A common but flawed design in existing CNN architectures is using strided convolutions and/or pooling layer,which will result in the loss of fine-grained feature information,especially for low-resolution images and sm...A common but flawed design in existing CNN architectures is using strided convolutions and/or pooling layer,which will result in the loss of fine-grained feature information,especially for low-resolution images and small objects.In this paper,a new CNN building block named SPD-Conv was used,which completely eliminated stride and pooling operations and replaced them with a space-to-depth convolution and a non-strided convolution.Such new design has the advantage of downsampling feature maps while retaining discriminant feature information.It also represents a general unified method,which can be easily applied to any CNN architectures,and can also be applied to strided conversion and pooling in the same way.展开更多
The aerial deployment method enables Unmanned Aerial Vehicles(UAVs)to be directly positioned at the required altitude for their mission.This method typically employs folding technology to improve loading efficiency,wi...The aerial deployment method enables Unmanned Aerial Vehicles(UAVs)to be directly positioned at the required altitude for their mission.This method typically employs folding technology to improve loading efficiency,with applications such as the gravity-only aerial deployment of high-aspect-ratio solar-powered UAVs,and aerial takeoff of fixed-wing drones in Mars research.However,the significant morphological changes during deployment are accompanied by strong nonlinear dynamic aerodynamic forces,which result in multiple degrees of freedom and an unstable character.This hinders the description and analysis of unknown dynamic behaviors,further leading to difficulties in the design of deployment strategies and flight control.To address this issue,this paper proposes an analysis method for dynamic behaviors during aerial deployment based on the Variational Autoencoder(VAE).Focusing on the gravity-only deployment problem of highaspect-ratio foldable-wing UAVs,the method encodes the multi-degree-of-freedom unstable motion signals into a low-dimensional feature space through a data-driven approach.By clustering in the feature space,this paper identifies and studies several dynamic behaviors during aerial deployment.The research presented in this paper offers a new method and perspective for feature extraction and analysis of complex and difficult-to-describe extreme flight dynamics,guiding the research on aerial deployment drones design and control strategies.展开更多
Frequency-modulated continuous-wave radar enables the non-contact and privacy-preserving recognition of human behavior.However,the accuracy of behavior recognition is directly influenced by the spatial relationship be...Frequency-modulated continuous-wave radar enables the non-contact and privacy-preserving recognition of human behavior.However,the accuracy of behavior recognition is directly influenced by the spatial relationship between human posture and the radar.To address the issue of low accuracy in behavior recognition when the human body is not directly facing the radar,a method combining local outlier factor with Doppler information is proposed for the correction of multi-classifier recognition results.Initially,the information such as distance,velocity,and micro-Doppler spectrogram of the target is obtained using the fast Fourier transform and histogram of oriented gradients-support vector machine methods,followed by preliminary recognition.Subsequently,Platt scaling is employed to transform recognition results into confidence scores,and finally,the Doppler-local outlier factor method is utilized to calibrate the confidence scores,with the highest confidence classifier result considered as the recognition outcome.Experimental results demonstrate that this approach achieves an average recognition accuracy of 96.23%for comprehensive human behavior recognition in various orientations.展开更多
Social media rumors not only affect the health of online social networks,but also reduce the quality of information accessed by its users.In the case of emergencies,the rapid spread of rumors often triggers mass anxie...Social media rumors not only affect the health of online social networks,but also reduce the quality of information accessed by its users.In the case of emergencies,the rapid spread of rumors often triggers mass anxiety and panic.This study integrates the planned behavior(TPB)and deterrence(TD)theories to study the factors affecting the rumor recognition behavior of social media users.The structural equation model(SEM)method is used to test the proposed model.Further,the interaction between various factors is analyzed to evaluate their impact on the rumor recognition behavior exhibited by social media users in emergencies.The results demonstrate that certainty and severity have significant positive effects on subjective norms.In addition,subjective norms,attitude,and perceived behavioral control all affect the rumor recognition behavior of social media users,and involvement negatively moderates the relationship between the subjective norms and attitude.Finally,insights into the formulation of rumor control strategies during emergencies are presented based on the empirical analysis.展开更多
Communication behavior recognition is an issue with increasingly importance in the antiterrorism and national defense area.However,the sensing data obtained in actual environment is often not sufficient to accurately ...Communication behavior recognition is an issue with increasingly importance in the antiterrorism and national defense area.However,the sensing data obtained in actual environment is often not sufficient to accurately analyze the communication behavior.Traditional means can hardly utilize the scarce and crude spectrum sensing data captured in a real scene.Thus,communication behavior recognition using raw sensing data under smallsample condition has become a new challenge.In this paper,a data enhanced communication behavior recognition(DECBR)scheme is proposed to meet this challenge.Firstly,a preprocessing method is designed to make the raw spectrum data suitable for the proposed scheme.Then,an adaptive convolutional neural network structure is exploited to carry out communication behavior recognition.Moreover,DCGAN is applied to support data enhancement,which realize communication behavior recognition under small-sample condition.Finally,the scheme is verified by experiments under different data size.The results show that the DECBR scheme can greatly improve the accuracy and efficiency of behavior recognition under smallsample condition.展开更多
The core technology in an intelligent video surveillance system is that detecting and recognizing abnormal behaviors timely and accurately.The key breakthrough point in recognizing abnormal behaviors is how to obtain ...The core technology in an intelligent video surveillance system is that detecting and recognizing abnormal behaviors timely and accurately.The key breakthrough point in recognizing abnormal behaviors is how to obtain the effective features of the picture,so as to solve the problem of recognizing them.In response to this difficulty,this paper introduces an adjustable jump link coefficients model based on the residual network.The effective coefficients for each layer of the network can be set after using this model to further improving the recognition accuracy of abnormal behavior.A convolution kernel of 1×1 size is added to reduce the number of parameters for the purpose of improving the speed of the model in this paper.In order to reduce the noise of the data edge,and at the same time,improve the accuracy of the data and speed up the training,a BN(Batch Normalization)layer is added before the activation function in this network.This paper trains this network model on the public ImageNet dataset,and then uses the transfer learning method to recognize these abnormal behaviors of human in the UTI behavior dataset processed by the YOLO_v3 target detection network.Under the same experimental conditions,compared with the original ResNet-50 model,the improved model in this paper has a 2.8%higher accuracy in recognition of abnormal behaviors on the public UTI dataset.展开更多
With the intensifying aging of the population,the phenomenon of the elderly living alone is also increasing.Therefore,using modern internet of things technology to monitor the daily behavior of the elderly in indoors ...With the intensifying aging of the population,the phenomenon of the elderly living alone is also increasing.Therefore,using modern internet of things technology to monitor the daily behavior of the elderly in indoors is a meaningful study.Video-based action recognition tasks are easily affected by object occlusion and weak ambient light,resulting in poor recognition performance.Therefore,this paper proposes an indoor human behavior recognition method based on wireless fidelity(Wi-Fi)perception and video feature fusion by utilizing the ability of Wi-Fi signals to carry environmental information during the propagation process.This paper uses the public WiFi-based activity recognition dataset(WIAR)containing Wi-Fi channel state information and essential action videos,and then extracts video feature vectors and Wi-Fi signal feature vectors in the datasets through the two-stream convolutional neural network and standard statistical algorithms,respectively.Then the two sets of feature vectors are fused,and finally,the action classification and recognition are performed by the support vector machine(SVM).The experiments in this paper contrast experiments between the two-stream network model and the methods in this paper under three different environments.And the accuracy of action recognition after adding Wi-Fi signal feature fusion is improved by 10%on average.展开更多
In order to effectively solve the problems of low accuracy and large amount of calculation of current human behavior recognition,a behavior recognition algorithm based on squeeze-and-excitation network(SENet) combined...In order to effectively solve the problems of low accuracy and large amount of calculation of current human behavior recognition,a behavior recognition algorithm based on squeeze-and-excitation network(SENet) combined with 3 D Inception network(I3 D) and gated recurrent unit(GRU) network is proposed.The algorithm first expands the Inception module to three-dimensional,and builds a network based on the three-dimensional module,and expands SENet to three-dimensional,making it an attention mechanism that can pay attention to the three-dimensional channel.Then SENet is introduced into the 13 D network,named SE-I3 D,and SENet is introduced into the CRU network,named SE-GRU.And,SE-13 D and SE-GRU are merged,named SE-13 D-GRU.Finally,the network uses Softmax to classify the results in the UCF-101 dataset.The experimental results show that the SE-I3 D-GRU network achieves a recognition rate of 93.2% on the UCF-101 dataset.展开更多
In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dime...In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dimensional batch normalization visual geometry group(3D-BN-VGG)and long short-term memory(LSTM)network is designed.In this network,3D convolutional layer is used to extract the spatial domain features and time domain features of video sequence at the same time,multiple small convolution kernels are stacked to replace large convolution kernels,thus the depth of neural network is deepened and the number of network parameters is reduced.In addition,the latest batch normalization algorithm is added to the 3-dimensional convolutional network to improve the training speed.Then the output of the full connection layer is sent to LSTM network as the feature vectors to extract the sequence information.This method,which directly uses the output of the whole base level without passing through the full connection layer,reduces the parameters of the whole fusion network to 15324485,nearly twice as much as those of 3D-BN-VGG.Finally,it reveals that the proposed network achieves 96.5%and 74.9%accuracy in the UCF-101 and HMDB-51 respectively,and the algorithm has a calculation speed of 1066 fps and an acceleration ratio of 1,which has a significant predominance in velocity.展开更多
In the process of human behavior recognition, the traditional dense optical flow method has too many pixels and too much overhead, which limits the running speed. This paper proposed a method combing YOLOv3 (You Only ...In the process of human behavior recognition, the traditional dense optical flow method has too many pixels and too much overhead, which limits the running speed. This paper proposed a method combing YOLOv3 (You Only Look Once v3) and local optical flow method. Based on the dense optical flow method, the optical flow modulus of the area where the human target is detected is calculated to reduce the amount of computation and save the cost in terms of time. And then, a threshold value is set to complete the human behavior identification. Through design algorithm, experimental verification and other steps, the walking, running and falling state of human body in real life indoor sports video was identified. Experimental results show that this algorithm is more advantageous for jogging behavior recognition.展开更多
Building indoor dangerous behavior recognition is a specific application in the field of abnormal human recognition.A human dangerous behavior recognition method based on LSTM-GCN with attention mechanism(GLA)model wa...Building indoor dangerous behavior recognition is a specific application in the field of abnormal human recognition.A human dangerous behavior recognition method based on LSTM-GCN with attention mechanism(GLA)model was proposed aiming at the problem that the existing human skeleton-based action recognition methods cannot fully extract the temporal and spatial features.The network connects GCN and LSTMnetwork in series,and inputs the skeleton sequence extracted by GCN that contains spatial information into the LSTM layer for time sequence feature extraction,which fully excavates the temporal and spatial features of the skeleton sequence.Finally,an attention layer is designed to enhance the features of key bone points,and Softmax is used to classify and identify dangerous behaviors.The dangerous behavior datasets are derived from NTU-RGB+D and Kinetics data sets.Experimental results show that the proposed method can effectively identify some dangerous behaviors in the building,and its accuracy is higher than those of other similar methods.展开更多
Compared with RGB videos and images,human bone data is less vulnerable to external factors and has stronger robustness.Therefore,behavior recognition methods based on skeletons are widely studied.Because graph convolu...Compared with RGB videos and images,human bone data is less vulnerable to external factors and has stronger robustness.Therefore,behavior recognition methods based on skeletons are widely studied.Because graph convolution network(GCN)can deal with the irregular topology data of hu-man skeletons very well,more and more researchers apply GCN to human behavior recognition.Tra-ditional graph convolution methods only consider the joints with physical connectivity or the same type when building the behavior recognition model based on human skeletons structure,which cannot capture higher-order information better.To solve this problem,Motif-GCN is used in this paper to ex-tract spatial features.The relationship between the joints with natural connection in the human body is encoded by the first Motif-GCN,and the possible relationship between the unconnected joints in the human skeleton is encoded by the second Motif-GCN.In this way,the relationship between non-physical joints can be strengthened.Then a two stream framework combining joint and bone informa-tion is used to capture more action information.Finally,experiments are conducted on two subdata-sets X-Sub and X-View of NTU-RGB+D,and the accuracy shown in Top-1 classification results is 89.5%and 95.4%respectively.The experimental results are 1.0%and 0.3%higher than those of the 2S-AGCN model respectively.The superiority of this method is also proved by the experimental results.展开更多
Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the...Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the residual module is extended to three dimensions,which can extract features in the time and space domain at the same time.Second,by changing the size of the pooling layer window the integrity of the time domain features is preserved,at the same time,in order to overcome the difficulty of network training and over-fitting problems,the batch normalization(BN)layer and the dropout layer are added.After that,because the global average pooling layer(GAP)is affected by the size of the feature map,the network cannot be further deepened,so the convolution layer and maxpool layer are added to the R3D network.Finally,because LSTM has the ability to memorize information and can extract more abstract timing features,the LSTM network is introduced into the R3D network.Experimental results show that the R3D+LSTM network achieves 91%recognition rate on the UCF-101 dataset.展开更多
Recently,human healthcare from body sensor data has gained considerable interest from a wide variety of human-computer communication and pattern analysis research owing to their real-time applications namely smart hea...Recently,human healthcare from body sensor data has gained considerable interest from a wide variety of human-computer communication and pattern analysis research owing to their real-time applications namely smart healthcare systems.Even though there are various forms of utilizing distributed sensors to monitor the behavior of people and vital signs,physical human action recognition(HAR)through body sensors gives useful information about the lifestyle and functionality of an individual.This article concentrates on the design of an Improved Transient Search Optimization with Machine Learning based BehaviorRecognition(ITSOMLBR)technique using body sensor data.The presented ITSOML-BR technique collects data from different body sensors namely electrocardiography(ECG),accelerometer,and magnetometer.In addition,the ITSOML-BR technique extract features like variance,mean,skewness,and standard deviation.Moreover,the presented ITSOML-BR technique executes a micro neural network(MNN)which can be employed for long term healthcare monitoring and classification.Furthermore,the parameters related to the MNN model are optimally selected via the ITSO algorithm.The experimental result analysis of the ITSOML-BR technique is tested on the MHEALTH dataset.The comprehensive comparison study reported a higher result for the ITSOMLBR approach over other existing approaches with maximum accuracy of 99.60%.展开更多
User behavior prediction has become a core element to Internet of Things(IoT)and received promising attention in the related fields.Many existing IoT systems(e.g.smart home systems)have been deployed various sensors a...User behavior prediction has become a core element to Internet of Things(IoT)and received promising attention in the related fields.Many existing IoT systems(e.g.smart home systems)have been deployed various sensors and the user’s behavior can be predicted through the sensor data.However,most of the existing sensor-based systems use the annotated behavior data which requires human intervention to achieve the behavior prediction.Therefore,it is a challenge to provide an automatic behavior prediction model based on the original sensor data.To solve the problem,this paper proposed a novel automatic annotated user behavior prediction(AAUBP)model.The proposed AAUBP model combined the Discontinuous Solving Order Sequence Mining(DVSM)behavior recognition model and behavior prediction model based on the Long Short Term Memory(LSTM)network.To evaluate the model,we performed several experiments on a real-world dataset tuning the parameters.The results showed that the AAUBP model can effectively recognize behaviors and had a good performance for behavior prediction.展开更多
This paper proposes the research on human body behavior recognition based on vision. Behavior based on high-level human structure can describe behavior more accurately, but it is dif？ cult to extract the behavioral c...This paper proposes the research on human body behavior recognition based on vision. Behavior based on high-level human structure can describe behavior more accurately, but it is dif？ cult to extract the behavioral characteristics while often relying on the accuracy of the human pose estimation. Moving object extraction of the moving targets in video analysis as the main content, research based on the image sequence robust, fast moving target extraction, motion estimation and target description algorithm, and the correlation between motion detection is to use frame, frame by comparing the difference between for change and not change area. The model is proposed based on the probability theory, and the future research will be focused on the simulation.展开更多
Due to the increasing demand for security, the development of intelligent surveillance systems has attracted considerable attention in recent years. This study aims to develop a system that is able to identify whether...Due to the increasing demand for security, the development of intelligent surveillance systems has attracted considerable attention in recent years. This study aims to develop a system that is able to identify whether or not the people need help in a public place. Different from previous work, our work considers not only the behaviors of the target person but also the interaction between him and nearby people. In the paper, we propose an event alarm system which can detect the human behaviors and recognize the happening event through integrating the results generated from the single and group behavior analysis. Several new effective features are proposed in the study. Besides, a mechanism capable of extracting one-to-one and multiple-to-one relations is also developed. Experimental results show that the proposed approach can correctly detect human behaviors and provide the alarm messages when emergency events occur.展开更多
Safety production is of great significance to the development of enterprises and society.Accidents often cause great losses because of the particularity environment of electric power.Therefore,it is important to impro...Safety production is of great significance to the development of enterprises and society.Accidents often cause great losses because of the particularity environment of electric power.Therefore,it is important to improve the safety supervision and protection in the electric power environment.In this paper,we simulate the actual electric power operation scenario by monitoring equipment and propose a real-time detection method of illegal actions based on human body key points to ensure safety behavior in real time.In this method,the human body key points in video frames were first extracted by the high-resolution network,and then classified in real time by spatial-temporal graph convolutional network.Experimental results show that this method can effectively detect illegal actions in the simulated scene.展开更多
With the increasing number of digital devices generating a vast amount of video data,the recognition of abnormal image patterns has become more important.Accordingly,it is necessary to develop a method that achieves t...With the increasing number of digital devices generating a vast amount of video data,the recognition of abnormal image patterns has become more important.Accordingly,it is necessary to develop a method that achieves this task using object and behavior information within video data.Existing methods for detecting abnormal behaviors only focus on simple motions,therefore they cannot determine the overall behavior occurring throughout a video.In this study,an abnormal behavior detection method that uses deep learning(DL)-based video-data structuring is proposed.Objects and motions are first extracted from continuous images by combining existing DL-based image analysis models.The weight of the continuous data pattern is then analyzed through data structuring to classify the overall video.The performance of the proposed method was evaluated using varying parameter settings,such as the size of the action clip and interval between action clips.The model achieved an accuracy of 0.9817,indicating excellent performance.Therefore,we conclude that the proposed data structuring method is useful in detecting and classifying abnormal behaviors.展开更多
With the development of wireless technology, Frequency-Modulated Continuous Wave (FMCW) radar has increased sensing capability and can be used to recognize human activity. These applications have gained wide-spread at...With the development of wireless technology, Frequency-Modulated Continuous Wave (FMCW) radar has increased sensing capability and can be used to recognize human activity. These applications have gained wide-spread attention and become a hot research area. FMCW signals reflected by target activity can be collected, and human activity can be recognized based on the measurements. This paper focused on human activity recognition based on FMCW and DenseNet. We collected point clouds from FMCW and analyzed them to recognize human activity because different activities could lead to unique point cloud features. We built and trained the neural network to implement human activities using a FMCW signal. Firstly, this paper presented recent reviews about human activity recognition using wireless signals. Then, it introduced the basic concepts of FMCW radar and described the fundamental principles of the system using FMCW radar. We also provided the system framework, experiment scenario, and DenseNet neural network structure. Finally, we presented the experimental results and analyzed the accuracy of different neural network models. The system achieved recognition accuracy of 100 percent for five activities using the DenseNet. We concluded the paper by discussing the current issues and future research directions.展开更多
文摘A common but flawed design in existing CNN architectures is using strided convolutions and/or pooling layer,which will result in the loss of fine-grained feature information,especially for low-resolution images and small objects.In this paper,a new CNN building block named SPD-Conv was used,which completely eliminated stride and pooling operations and replaced them with a space-to-depth convolution and a non-strided convolution.Such new design has the advantage of downsampling feature maps while retaining discriminant feature information.It also represents a general unified method,which can be easily applied to any CNN architectures,and can also be applied to strided conversion and pooling in the same way.
基金co-supported by the Natural Science Basic Research Program of Shaanxi,China(No.2023-JC-QN-0043)the ND Basic Research Funds,China(No.G2022WD).
文摘The aerial deployment method enables Unmanned Aerial Vehicles(UAVs)to be directly positioned at the required altitude for their mission.This method typically employs folding technology to improve loading efficiency,with applications such as the gravity-only aerial deployment of high-aspect-ratio solar-powered UAVs,and aerial takeoff of fixed-wing drones in Mars research.However,the significant morphological changes during deployment are accompanied by strong nonlinear dynamic aerodynamic forces,which result in multiple degrees of freedom and an unstable character.This hinders the description and analysis of unknown dynamic behaviors,further leading to difficulties in the design of deployment strategies and flight control.To address this issue,this paper proposes an analysis method for dynamic behaviors during aerial deployment based on the Variational Autoencoder(VAE).Focusing on the gravity-only deployment problem of highaspect-ratio foldable-wing UAVs,the method encodes the multi-degree-of-freedom unstable motion signals into a low-dimensional feature space through a data-driven approach.By clustering in the feature space,this paper identifies and studies several dynamic behaviors during aerial deployment.The research presented in this paper offers a new method and perspective for feature extraction and analysis of complex and difficult-to-describe extreme flight dynamics,guiding the research on aerial deployment drones design and control strategies.
基金the National Key Research and Development Program of China(No.2022YFC3601400)。
文摘Frequency-modulated continuous-wave radar enables the non-contact and privacy-preserving recognition of human behavior.However,the accuracy of behavior recognition is directly influenced by the spatial relationship between human posture and the radar.To address the issue of low accuracy in behavior recognition when the human body is not directly facing the radar,a method combining local outlier factor with Doppler information is proposed for the correction of multi-classifier recognition results.Initially,the information such as distance,velocity,and micro-Doppler spectrogram of the target is obtained using the fast Fourier transform and histogram of oriented gradients-support vector machine methods,followed by preliminary recognition.Subsequently,Platt scaling is employed to transform recognition results into confidence scores,and finally,the Doppler-local outlier factor method is utilized to calibrate the confidence scores,with the highest confidence classifier result considered as the recognition outcome.Experimental results demonstrate that this approach achieves an average recognition accuracy of 96.23%for comprehensive human behavior recognition in various orientations.
基金This work is supported by grants from National Natural Science Foundation of China under Grant No.71874025,71503033,and 62076114Humanities and Social Sciences Research Planning Foundation of the Ministry of Education under Grant No.20YJA630058.
文摘Social media rumors not only affect the health of online social networks,but also reduce the quality of information accessed by its users.In the case of emergencies,the rapid spread of rumors often triggers mass anxiety and panic.This study integrates the planned behavior(TPB)and deterrence(TD)theories to study the factors affecting the rumor recognition behavior of social media users.The structural equation model(SEM)method is used to test the proposed model.Further,the interaction between various factors is analyzed to evaluate their impact on the rumor recognition behavior exhibited by social media users in emergencies.The results demonstrate that certainty and severity have significant positive effects on subjective norms.In addition,subjective norms,attitude,and perceived behavioral control all affect the rumor recognition behavior of social media users,and involvement negatively moderates the relationship between the subjective norms and attitude.Finally,insights into the formulation of rumor control strategies during emergencies are presented based on the empirical analysis.
基金supported by the National Natural Science Foundation of China(No.61971439 and No.61702543)the Natural Science Foundation of the Jiangsu Province of China(No.BK20191329)+1 种基金the China Postdoctoral Science Foundation Project(No.2019T120987)the Startup Foundation for Introducing Talent of NUIST(No.2020r100).
文摘Communication behavior recognition is an issue with increasingly importance in the antiterrorism and national defense area.However,the sensing data obtained in actual environment is often not sufficient to accurately analyze the communication behavior.Traditional means can hardly utilize the scarce and crude spectrum sensing data captured in a real scene.Thus,communication behavior recognition using raw sensing data under smallsample condition has become a new challenge.In this paper,a data enhanced communication behavior recognition(DECBR)scheme is proposed to meet this challenge.Firstly,a preprocessing method is designed to make the raw spectrum data suitable for the proposed scheme.Then,an adaptive convolutional neural network structure is exploited to carry out communication behavior recognition.Moreover,DCGAN is applied to support data enhancement,which realize communication behavior recognition under small-sample condition.Finally,the scheme is verified by experiments under different data size.The results show that the DECBR scheme can greatly improve the accuracy and efficiency of behavior recognition under smallsample condition.
基金This research was funded by the Science and Technology Department of Shaanxi Province,China,Grant Number 2019GY-036.
文摘The core technology in an intelligent video surveillance system is that detecting and recognizing abnormal behaviors timely and accurately.The key breakthrough point in recognizing abnormal behaviors is how to obtain the effective features of the picture,so as to solve the problem of recognizing them.In response to this difficulty,this paper introduces an adjustable jump link coefficients model based on the residual network.The effective coefficients for each layer of the network can be set after using this model to further improving the recognition accuracy of abnormal behavior.A convolution kernel of 1×1 size is added to reduce the number of parameters for the purpose of improving the speed of the model in this paper.In order to reduce the noise of the data edge,and at the same time,improve the accuracy of the data and speed up the training,a BN(Batch Normalization)layer is added before the activation function in this network.This paper trains this network model on the public ImageNet dataset,and then uses the transfer learning method to recognize these abnormal behaviors of human in the UTI behavior dataset processed by the YOLO_v3 target detection network.Under the same experimental conditions,compared with the original ResNet-50 model,the improved model in this paper has a 2.8%higher accuracy in recognition of abnormal behaviors on the public UTI dataset.
基金supported by the National Natural Science Foundation of China(No.62006135)the Natural Science Foundation of Shandong Province(No.ZR2020QF116)。
文摘With the intensifying aging of the population,the phenomenon of the elderly living alone is also increasing.Therefore,using modern internet of things technology to monitor the daily behavior of the elderly in indoors is a meaningful study.Video-based action recognition tasks are easily affected by object occlusion and weak ambient light,resulting in poor recognition performance.Therefore,this paper proposes an indoor human behavior recognition method based on wireless fidelity(Wi-Fi)perception and video feature fusion by utilizing the ability of Wi-Fi signals to carry environmental information during the propagation process.This paper uses the public WiFi-based activity recognition dataset(WIAR)containing Wi-Fi channel state information and essential action videos,and then extracts video feature vectors and Wi-Fi signal feature vectors in the datasets through the two-stream convolutional neural network and standard statistical algorithms,respectively.Then the two sets of feature vectors are fused,and finally,the action classification and recognition are performed by the support vector machine(SVM).The experiments in this paper contrast experiments between the two-stream network model and the methods in this paper under three different environments.And the accuracy of action recognition after adding Wi-Fi signal feature fusion is improved by 10%on average.
基金Supported by the Shaanxi Province Key Research and Development Project(No.2021 GY-280)the Natural Science Foundation of Shaanxi Province(No.2021JM-459)the National Natural Science Foundation of China(No.61772417,61634004,61602377).
文摘In order to effectively solve the problems of low accuracy and large amount of calculation of current human behavior recognition,a behavior recognition algorithm based on squeeze-and-excitation network(SENet) combined with 3 D Inception network(I3 D) and gated recurrent unit(GRU) network is proposed.The algorithm first expands the Inception module to three-dimensional,and builds a network based on the three-dimensional module,and expands SENet to three-dimensional,making it an attention mechanism that can pay attention to the three-dimensional channel.Then SENet is introduced into the 13 D network,named SE-I3 D,and SENet is introduced into the CRU network,named SE-GRU.And,SE-13 D and SE-GRU are merged,named SE-13 D-GRU.Finally,the network uses Softmax to classify the results in the UCF-101 dataset.The experimental results show that the SE-I3 D-GRU network achieves a recognition rate of 93.2% on the UCF-101 dataset.
基金the National Natural Science Foundation of China(No.61772417,61634004,61602377)Key R&D Program Projects in Shaanxi Province(No.2017GY-060)Shaanxi Natural Science Basic Research Project(No.2018JM4018).
文摘In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dimensional batch normalization visual geometry group(3D-BN-VGG)and long short-term memory(LSTM)network is designed.In this network,3D convolutional layer is used to extract the spatial domain features and time domain features of video sequence at the same time,multiple small convolution kernels are stacked to replace large convolution kernels,thus the depth of neural network is deepened and the number of network parameters is reduced.In addition,the latest batch normalization algorithm is added to the 3-dimensional convolutional network to improve the training speed.Then the output of the full connection layer is sent to LSTM network as the feature vectors to extract the sequence information.This method,which directly uses the output of the whole base level without passing through the full connection layer,reduces the parameters of the whole fusion network to 15324485,nearly twice as much as those of 3D-BN-VGG.Finally,it reveals that the proposed network achieves 96.5%and 74.9%accuracy in the UCF-101 and HMDB-51 respectively,and the algorithm has a calculation speed of 1066 fps and an acceleration ratio of 1,which has a significant predominance in velocity.
文摘In the process of human behavior recognition, the traditional dense optical flow method has too many pixels and too much overhead, which limits the running speed. This paper proposed a method combing YOLOv3 (You Only Look Once v3) and local optical flow method. Based on the dense optical flow method, the optical flow modulus of the area where the human target is detected is calculated to reduce the amount of computation and save the cost in terms of time. And then, a threshold value is set to complete the human behavior identification. Through design algorithm, experimental verification and other steps, the walking, running and falling state of human body in real life indoor sports video was identified. Experimental results show that this algorithm is more advantageous for jogging behavior recognition.
文摘Building indoor dangerous behavior recognition is a specific application in the field of abnormal human recognition.A human dangerous behavior recognition method based on LSTM-GCN with attention mechanism(GLA)model was proposed aiming at the problem that the existing human skeleton-based action recognition methods cannot fully extract the temporal and spatial features.The network connects GCN and LSTMnetwork in series,and inputs the skeleton sequence extracted by GCN that contains spatial information into the LSTM layer for time sequence feature extraction,which fully excavates the temporal and spatial features of the skeleton sequence.Finally,an attention layer is designed to enhance the features of key bone points,and Softmax is used to classify and identify dangerous behaviors.The dangerous behavior datasets are derived from NTU-RGB+D and Kinetics data sets.Experimental results show that the proposed method can effectively identify some dangerous behaviors in the building,and its accuracy is higher than those of other similar methods.
基金the National Natural Science Foundation of China(No.61834005,61772417,61802304)the Shaanxi Province Key Research and Development Project(2021GY280).
文摘Compared with RGB videos and images,human bone data is less vulnerable to external factors and has stronger robustness.Therefore,behavior recognition methods based on skeletons are widely studied.Because graph convolution network(GCN)can deal with the irregular topology data of hu-man skeletons very well,more and more researchers apply GCN to human behavior recognition.Tra-ditional graph convolution methods only consider the joints with physical connectivity or the same type when building the behavior recognition model based on human skeletons structure,which cannot capture higher-order information better.To solve this problem,Motif-GCN is used in this paper to ex-tract spatial features.The relationship between the joints with natural connection in the human body is encoded by the first Motif-GCN,and the possible relationship between the unconnected joints in the human skeleton is encoded by the second Motif-GCN.In this way,the relationship between non-physical joints can be strengthened.Then a two stream framework combining joint and bone informa-tion is used to capture more action information.Finally,experiments are conducted on two subdata-sets X-Sub and X-View of NTU-RGB+D,and the accuracy shown in Top-1 classification results is 89.5%and 95.4%respectively.The experimental results are 1.0%and 0.3%higher than those of the 2S-AGCN model respectively.The superiority of this method is also proved by the experimental results.
基金Supported by the Shaanxi Province Key Research and Development Project (No. 2021GY-280)Shaanxi Province Natural Science Basic Research Program (No. 2021JM-459)the National Natural Science Foundation of China (No. 61772417)
文摘Because behavior recognition is based on video frame sequences,this paper proposes a behavior recognition algorithm that combines 3D residual convolutional neural network(R3D)and long short-term memory(LSTM).First,the residual module is extended to three dimensions,which can extract features in the time and space domain at the same time.Second,by changing the size of the pooling layer window the integrity of the time domain features is preserved,at the same time,in order to overcome the difficulty of network training and over-fitting problems,the batch normalization(BN)layer and the dropout layer are added.After that,because the global average pooling layer(GAP)is affected by the size of the feature map,the network cannot be further deepened,so the convolution layer and maxpool layer are added to the R3D network.Finally,because LSTM has the ability to memorize information and can extract more abstract timing features,the LSTM network is introduced into the R3D network.Experimental results show that the R3D+LSTM network achieves 91%recognition rate on the UCF-101 dataset.
文摘Recently,human healthcare from body sensor data has gained considerable interest from a wide variety of human-computer communication and pattern analysis research owing to their real-time applications namely smart healthcare systems.Even though there are various forms of utilizing distributed sensors to monitor the behavior of people and vital signs,physical human action recognition(HAR)through body sensors gives useful information about the lifestyle and functionality of an individual.This article concentrates on the design of an Improved Transient Search Optimization with Machine Learning based BehaviorRecognition(ITSOMLBR)technique using body sensor data.The presented ITSOML-BR technique collects data from different body sensors namely electrocardiography(ECG),accelerometer,and magnetometer.In addition,the ITSOML-BR technique extract features like variance,mean,skewness,and standard deviation.Moreover,the presented ITSOML-BR technique executes a micro neural network(MNN)which can be employed for long term healthcare monitoring and classification.Furthermore,the parameters related to the MNN model are optimally selected via the ITSO algorithm.The experimental result analysis of the ITSOML-BR technique is tested on the MHEALTH dataset.The comprehensive comparison study reported a higher result for the ITSOMLBR approach over other existing approaches with maximum accuracy of 99.60%.
基金supported by the National Natural Science Foundation of China(62071069)。
文摘User behavior prediction has become a core element to Internet of Things(IoT)and received promising attention in the related fields.Many existing IoT systems(e.g.smart home systems)have been deployed various sensors and the user’s behavior can be predicted through the sensor data.However,most of the existing sensor-based systems use the annotated behavior data which requires human intervention to achieve the behavior prediction.Therefore,it is a challenge to provide an automatic behavior prediction model based on the original sensor data.To solve the problem,this paper proposed a novel automatic annotated user behavior prediction(AAUBP)model.The proposed AAUBP model combined the Discontinuous Solving Order Sequence Mining(DVSM)behavior recognition model and behavior prediction model based on the Long Short Term Memory(LSTM)network.To evaluate the model,we performed several experiments on a real-world dataset tuning the parameters.The results showed that the AAUBP model can effectively recognize behaviors and had a good performance for behavior prediction.
文摘This paper proposes the research on human body behavior recognition based on vision. Behavior based on high-level human structure can describe behavior more accurately, but it is dif？ cult to extract the behavioral characteristics while often relying on the accuracy of the human pose estimation. Moving object extraction of the moving targets in video analysis as the main content, research based on the image sequence robust, fast moving target extraction, motion estimation and target description algorithm, and the correlation between motion detection is to use frame, frame by comparing the difference between for change and not change area. The model is proposed based on the probability theory, and the future research will be focused on the simulation.
基金supported by the“MOST”under Grant No.104-2221-E-259-024-MY2
文摘Due to the increasing demand for security, the development of intelligent surveillance systems has attracted considerable attention in recent years. This study aims to develop a system that is able to identify whether or not the people need help in a public place. Different from previous work, our work considers not only the behaviors of the target person but also the interaction between him and nearby people. In the paper, we propose an event alarm system which can detect the human behaviors and recognize the happening event through integrating the results generated from the single and group behavior analysis. Several new effective features are proposed in the study. Besides, a mechanism capable of extracting one-to-one and multiple-to-one relations is also developed. Experimental results show that the proposed approach can correctly detect human behaviors and provide the alarm messages when emergency events occur.
基金the Science and Technology Program of State Grid Corporation of China(No.5211TZ1900S6)。
文摘Safety production is of great significance to the development of enterprises and society.Accidents often cause great losses because of the particularity environment of electric power.Therefore,it is important to improve the safety supervision and protection in the electric power environment.In this paper,we simulate the actual electric power operation scenario by monitoring equipment and propose a real-time detection method of illegal actions based on human body key points to ensure safety behavior in real time.In this method,the human body key points in video frames were first extracted by the high-resolution network,and then classified in real time by spatial-temporal graph convolutional network.Experimental results show that this method can effectively detect illegal actions in the simulated scene.
基金supported by Basic Science Research Program through the NationalResearch Foundation of Korea (NRF)funded by the Ministry of Education (2020R1A6A1A03040583).
文摘With the increasing number of digital devices generating a vast amount of video data,the recognition of abnormal image patterns has become more important.Accordingly,it is necessary to develop a method that achieves this task using object and behavior information within video data.Existing methods for detecting abnormal behaviors only focus on simple motions,therefore they cannot determine the overall behavior occurring throughout a video.In this study,an abnormal behavior detection method that uses deep learning(DL)-based video-data structuring is proposed.Objects and motions are first extracted from continuous images by combining existing DL-based image analysis models.The weight of the continuous data pattern is then analyzed through data structuring to classify the overall video.The performance of the proposed method was evaluated using varying parameter settings,such as the size of the action clip and interval between action clips.The model achieved an accuracy of 0.9817,indicating excellent performance.Therefore,we conclude that the proposed data structuring method is useful in detecting and classifying abnormal behaviors.
文摘With the development of wireless technology, Frequency-Modulated Continuous Wave (FMCW) radar has increased sensing capability and can be used to recognize human activity. These applications have gained wide-spread attention and become a hot research area. FMCW signals reflected by target activity can be collected, and human activity can be recognized based on the measurements. This paper focused on human activity recognition based on FMCW and DenseNet. We collected point clouds from FMCW and analyzed them to recognize human activity because different activities could lead to unique point cloud features. We built and trained the neural network to implement human activities using a FMCW signal. Firstly, this paper presented recent reviews about human activity recognition using wireless signals. Then, it introduced the basic concepts of FMCW radar and described the fundamental principles of the system using FMCW radar. We also provided the system framework, experiment scenario, and DenseNet neural network structure. Finally, we presented the experimental results and analyzed the accuracy of different neural network models. The system achieved recognition accuracy of 100 percent for five activities using the DenseNet. We concluded the paper by discussing the current issues and future research directions.
