Aiming at the shortcomings of current gesture tracking methods in accuracy and speed, based on deep learning You Only Look Once version 4(YOLOv4) model, a new YOLOv4 model combined with Kalman filter real-time hand tr...Aiming at the shortcomings of current gesture tracking methods in accuracy and speed, based on deep learning You Only Look Once version 4(YOLOv4) model, a new YOLOv4 model combined with Kalman filter real-time hand tracking method was proposed. The new algorithm can address some problems existing in hand tracking technology such as detection speed, accuracy and stability. The convolutional neural network(CNN) model YOLOv4 is used to detect the target of current frame tracking and Kalman filter is applied to predict the next position and bounding box size of the target according to its current position. The detected target is tracked by comparing the estimated result with the detected target in the next frame and, finally, the real-time hand movement track is displayed. The experimental results validate the proposed algorithm with the overall success rate of 99.43% at speed of 41.822 frame/s, achieving superior results than other algorithms.展开更多
Hand tracking is a challenging problem due to the complexity of searching in a 20 + degrees of freedom (DOF) space for an optimal estimation of hand configuration. The feasible hand configurations are represented a...Hand tracking is a challenging problem due to the complexity of searching in a 20 + degrees of freedom (DOF) space for an optimal estimation of hand configuration. The feasible hand configurations are represented as a discrete space, which avoids learning to find parameters as general configuration space representations do. Then, an extended simulated annealing method with particle filtering to search for optimal hand configuration in the proposed discrete space, in which simplex search running in multi-processor is designed to predict the hand motion instead of initializing the simulated annealing randomly, and particle filtering is employed to represent the state of the tracker at each layer for searching in high dimensional configuration space. Experimental results show that the proposed method makes the hand tracking more efficient and robust.展开更多
In the majority of the interaction process, the operator often focuses on the tracked 3D hand gesture model at the "interaction points" in the collision detectionscene, such as "grasp" and "release" and objects ...In the majority of the interaction process, the operator often focuses on the tracked 3D hand gesture model at the "interaction points" in the collision detectionscene, such as "grasp" and "release" and objects in the scene, without paying attention to the tracked 3D hand gesture model in the total procedure. Thus in this paper, a visual attention distribution model of operator in the "grasp", "translation", "release" and other basic operation procedures is first studied and a 3D hand gesture tracking algorithm based on this distribution model is proposed. Utilizing the algorithm, in the period with a low degree of visual attention, a pre-stored 3D hand gesture animation can be used to directly visualise a 3D hand gesture model in the interactive scene; in the time period with a high degree of visual attention, an existing "frame-by-frame tracking" approach can be adopted to obtain a 3D gesture model. The results demonstrate that the proposed method can achieve real-time tracking of 3D hand gestures with an effective improvement on the efficiency, fluency, and availability of 3D hand gesture interaction.展开更多
People with complex communication needs can use a high-technology augmentative and alternative communication device to communicate with others.Currently,researchers and clinicians often use data logging from high-tech...People with complex communication needs can use a high-technology augmentative and alternative communication device to communicate with others.Currently,researchers and clinicians often use data logging from high-tech augmentative and alternative communication devices to analyze augmentative and alternative communication user performance.However,existing automated data logging systems cannot differentiate the authorship of the data log when more than one user accesses the device.This issue reduces the validity of the data logs and increases the difficulties of performance analysis.Therefore,this paper presents a solution using a deep neural network-based visual analysis approach to process videos to detect different augmentative and alternative communication users in practice sessions.This approach has significant potential to improve the validity of data logs and ultimately to enhance augmentative and alternative communication outcome measures.展开更多
This paper propees the consistent extended Kalman flter(CEKF)for the maneuvering target tracking(MTT)with nonlinear uncertain dynamics,and applies it on hand poition tracking.The general modlel of the MTT system i pre...This paper propees the consistent extended Kalman flter(CEKF)for the maneuvering target tracking(MTT)with nonlinear uncertain dynamics,and applies it on hand poition tracking.The general modlel of the MTT system i presented with unmodleled dynamics in terms of nonlinear unknown function of states.The CEKF is propoeed to ensure that the bounds of the estimation error's covariance matrix are av ailable through the flter algorithm.As a result,the creponding accuracy of the flter approach can be achieved online.Furthermore,a CEKF-baaed MTT algorithm is constructed via the tumning aw of the critical parameter matrix QE Finally,the efectiveness of CEKF i verified by MTT numerical simulations and hand tacking expeiments under dilferent maneuvens.Specifcally,two indices are employed to compare the CEKF with extended Kalman filter(EKF):the mean square errors(MSEa)and the bounded percentage,ie the percentage of the rang w bere the estimation error is encboed by the bound calculated by algorithms.All MSEs of CEKF are smaller than thoee of EKF,where the worst MSEa of CEKF and EKF are0.14 and 418 in the simulation,a8 well 80.11 and 059 in the expeiments,respectively;all bounded percentages of CEKF are larger than thoee of EKF,where the wonst average bounded percentages of CEKF and EKF ame 87.86%and 14.58%,8 well as 97.41%and 41.79%in the experiments,reapectively.展开更多
文摘Aiming at the shortcomings of current gesture tracking methods in accuracy and speed, based on deep learning You Only Look Once version 4(YOLOv4) model, a new YOLOv4 model combined with Kalman filter real-time hand tracking method was proposed. The new algorithm can address some problems existing in hand tracking technology such as detection speed, accuracy and stability. The convolutional neural network(CNN) model YOLOv4 is used to detect the target of current frame tracking and Kalman filter is applied to predict the next position and bounding box size of the target according to its current position. The detected target is tracked by comparing the estimated result with the detected target in the next frame and, finally, the real-time hand movement track is displayed. The experimental results validate the proposed algorithm with the overall success rate of 99.43% at speed of 41.822 frame/s, achieving superior results than other algorithms.
基金the National Natural Science Foundation of China (60473049)
文摘Hand tracking is a challenging problem due to the complexity of searching in a 20 + degrees of freedom (DOF) space for an optimal estimation of hand configuration. The feasible hand configurations are represented as a discrete space, which avoids learning to find parameters as general configuration space representations do. Then, an extended simulated annealing method with particle filtering to search for optimal hand configuration in the proposed discrete space, in which simplex search running in multi-processor is designed to predict the hand motion instead of initializing the simulated annealing randomly, and particle filtering is employed to represent the state of the tracker at each layer for searching in high dimensional configuration space. Experimental results show that the proposed method makes the hand tracking more efficient and robust.
基金Supported by the National Natural Science Foundation of China(61472163)the National Key Research&Development Plan of China(2016YFB1001403)the Science and Technology Project of Shandong Province(2015GGX101025)
文摘In the majority of the interaction process, the operator often focuses on the tracked 3D hand gesture model at the "interaction points" in the collision detectionscene, such as "grasp" and "release" and objects in the scene, without paying attention to the tracked 3D hand gesture model in the total procedure. Thus in this paper, a visual attention distribution model of operator in the "grasp", "translation", "release" and other basic operation procedures is first studied and a 3D hand gesture tracking algorithm based on this distribution model is proposed. Utilizing the algorithm, in the period with a low degree of visual attention, a pre-stored 3D hand gesture animation can be used to directly visualise a 3D hand gesture model in the interactive scene; in the time period with a high degree of visual attention, an existing "frame-by-frame tracking" approach can be adopted to obtain a 3D gesture model. The results demonstrate that the proposed method can achieve real-time tracking of 3D hand gestures with an effective improvement on the efficiency, fluency, and availability of 3D hand gesture interaction.
文摘People with complex communication needs can use a high-technology augmentative and alternative communication device to communicate with others.Currently,researchers and clinicians often use data logging from high-tech augmentative and alternative communication devices to analyze augmentative and alternative communication user performance.However,existing automated data logging systems cannot differentiate the authorship of the data log when more than one user accesses the device.This issue reduces the validity of the data logs and increases the difficulties of performance analysis.Therefore,this paper presents a solution using a deep neural network-based visual analysis approach to process videos to detect different augmentative and alternative communication users in practice sessions.This approach has significant potential to improve the validity of data logs and ultimately to enhance augmentative and alternative communication outcome measures.
基金supported in part by the National Natural Science Foundation of China(Grant Nos.62025307,U1913209,61973299,61873013)the Beijing Natural Science Foundation(Grant No.JQ19020)supported in part by the Key Laboratory of Systems and Control,Chinese Academy of Sciences.
文摘This paper propees the consistent extended Kalman flter(CEKF)for the maneuvering target tracking(MTT)with nonlinear uncertain dynamics,and applies it on hand poition tracking.The general modlel of the MTT system i presented with unmodleled dynamics in terms of nonlinear unknown function of states.The CEKF is propoeed to ensure that the bounds of the estimation error's covariance matrix are av ailable through the flter algorithm.As a result,the creponding accuracy of the flter approach can be achieved online.Furthermore,a CEKF-baaed MTT algorithm is constructed via the tumning aw of the critical parameter matrix QE Finally,the efectiveness of CEKF i verified by MTT numerical simulations and hand tacking expeiments under dilferent maneuvens.Specifcally,two indices are employed to compare the CEKF with extended Kalman filter(EKF):the mean square errors(MSEa)and the bounded percentage,ie the percentage of the rang w bere the estimation error is encboed by the bound calculated by algorithms.All MSEs of CEKF are smaller than thoee of EKF,where the worst MSEa of CEKF and EKF are0.14 and 418 in the simulation,a8 well 80.11 and 059 in the expeiments,respectively;all bounded percentages of CEKF are larger than thoee of EKF,where the wonst average bounded percentages of CEKF and EKF ame 87.86%and 14.58%,8 well as 97.41%and 41.79%in the experiments,reapectively.