At present, the human interaction behavior algorithm has received great attention, but how to effectively extract the interactive characteristics of human interaction and establish the complex model between multiple targets is still a difficult problem. Aiming at this problem, we proposed a human interaction recognition method based on local spatial - temporal and global feature. This method treats people who are interacting as a whole. Firstly, foreground human object is extracted by the inter-frame difference. Secondly, the optical flow and space-time points of interest are extracted. Considering the large and high dimension of the feature, the characteristics of each frame image are described by the gradient direction histogram HOG and the optical flow histogram HOF. Then, BP neural network is used to classify each feature of each frame. Considering the limitations of different features for interactive behavior recognition, BP neural network combined with classification fusion is used to obtain the final interaction behavior category. The algorithm tested in the UT interaction dataset, and the experimental results show that this method can recognize the interaction behaviors of hitting, hugging, kicking, pushing and handshaking. The proposed method can be applied to intelligent video surveillance.

https://iopscience.iop.org/article/10.1088/1742-6596/1754/1/012188/pdf

Human Interaction Behavior Recognition based on Local Spatial - Temporal and Global Feature

Real-time Pedestrian Detection Based on Edge Factor and Histogram of Oriented Gradient

Compared with behavior recognition based on RGB images and videos, bone behavior recognition is less susceptible to environmental factors and has stronger robustness. Therefore, in recent years, it has attracted extensive attention in the field of human behavior recognition. The information of adjacent nodes is only contained in the adjacency matrix defined in the traditional Graph Convolution Networks (GCNs), and the non-adjacent nodes which contain important potential information of bone posture are ignored. To solve this problem, a new division strategy of skeleton joint based on Two Stream Adaptive Graph Convolutional Network (2S-AGCN) is proposed in this paper, and the division rule is changed from the original three partitions to five partitions. Compared with the original method, the relationship between physical connection and non-physical connection between skeleton joints is strengthened by the new method. Finally, through experimenting on large data set NTU-RGB+D. The classification accuracy of Top-1 on X-Sub and X-View of NTU-RGB+D data set is 88.6% and 95.5% respectively, which is improved by 0.1% and 0.4% compared with the original model. The performance of this method is demonstrated in the experimental results.

2S-AGCN Human Behavior Recognition Based on New Partition Strategy

Compared with behavior recognition based on RGB images and videos, bone behavior recognition is less susceptible to environmental factors and has stronger robustness. Therefore, in recent years, it has attracted extensive attention in the field of human behavior recognition. The information of adjacent nodes is only contained in the adjacency matrix defined in the traditional Graph Convolution Networks (GCNs), and the non-adjacent nodes which contain important potential information of bone posture are ignored. To solve this problem, a new division strategy of skeleton joint based on Two Stream Adaptive Graph Convolutional Network (2S-AGCN) is proposed in this paper, and the division rule is changed from the original three partitions to five partitions. Compared with the original method, the relationship between physical connection and non-physical connection between skeleton joints is strengthened by the new method. Finally, through experimenting on large data set NTU-RGB+D. The classification accuracy of Top-1 on X-Sub and X-View of NTU-RGB+D data set is 88.6% and 95.5% respectively, which is improved by 0.1% and 0.4% compared with the original model. The performance of this method is demonstrated in the experimental results. 

In response to the problem where many existing research models only consider acquiring the temporal information between sequences of continuous skeletons and in response to the lack of the ability to model spatial information, this study proposes a model for recognizing worker falls and lays out abnormal behaviors based on human skeletal key points and a spatio-temporal graph convolutional network (ST-GCN). Skeleton extraction of the human body in video sequences was performed using Alphapose. To resolve the problem of graph convolutional networks not being effective enough for skeletal key points feature aggregation, we propose an NAM-STGCN model that incorporates a normalized attention mechanism. By using the activation function PReLU to optimize the model structure, the improved ST-GCN model can more effectively extract skeletal key points action features in the spatio-temporal dimension for the purposes of abnormal behavior recognition. The experimental results show that our optimized model achieves a 96.72% accuracy for recognition on the self-built dataset, which is 4.92% better than the original model; the model loss value converges below 0.2. Tests were performed on the KTH and Le2i datasets, which are both better than typical classification recognition networks. The model can precisely identify abnormal human behaviors, facilitating the detection of abnormalities and rescue in a timely manner and offering novel ideas for smart site construction.

https://www.mdpi.com/2079-9292/12/13/2915/pdf?version=1688367716

Worker Abnormal Behavior Recognition Based on Spatio-Temporal Graph Convolution and Attention Model

Human behavior analysis is a hot research in the field of computer vision. It has broad application prospects in the fields of intelligent monitoring, human-computer interaction, motion analysis and virtual reality. In order to improve the accuracy of human behavior recognition, a human behavior recognition method based on HOG feature and SVM classifier is proposed. First, the HOG features of the training set and the test set are extracted. Then, the multi-class problem is transformed into multiple dual-class problems, and multiple SVM classifiers are trained by using the HOG features. Finally, the trained classifiers are employed to recognize the human walking and waving behavior. Experimental results show that the recognition rate of walking and waving is 87.5% for the UIUC database. The human behavior recognition method proposed in this paper can effectively improve the recognition rate.

Qing Cai

Papers

Human Behavior Recognition Algorithm Based on HOG Feature and SVM Classifier