by continuous system uptime;system performance and clinical feasibility were evaluated by the frequencies of risk actions and accidental dislodgement of medical supplies(ADMS).Results All 80 participants completed the intervention,with 40 patients in each group.The baseline characteristics and median observation time of the two groups were balanced(intervention group:48 h/patient vs.control group:49 h/patient).Compared with the control group,the intervention group showed fewer ADMS(2/40 vs.9/40)and detected more risk actions per 100 h(36 vs.25);all system-detected events had corroborating images with complete concordance on manual review,and all nurse-recorded hand-contact events were accurately captured.Conclusions The study demonstrated that the image recognition-based detection system can function stably in clinical settings,providing accurate and continuous surveillance while supporting the early detection of risk actions.By reducing the observation burden and offering real-time cognitive support,the system complements routine nursing care and serves as an additional safety measure in ICU practice.With further optimization and larger multicenter validation,this approach could have the potential to make a significant contribution to the development of smart ICUs and the broader digital transformation of nursing care.
基金the National Key Research and Development Program of China(Grant No.2023YFC3009400).
文摘Discontinuities in rock masses critically impact the stability and safety of underground engineering.Mainstream discontinuities identificationmethods,which rely on normal vector estimation and clustering algorithms,suffer from accuracy degradation,omission of critical discontinuities when orientation density is unevenly distributed,and need manual intervention.To overcome these limitations,this paper introduces a novel discontinuities identificationmethod based on geometric feature analysis of rock mass.By analyzing spatial distribution variability of point cloud and integrating an adaptive region growing algorithm,the method accurately detects independent discontinuities under complex geological conditions.Given that rock mass orientations typically follow a Fisher distribution,an adaptive hierarchical clustering algorithm based on statistical analysis is employed to automatically determine the optimal number of structural sets,eliminating the need for preset clusters or thresholds inherent in traditional methods.The proposed approach effectively handles diverse rock mass shapes and sizes,leveraging both local and global geometric features to minimize noise interference.Experimental validation on three real-world rock mass models,alongside comparisons with three conventional directional clustering algorithms,demonstrates superior accuracy and robustness in identifying optimal discontinuity sets.The proposed method offers a reliable and efficienttool for discontinuities detection and grouping in underground engineering,significantlyenhancing design and construction outcomes.
文摘In the field of intelligent air combat,real-time and accurate recognition of within-visual-range(WVR)maneuver actions serves as the foundational cornerstone for constructing autonomous decision-making systems.However,existing methods face two major challenges:traditional feature engineering suffers from insufficient effective dimensionality in the feature space due to kinematic coupling,making it difficult to distinguish essential differences between maneuvers,while end-to-end deep learning models lack controllability in implicit feature learning and fail to model high-order long-range temporal dependencies.This paper proposes a trajectory feature pre-extraction method based on a Long-range Masked Autoencoder(LMAE),incorporating three key innovations:(1)Random Fragment High-ratio Masking(RFH-Mask),which enforces the model to learn long-range temporal correlations by masking 80%of trajectory data while retaining continuous fragments;(2)Kalman Filter-Guided Objective Function(KFG-OF),integrating trajectory continuity constraints to align the feature space with kinematic principles;and(3)Two-stage Decoupled Architecture,enabling efficient and controllable feature learning through unsupervised pre-training and frozen-feature transfer.Experimental results demonstrate that LMAE significantly improves the average recognition accuracy for 20-class maneuvers compared to traditional end-to-end models,while significantly accelerating convergence speed.The contributions of this work lie in:introducing high-masking-rate autoencoders into low-informationdensity trajectory analysis,proposing a feature engineering framework with enhanced controllability and efficiency,and providing a novel technical pathway for intelligent air combat decision-making systems.
基金supported by the National Natural Science Foundation of China(Nos.61473307,61304120)
文摘Drogue recognition and 3D locating is a key problem during the docking phase of the autonomous aerial refueling （AAR）. To solve this problem, a novel and effective method based on monocular vision is presented in this paper. Firstly, by employing computer vision with red-ring-shape feature, a drogue detection and recognition algorithm is proposed to guarantee safety and ensure the robustness to the drogue diversity and the changes in environmental condi- tions, without using a set of infrared light emitting diodes （LEDs） on the parachute part of the dro- gue. Secondly, considering camera lens distortion, a monocular vision measurement algorithm for drogue 3D locating is designed to ensure the accuracy and real-time performance of the system, with the drogue attitude provided. Finally, experiments are conducted to demonstrate the effective- ness of the proposed method. Experimental results show the performances of the entire system in contrast with other methods, which validates that the proposed method can recognize and locate the drogue three dimensionally, rapidly and precisely.
基金supported by the National Natural Science Foundation of China (Grant No. 91948302)。
文摘This paper proposes a data-driven method using a parametric representation of relative rotations to classify human lower-limb locomotion, which is designed for wearable robots. Three Inertial measurement units(IMUs) are mounted on the subject's waist,left knee, and right knee, respectively. Features for classification comprise relative rotations, angular velocities, and waist acceleration. Those relative rotations are represented by the exponential coordinates. The rotation matrices are normalized by Karcher mean and then the Support Vector Machine(SVM) method is used to train the data. Experiments are conducted with a time-window size of less than 40 ms. Three SVM classifiers telling 3, 5 and 6 rough lower-limb locomotion types respectively are trained, and the average accuracies are all over 98%. With the combination of those rough SVM classifiers, an easy SVMbased ensembled-system is proposed to classify 16 fine locomotion types, achieving the average accuracy of 98.22%, and its latency is 18 ms when deployed to an onboard computer.
文摘This paper proposes a supervised classification approach for the real-time pattern recognition of sows in an animal supervision system(asup).Our approach offers the possibility of the foreground subtraction in an asup’s image processing module where there is lack of statistical information regarding the background.A set of 7 farrowing sessions of sows,during day and night,have been captured(approximately 7 days/sow),which is used for this study.The frames of these recordings have been grabbed with a time shift of 20 s.A collection of 215 frames of 7 different sows with the same lighting condition have been marked and used as the training set.Based on small neighborhoods around a point,a number of image local features are defined,and their separability and performance metrics are compared.For the classification task,a feed-forward neural network(NN)is studied and a realistic configuration in terms of an acceptable level of accuracy and computation time is chosen.The results show that the dense neighborhood feature(d.3×3)is the smallest local set of features with an acceptable level of separability,while it has no negative effect on the complexity of NN.The results also confirm that a significant amount of the desired pattern is accurately detected,even in situations where a portion of the body of a sow is covered by the crate’s elements.The performance of the proposed feature set coupled with our chosen configuration reached the rate of 8.5 fps.The true positive rate(TPR)of the classifier is 84.6%,while the false negative rate(FNR)is only about 3%.A comparison between linear logistic regression and NN shows the highly non-linear nature of our proposed set of features.
文摘The wearable lower limb exoskeleton is a typical human-in-loop human–robot coupled system,which conducts natural and close cooperation with the human by recognizing human locomotion timely.Requiring subject-specific training is the main challenge of the existing approaches,and most methods have the problem of insufficient recognition.This paper proposes an integral subject-adaptive real-time Locomotion Mode Recognition(LMR)method based on GA-CNN for a lower limb exoskeleton system.The LMR method is a combination of Convolutional Neural Networks(CNN)and Genetic Algorithm(GA)-based multi-sensor information selection.To improve network performance,the hyper-parameters are optimized by Bayesian optimization.An exoskeleton prototype system with multi-type sensors and novel sensing-shoes is used to verify the proposed method.Twelve locomotion modes,which composed an integral locomotion system for the daily application of the exoskeleton,can be recognized by the proposed method.According to a series of experiments,the recognizer shows strong comprehensive abilities including high accuracy,low delay,and sufficient adaption to different subjects.
文摘Over the past decade, automatic traffic accident recognition has become a prominent objective in the area of machine vision and pattern recognition because of its immense application potential in developing autonomous Intelligent Transportation Systems (ITS). In this paper, we present a new framework toward a real-time automated recognition of traffic accident based on the Histogram of Flow Gradient (HFG) and statistical logistic regression analysis. First, optical flow is estimated and the HFG is constructed from video shots. Then vehicle patterns are clustered based on the HFG-features. By using logistic regression analysis to fit data to logistic curves, the classifier model is generated. Finally, the trajectory of the vehicle by which the accident was occasioned, is determined and recorded. The experimental results on real video sequences demonstrate the efficiency and the applicability of the framework and show it is of higher robustness and can comfortably provide latency guarantees to real-time surveillance and traffic monitoring applications.
