Abstract
Human action recognition has turned into one of the most attractive and demanding fields of research in computer vision and pattern recognition for facilitating easy, smart, and comfortable ways of human-machine interaction. With the witnessing of massive improvements to research in recent years, several methods have been suggested for the discrimination of different types of human actions using color, depth, inertial, and skeleton information. Despite having several action identification methods using different modalities, classifying human actions using skeleton joints information in 3-dimensional space is still a challenging problem. In this paper, we conceive an efficacious method for action recognition using 3D skeleton data. First, large-scale 3D skeleton joints information was analyzed and accomplished some meaningful pre-processing. Then, a simple straight-forward deep convolutional neural network (DCNN) was designed for the classification of the desired actions in order to evaluate the effectiveness and embonpoint of the proposed system. We also conducted prior DCNN models such as ResNet18 and MobileNetV2, which outperform existing systems using human skeleton joints information.
Highlights
Over the past years, various machines such as computers, mobiles, and cameras have been introduced by many scholars with the massive improvement of modern science
We are grasping the use of wireless mouses, keyboards, and headphones, as well as many other digital devices to interact with systems in luxurious and comfortable ways when performing desired tasks
Illustrated a new technique for skeleton data where the most informative distance and the angle between joints were taken as a feature set, and deep neural network was used for action recognition
Summary
Various machines such as computers, mobiles, and cameras have been introduced by many scholars with the massive improvement of modern science. Computer vision-based methods, for instance hand gesture recognition, gait recognition, human action recognition, and pose estimation, are the most popular in today’s research era. Hand gesture recognition has gained extensive popularity in terms of communicating with the devices, those interacting with objects in augmented and virtual reality. With the advantage of low cost, portability, and easy to use sensors, action recognition has become a popular research field among contemporary researchers. Nowadays, using these sensors, we get some renowned and perfect datasets, which are used in experiments. Many handcrafted methods were proposed for the extraction of distinctive features from the skeleton data of the actions in order to perform the recognition. Deep learning networks including recurrent neural network (RNN) or CNN were used largely for skeleton-based action recognition in the last few years
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
