Gesture Recognition Algorithm of Human Motion Target Based on Deep Neural Network
TL;DR: In this article, a gesture recognition algorithm of human motion based on deep neural network was proposed, where the Kinect interface equipment was used to collect the coordinate information of human skeleton joints, extract the characteristics of motion gesture nodes, and construct the whole structure of key node network by using deep neural networks.
read more
Abstract: There are some problems in the current human motion target gesture recognition algorithms, such as classification accuracy, overlap ratio, low recognition accuracy and recall, and long recognition time. A gesture recognition algorithm of human motion based on deep neural network was proposed. First, Kinect interface equipment was used to collect the coordinate information of human skeleton joints, extract the characteristics of motion gesture nodes, and construct the whole structure of key node network by using deep neural network. Second, the local recognition region was introduced to generate high-dimensional feature map, and the sampling kernel function was defined. The minimum space-time domain of node structure map was located by sampling in the space-time domain. Finally, the deep neural network classifier was constructed to integrate and classify the human motion target gesture data features to realize the recognition of human motion target. The results show that the proposed algorithm has high classification accuracy and overlap ratio of human motion target gesture, the recognition accuracy is as high as 93%, the recall rate is as high as 88%, and the recognition time is 17.8 s, which can effectively improve the human motion target attitude recognition effect.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Dynamic Gesture Contour Feature Extraction Method Using Residual Network Transfer Learning
Xianmin Ma,Xiaofeng Li +1 more
TL;DR: This method can effectively improve the recognition rate and type recognition accuracy of dynamic gestures contour features and shorten the time for dynamic gesture contour feature recognition, and the value is 0.92, with good comprehensive performance.
Multifeature Fusion Human Motion Behavior Recognition Algorithm Using Deep Reinforcement Learning
TL;DR: Wang et al. as discussed by the authors proposed a multifeature fusion human behavior recognition algorithm using deep reinforcement learning, where the attention model is constructed and the small sampling area is used as the model input.
Sports game teaching and high precision sports training system based on virtual reality technology
Yang Pan
TL;DR: This study integrates virtual reality technology with high-precision training to enhance college students' physical exercise efficiency and motivation, achieving a 6 mm error reduction in motion capture accuracy and a 712.407% cumulative variance explanation rate.
2
Real-Time Capture of Snowboarder’s Skiing Motion Using a 3D Vision Sensor
TL;DR: In this article, a real-time ski motion capture method of snowboarders based on a 3D vision sensor is proposed, which combines the Time of Fight (TOF) camera and high-speed vision sensor to form a motion acquisition system.
A Survey on Chinese Sign Language Recognition: From Traditional Methods to Artificial Intelligence
Xianwei Jiang,Yanqiong Zhang,Juan Lei,Yudong Zhang +3 more
TL;DR: This survey reviews 20 years of Chinese Sign Language Recognition (CSLR) research, transitioning from traditional methods (HMM, SVM, DTW) to AI-driven approaches (CNN, DNNs, CapsNet) with challenges in accuracy, robustness, and real-time performance.
2
References
Deep neural networks for bot detection
Sneha Kudugunta,Emilio Ferrara +1 more
TL;DR: This paper proposes a deep neural network based on contextual long short-term memory (LSTM) architecture that exploits both content and metadata to detect bots at the tweet level, and applies the same architecture to account-level bot detection, achieving nearly perfect classification accuracy.
A model-based gait recognition method with body pose and human prior knowledge
TL;DR: PoseGait exploits human 3D pose estimated from images by Convolutional Neural Network as the input feature for gait recognition and design spatio-temporal features from the3D pose to improve the recognition rate.
464
View-Invariant Deep Architecture for Human Action Recognition Using Two-Stream Motion and Shape Temporal Dynamics
TL;DR: Wang et al. as discussed by the authors proposed a deep view-invariant human action recognition framework, which is a novel integration of two important action cues: motion and shape temporal dynamics (STD), which are generated by approximate rank pooling (ARP) and processed by using fine-tuned InceptionV3 model.
126
View-invariant Deep Architecture for Human Action Recognition using late fusion.
TL;DR: This work proposes a deep view-invariant human action recognition framework, which is a novel integration of two important action cues: motion and shape temporal dynamics (STD), and outperforms existing state-of-the-arts significantly.
86
Recognition of green apples in an orchard environment by combining the GrabCut model and Ncut algorithm
TL;DR: Experimental results showed that the proposed GrabCut model for fruit region extraction of the salient fruits could accurately recognise green apples under natural light conditions.
57