Human action recognition using autoencoder

Qu, Xiao; Yang, Shi Qing

doi:10.1109/compcomm.2017.8322824

Cited by 9 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature maps were then passed through RNN layer to analyze according to temporal domain. Xiao et al (2017) [3], used autoencoder to train for both human body segmentation and motion modeling. Then a deep network is used to perform action recognition.…”

Section: Core Background Studymentioning

confidence: 99%

“…This can be solved using CapsNet's instantaneous feature extraction and vector modeling in a hierarchical way. Xiao et al (2017) [3] used encoder-decoder model using backpropagation to train the autoencoders which encode the features of the frame and constructs a pattern recognition network. This requires a lot of computational power to encode and decode the models.…”

Section: Review Based On Frameworkmentioning

confidence: 99%

“…Zhang et al (2017)[16] dynamically adjusted the position of a subject through adaptive LSTM by creating a new virtual camera viewpoint. In [17], time-varying geometric shapes extracted from human joints are input to 3 layers LSTM for action recognition.Xiao et al (2017)[3] trained autoencoder using deep learning techniques to extract features which are later used by Pattern Recognition Neural Network (PRNN) to detect human action. InLi et al (2018)…”

mentioning

confidence: 99%

See 2 more Smart Citations

Aggressive Action Estimation: A Comprehensive Review on Neural Network Based Human Segmentation and Action Recognition

Saif

Akib

Khan

et al. 2019

IJEME

View full text Add to dashboard Cite

Human action recognition has been a talked topic since machine vision was coined. With the advent of neural networks and deep learning methods, various architectures were suggested to address the problems within a context. Convolutional neural network has been the primary go-to architecture for image segmentation, flow estimation and action recognition in recent days. As the problem itself is an extended version of various subproblems, such as frame segmentation, spatial and temporal feature extraction, motion modeling and action classification as a whole, some methods reviewed in this paper addressed sub-problems and some tried to address a single architecture to the action recognition problem. While being a success, convolution neural networks have drawbacks in its pooling methods. CapsNet, on the other hand, uses squashing function to determine the activation. Also it addresses spatiotemporal information with the normalized vector maps while CNN-based methods extracts feature map for spatial and temporal information and later augment them in a fusion layer for combining two separate feature maps. Critical review of papers provided in this work can contribute significantly in addressing human action recognition problem as a whole.

show abstract

Section: Core Background Studymentioning

confidence: 99%

Section: Review Based On Frameworkmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Aggressive Action Estimation: A Comprehensive Review on Neural Network Based Human Segmentation and Action Recognition

Saif

Akib

Khan

et al. 2019

IJEME

View full text Add to dashboard Cite

show abstract

“…Feature extraction and selection are other issues in machine learning classification. Many feature extraction methods have been proposed using principal components analysis (PCA) [ 13 , 17 , 18 ], autoencoders (AEs) [ 18 , 19 , 20 , 21 , 22 ], and convolutional neural networks (CNNs) [ 23 ]. PCA requires less calculation and has faster responses and AE is suitable for situations lacking negative sampling.…”

Section: Introductionmentioning

confidence: 99%

End-to-End Deep Learning by MCU Implementation: An Intelligent Gripper for Shape Identification

Hung

Zeng

Lee

et al. 2021

Sensors

View full text Add to dashboard Cite

This paper introduces a real-time processing and classification of raw sensor data using a convolutional neural network (CNN). The established system is a microcontroller-unit (MCU) implementation of an intelligent gripper for shape identification of grasped objects. The pneumatic gripper has two embedded accelerometers to sense acceleration (in the form of vibration signals) on the jaws for identification. The raw data is firstly transferred into images by short-time Fourier transform (STFT), and then the CNN algorithm is adopted to extract features for classifying objects. In addition, the hyperparameters of the CNN are optimized to ensure hardware implementation. Finally, the proposed artificial intelligent model is implemented on a MCU (Renesas RX65N) from raw data to classification. Experimental results and discussions are introduced to show the performance and effectiveness of our proposed approach.

show abstract

“…The restricted Boltzmann machine (RBM) architecture and stack autoencoder (SAE) extracts features of handwriting recognition, then classifies them by SVM [13]. The data of the time domain can also be compressed via AE, such an AE is used to extract features of limb motion and then classify by pattern recognition neural network (PRNN) [14]. Although the effect of AE is worse than the original CNN, it reduces a lot of computing costs.…”

Section: Introductionmentioning

confidence: 99%

Design of a Chamfering Tool Diagnosis System Using Autoencoder Learning Method

Hung

Mao

et al. 2019

Energies

View full text Add to dashboard Cite

. In this paper, the autoencoder learning method is proposed for the system diagnosis of chamfering tool equipment. The autoencoder uses unsupervised learning architecture. The training dataset that requires only a positive sample is quite suitable for industrial production lines. The abnormal tool can be diagnosed by comparing the output and input of the autoencoder neural network. The adjustable threshold can effectively improve accuracy. This method can effectively adapt to the current environment when the data contain multiple signals. In the experimental setup, the main diagnostic signal is the current of the motor. The current reflects the torque change when the tool is abnormal. Four-step conversions are developed to process the current signal, including (1) current-to-voltage conversion, (2) analog-digital conversion, (3) downsampling rate, and (4) discrete Fourier transform. The dataset is used to find the best autoencoder parameters by grid search. In training results, the testing accuracy, true positive rate, and precision approach are 87.5%, 83.33%, and 90.91%, respectively. The best model of the autoencoder is evaluated by online testing. The online test means loading the diagnosis model in the production line and evaluating the model. It is shown that the proposed tool can effectively detect abnormal conditions. The online assessment accuracy, true positive rate, and precision are 75%, 90%, and 69.23% in the original threshold, respectively. The accuracy can be up to 90% after adjusting the threshold, and the true positive rate and precision are up to 80% and 100%, respectively.

show abstract

Human action recognition using autoencoder

Cited by 9 publications

References 10 publications

Aggressive Action Estimation: A Comprehensive Review on Neural Network Based Human Segmentation and Action Recognition

Aggressive Action Estimation: A Comprehensive Review on Neural Network Based Human Segmentation and Action Recognition

End-to-End Deep Learning by MCU Implementation: An Intelligent Gripper for Shape Identification

Design of a Chamfering Tool Diagnosis System Using Autoencoder Learning Method

Contact Info

Product

Resources

About