scholarly journals “Reading Pictures Instead of Looking”: RGB-D Image-Based Action Recognition via Capsule Network and Kalman Filter

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2217
Author(s):  
Botong Zhao ◽  
Yanjie Wang ◽  
Keke Su ◽  
Hong Ren ◽  
Haichao Sun
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Action Recognition ◽  
Recognition Algorithm ◽  
Dendritic Network ◽  
Time Operation ◽  
The Neural Network ◽  
Real Time Operation ◽  
Spatial Coordinates ◽  
Depth Learning

This paper proposes an action recognition algorithm based on the capsule network and Kalman filter called “Reading Pictures Instead of Looking” (RPIL). This method resolves the convolutional neural network’s over sensitivity to rotation and scaling and increases the interpretability of the model as per the spatial coordinates in graphics. The capsule network is first used to obtain the components of the target human body. The detected parts and their attribute parameters (e.g., spatial coordinates, color) are then analyzed by Bert. A Kalman filter analyzes the predicted capsules and filters out any misinformation to prevent the action recognition results from being affected by incorrectly predicted capsules. The parameters between neuron layers are evaluated, then the structure is pruned into a dendritic network to enhance the computational efficiency of the algorithm. This minimizes the dependence of in-depth learning on the random features extracted by the CNN without sacrificing the model’s accuracy. The association between hidden layers of the neural network is also explained. With a 90% observation rate, the OAD dataset test precision is 83.3%, the ChaLearn Gesture dataset test precision is 72.2%, and the G3D dataset test precision is 86.5%. The RPILNet also satisfies real-time operation requirements (>30 fps).

scholarly journals Exploring 3D Human Action Recognition Using STACOG on Multi-View Depth Motion Maps Sequences

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3642
Author(s):  
Mohammad Farhad Bulbul ◽  
Sadiya Tabussum ◽  
Hazrat Ali ◽  
Wenli Zheng ◽  
Mi Young Lee ◽  
...  
Keyword(s):  
Action Recognition ◽  
Depth Map ◽  
Human Action Recognition ◽  
Human Action ◽  
Collaborative Representation ◽  
Auto Correlation ◽  
Time Operation ◽  
Real Time Operation ◽  
Benchmark Datasets ◽  
Depth Motion Maps

This paper proposes an action recognition framework for depth map sequences using the 3D Space-Time Auto-Correlation of Gradients (STACOG) algorithm. First, each depth map sequence is split into two sets of sub-sequences of two different frame lengths individually. Second, a number of Depth Motion Maps (DMMs) sequences from every set are generated and are fed into STACOG to find an auto-correlation feature vector. For two distinct sets of sub-sequences, two auto-correlation feature vectors are obtained and applied gradually to L2-regularized Collaborative Representation Classifier (L2-CRC) for computing a pair of sets of residual values. Next, the Logarithmic Opinion Pool (LOGP) rule is used to combine the two different outcomes of L2-CRC and to allocate an action label of the depth map sequence. Finally, our proposed framework is evaluated on three benchmark datasets named MSR-action 3D dataset, DHA dataset, and UTD-MHAD dataset. We compare the experimental results of our proposed framework with state-of-the-art approaches to prove the effectiveness of the proposed framework. The computational efficiency of the framework is also analyzed for all the datasets to check whether it is suitable for real-time operation or not.

scholarly journals I3D-Shufflenet Based Human Action Recognition

Algorithms ◽  
2020 ◽  
Vol 13 (11) ◽  
pp. 301
Author(s):  
Guocheng Liu ◽  
Caixia Zhang ◽  
Qingyang Xu ◽  
Ruoshi Cheng ◽  
Yong Song ◽  
...  
Keyword(s):  
Neural Network ◽  
Action Recognition ◽  
Human Action Recognition ◽  
Human Action ◽  
Recognition Algorithm ◽  
Convolution Kernel ◽  
Histogram Of Oriented Gradients ◽  
Temporal Features ◽  
Convolution Kernels

In view of difficulty in application of optical flow based human action recognition due to large amount of calculation, a human action recognition algorithm I3D-shufflenet model is proposed combining the advantages of I3D neural network and lightweight model shufflenet. The 5 × 5 convolution kernel of I3D is replaced by a double 3 × 3 convolution kernels, which reduces the amount of calculations. The shuffle layer is adopted to achieve feature exchange. The recognition and classification of human action is performed based on trained I3D-shufflenet model. The experimental results show that the shuffle layer improves the composition of features in each channel which can promote the utilization of useful information. The Histogram of Oriented Gradients (HOG) spatial-temporal features of the object are extracted for training, which can significantly improve the ability of human action expression and reduce the calculation of feature extraction. The I3D-shufflenet is testified on the UCF101 dataset, and compared with other models. The final result shows that the I3D-shufflenet has higher accuracy than the original I3D with an accuracy of 96.4%.

scholarly journals Power Quality Disturbance Identification and Optimization Based on Machine Learning

2021 ◽  
Author(s):  
Fei Long ◽  
Fen Liu ◽  
Xiangli Peng ◽  
Zheng Yu ◽  
Huan Xu ◽  
...  
Keyword(s):  
Neural Network ◽  
Power Quality ◽  
Classification Method ◽  
Neural Network Training ◽  
Training Set ◽  
Network Training ◽  
The Neural Network ◽  
Recognition Ability ◽  
Power Quality Disturbance ◽  
Depth Learning

In order to improve the electrical quality disturbance recognition ability of the neural network, this paper studies a depth learning-based power quality disturbance recognition and classification method: constructing a power quality perturbation model, generating training set; construct depth neural network; profit training set to depth neural network training; verify the performance of the depth neural network; the results show that the training set is randomly added 20DB-50DB noise, even in the most serious 20dB noise conditions, it can reach more than 99% identification, this is a tradition. The method is impossible to implement. Conclusion: the deepest learning-based power quality disturbance identification and classification method overcomes the disadvantage of the selection steps of artificial characteristics, poor robustness, which is beneficial to more accurately and quickly discover the category of power quality issues.

scholarly journals The approach to the formation of the neural network architecture for pattern recognition

2016 ◽  
Vol 12 (2) ◽  
pp. 61-64 ◽  
Author(s):  
Vitaly M Tatyankin
Keyword(s):  
Neural Network ◽  
Pattern Recognition ◽  
Network Architecture ◽  
Test Sample ◽  
Recognition Algorithm ◽  
Neural Network Architecture ◽  
Pattern Recognition Algorithm ◽  
The Neural Network

An approach to the formation of an efficient pattern recognition algorithm. Under efficiency, understood as a zero error, resulting in the identification of the images on the test sample. As a test sample is considered an open database of images of handwritten digits MNIST.

scholarly journals Nonlinear Autoregressive Neural Network and Extended Kalman Filters for Prediction of Financial Time Series

2020 ◽  
Vol 2020 ◽  
pp. 1-6 ◽  
Author(s):  
Ghassane Benrhmach ◽  
Khalil Namir ◽  
Abdelwahed Namir ◽  
Jamal Bouyaghroumni
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Financial Time Series ◽  
Broad Class ◽  
Financial Time ◽  
The Neural Network ◽  
Nonlinear Autoregressive ◽  
Autoregressive Neural Network

Time series analysis and prediction are major scientific challenges that find their applications in fields as diverse as finance, biology, economics, meteorology, and so on. Obtaining the method with the least prediction error is one of the difficult problems of financial market and investment analysts. State space modelling is an efficient and flexible method for statistical inference of a broad class of time series and other data. The neural network is an important tool for analyzing time series especially when it is nonlinear and nonstationary. Essential tools for the study of Box-Jenkins methodology, neural networks, and extended Kalman filter were put together. We examine the use of the nonlinear autoregressive neural network method as a prediction technique for financial time series and the application of the extended Kalman filter algorithm to improve the accuracy of the model. As application on a real example, we are analyzing the time series of the daily price of steel over a 790-day period for establishing the superiority of this method over other existing methods. The simulation results using MATLAB and R software show that the model is capable of producing a reasonable accuracy.

Incorporation of Neural Network State Estimator for GPS Attitude Determination

2004 ◽  
Vol 57 (1) ◽  
pp. 117-134 ◽  
Author(s):  
Dah-Jing Jwo ◽  
Chun-Fan Pai
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Least Squares ◽  
Kalman Filtering ◽  
Attitude Determination ◽  
Least Squares Method ◽  
State Estimator ◽  
Estimation Errors ◽  
Network State ◽  
The Neural Network

The Global Positioning System (GPS) can be employed as a free attitude determination interferometer when carrier phase measurements are utilized. Conventional approaches for the baseline vectors are essentially based on the least-squares or Kalman filtering methods. The raw attitude solutions are inherently noisy if the solutions of baseline vectors are obtained based on the least-squares method. The Kalman filter attempts to minimize the error variance of the estimation errors and will provide the optimal result while it is required that the complete a priori knowledge of both the process noise and measurement noise covariance matrices are available. In this article, a neural network state estimator, which replaces the Kalman filter, will be incorporated into the attitude determination mechanism for estimating the attitude angles from the noisy raw attitude solutions. Employing the neural network estimator improves robustness compared to the Kalman filtering method when uncertainty in noise statistical knowledge exists. Simulation is conducted and a comparative evaluation based on the neural network estimator and Kalman filter is provided.

Neural network using the Levenberg–Marquardt algorithm for optimal real-time operation of water distribution systems

2018 ◽  
Vol 15 (7) ◽  
pp. 692-699 ◽  
Author(s):  
Geraldo de Araújo Moura ◽  
Saulo de Tarso Marques Bezerra ◽  
Heber Pimentel Gomes ◽  
Simplício Arnaud da Silva
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Distribution Systems ◽  
Water Distribution ◽  
Water Distribution Systems ◽  
Time Operation ◽  
Marquardt Algorithm ◽  
Levenberg Marquardt ◽  
Real Time Operation

scholarly journals Neural network assisted Kalman filter for INS/UWB integrated seamless quadrotor localization

2021 ◽  
Vol 7 ◽  
pp. e630
Author(s):  
Shuhui Bi ◽  
Liyao Ma ◽  
Tao Shen ◽  
Yuan Xu ◽  
Fukun Li
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Wide Band ◽  
Indoor Environments ◽  
Position Information ◽  
Localization Accuracy ◽  
The Neural Network ◽  
Measurement Vector ◽  
Localization Information ◽  
Real Test

Due to some harsh indoor environments, the signal of the ultra wide band (UWB) may be lost, which makes the data fusion filter can not work. For overcoming this problem, the neural network (NN) assisted Kalman filter (KF) for fusing the UWB and the inertial navigation system (INS) data seamlessly is present in this work. In this approach, when the UWB data is available, both the UWB and the INS are able to provide the position information of the quadrotor, and thus, the KF is used to provide the localization information by the fusion of position difference between the INS and the UWB, meanwhile, the KF can provide the estimation of the INS position error, which is able to assist the NN to build the mapping between the state vector and the measurement vector off-line. The NN can estimate the KF’s measurement when the UWB data is unavailable. For confirming the effectiveness of the proposed method, one real test has been done. The test’s results demonstrate that the proposed NN assisted KF is effective to the fusion of INS and UWB data seamlessly, which shows obvious improvement of localization accuracy. Compared with the LS-SVM assisted KF, the proposed NN assisted KF is able to reduce the localization error by about 54.34%.

Electric Machines Excitation Control via Higher Order Neural Networks

2010 ◽  
pp. 366-396 ◽  
Author(s):  
Yannis L. Karnavas
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
Real Time ◽  
Fuzzy Logic Controller ◽  
Synchronous Generator ◽  
Higher Order ◽  
Excitation Control ◽  
Time Operation ◽  
Real Time Operation ◽  
Neural Network Controllers

This chapter is demonstrating a practical design of an intelligent type of controller using higher order neural network (HONN) concepts, for the excitation control of a practical power generating system. This type of controller is suitable for real time operation, and aims to improve the dynamic characteristics of the generating unit by acting properly on its original excitation system. The modeling of the power system under study consists of a synchronous generator connected via a transformer and a transmission line to an infinite bus. For comparison purposes and also for producing useful data in order for the demonstrating neural network controllers to be trained, digital simulations of the above system are performed using fuzzy logic control (FLC) techniques, which are based on previous work. Then, two neural network controllers are designed and applied by adopting the HONN architectures. The first one utilizes a single pi-sigma neural network (PSNN) and the significant advantages over the standard multi layered perceptron (MLP) are discussed. Secondly, an enhanced controller is designed, leading to a ridge polynomial neural network (RPNN) by combining multiple PSNNs if needed. Both controllers used, can be pre-trained rapidly from the corresponding FLC output signal and act as model dynamics capturers. The dynamic performances of the fuzzy logic controller (FLC) along with those of the two demonstrated controllers are presented by comparison using the well known integral square error criterion (ISE). The latter controllers, show excellent convergence properties and accuracy for function approximation. Typical transient responses of the system are shown for comparison in order to demonstrate the effectiveness of the designed controllers. The computer simulation results obtained show clearly that the performance of the developed controllers offers competitive damping effects on the synchronous generator’s oscillations, with respect to the associated ones of the FLC, over a wider range of operating conditions, while their hardware implementation is apparently much easier and the computational time needed for real-time applications is drastically reduced.

Image segmentation of clouds based on deep learning

2020 ◽  
Vol 2020 (48) ◽  
pp. 72-78
Author(s):  
B.P. Rusyn ◽  
◽  
O.A. Lutsyk ◽  
R.Ya. Kosarevych ◽  
V.V. Korniy ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Deep Learning ◽  
Weather Forecasting ◽  
Quality Criteria ◽  
Time Operation ◽  
Real Time Operation ◽  
Automated Processing ◽  
Segmentation Of Images ◽  
Remote Sensing Methods

The paper is devoted to the development of the methods for segmentation of images of atmospheric clouds, which are obtained by remote sensing methods using aircraft or satellite onboard systems. The proposed approach is some extent further improvement of the convolutional neural network of the U-net type. The uses known quality criteria for segmentation, which allows us to compare the proposed approach with already known methods in the field of segmentation of images of atmospheric clouds. A large number of experiments on real images shows the feasi-bility of using the proposed method of segmentation for automated processing with the require-ments for real-time operation. Applied use of the results is possible in the tasks of monitoring and classification for weather forecasting, agriculture, and other areas related to observations of atmospheric clouds.

Sign in / Sign up

Export Citation Format

Share Document