Gesture recognition based on skeletonization algorithm and CNN with ASL database

Du, Jiang; Li, Gongfa; Sun, Ying; Kong, Jianyi; Tao, Bo

doi:10.1007/s11042-018-6748-0

Cited by 142 publications

(98 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the preparation of sEMG noise reduction and feature extraction, in order to realize the final classification of hand movements, the feature vectors need to be input into the appropriate classifier, and the final recognition rate is very high with the separators, so the selection and design of the classifier is particularly important [52]. However, many kinds of classifiers are used at present, and both of them are in their own advantages and short boards.…”

Section: Hand Movement Recognition Based On Svm and Grnnmentioning

confidence: 99%

Surface EMG data aggregation processing for intelligent prosthetic action recognition

Jiang

et al. 2018

Neural Comput & Applic

Self Cite

107

View full text Add to dashboard Cite

In the current development and design of sports rehabilitation equipment or biomimetic prostheses, in addition to pay attention to the development and design of the structure, the more core is how to realize the accurate and effective control of the rehabilitation equipment or intelligent prosthesis, and the current research is based on data process and pattern recognition. This paper designs 9 kinds of actions that can react effectively to the function of the hand and extracts the original EMG signals, which are based on the sEMG of the forearm muscles of human hand movement, and uses the 20 order comb filter and wavelet threshold to preprocess the signal, and uses the root mean square, wavelength and nonlinear characteristics sample entropy in time domain as three eigenvalues to construct the input feature vectors of the subsequent action classifier. Finally, the recognition of the hand movements is realized successfully through GRNN and SVM. The recognition rate is 98.64% in SVM classifier and 96.27% in GRNN classifier. Experimental results show that the SVM classifier is better than the GRNN classifier.

show abstract

Section: Hand Movement Recognition Based On Svm and Grnnmentioning

confidence: 99%

Surface EMG data aggregation processing for intelligent prosthetic action recognition

Jiang

et al. 2018

Neural Comput & Applic

Self Cite

107

View full text Add to dashboard Cite

show abstract

“…Aiming at the advantages and disadvantages of the above gesture segmentation method, this paper adopts the segmentation method combining depth information and color information. two-dimensional array is mapped with the depth image [15], and then the gesture coordinate points in the depth coordinate space after the mapping process are converted into a color coordinate space, and finally displayed in color, as shown in Figure 1.…”

Section: Related Workmentioning

confidence: 99%

“…Calculate the difference between each sample data and the mean: (15) The covariance matrix for all samples is: ∈ℜ , Where l is the dimension reduction dimension, the larger l is, the more eigenvectors are in reduce U , the original feature data will not be lost a lot, the error will be smaller, and the size of l is determined by the contribution rate of eigenvalues, that is:…”

Section: Dimensionality Reduction Of Feature Datamentioning

confidence: 99%

Research on gesture recognition of smart data fusion features in the IoT

Tan

Sun

et al. 2019

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

With the rapid development of Internet of Things (IoT) technology, the interaction between people and things has become increasingly frequent. Use simple gestures instead of complex operations to interact with the machine, the fusion of smart data feature information and so on has gradually become a research hotspot. Considering that the depth image of the Kinect sensor lacks color information and is susceptible to depth thresholds, this paper proposes a gesture segmentation method based on the fusion of color information and depth information, in order to ensure the complete information of the segmentation image, a gesture feature extraction method based on Hu invariant moment and HOG feature fusion is proposed, by determining the optimal weight parameters, the global and local features are effectively fused. Finally, the SVM classifier is used to classify and identify gestures. The experimental results show that the proposed fusion features method has a higher gesture recognition rate and better robustness than the traditional method.

show abstract

“…During the operation of the loading excavator, various sensors are used to monitor various data of the cooling system [18,19]. These data include video and pictures of the radiator, temperature parameters, etc [20,21]. Using sensors to obtain large amounts of data for condition assessment can help us adjust the cooling system to achieve the best condition [22].…”

Section: Test Instrument and Data Acquisition Point Arrangementmentioning

confidence: 99%

Heat Dissipation Performance of Loader-Digger Cooling System based on Simulation and Test Data

Chen

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

High temperature of the radiator group is harmful to the power system and hydraulic system. In order to improve the heat dissipation performance of the loader, the flow field characteristics of the cooling chamber are analyzed by simulation and heat balance test. Firstly, the mathematical model of heat flow is established. Secondly, the flow field in the cooling chamber under different speeds is simulated based on CFX. And then the influence of fan position and internal flow field distribution on radiator performance is studied. Through the simulation of four different distances, it is concluded that the optimal distance between cooling fan and radiator is 76mm. Finally, a testing system is built for the temperature acquisition of engine water radiator, torque converter oil radiator, hydraulic oil radiator and air-to-air cooler of the hood structure, and then the simulation results are verified. The test results show that the heat dissipation performance of the whole machine meets the requirements after optimization, and the optimized scheme can make the loader-digger in an efficient and energy-saving operation state.

show abstract

Gesture recognition based on skeletonization algorithm and CNN with ASL database

Cited by 142 publications

References 28 publications

Surface EMG data aggregation processing for intelligent prosthetic action recognition

Surface EMG data aggregation processing for intelligent prosthetic action recognition

Research on gesture recognition of smart data fusion features in the IoT

Heat Dissipation Performance of Loader-Digger Cooling System based on Simulation and Test Data

Contact Info

Product

Resources

About