Two stream skeleton behavior recognition algorithm based on Motif-GCN

Compared with RGB videos and images,human bone data is less vulnerable to external factors and has stronger robustness.Therefore,behavior recognition methods based on skeletons are widely studied.Because graph convolution network(GCN)can deal with the irregular topology data of hu-man skeletons very well,more and more researchers apply GCN to human behavior recognition.Tra-ditional graph convolution methods only consider the joints with physical connectivity or the same type when building the behavior recognition model based on human skeletons structure,which cannot capture higher-order information better.To solve this problem,Motif-GCN is used in this paper to ex-tract spatial features.The relationship between the joints with natural connection in the human body is encoded by the first Motif-GCN,and the possible relationship between the unconnected joints in the human skeleton is encoded by the second Motif-GCN.In this way,the relationship between non-physical joints can be strengthened.Then a two stream framework combining joint and bone informa-tion is used to capture more action information.Finally,experiments are conducted on two subdata-sets X-Sub and X-View of NTU-RGB+D,and the accuracy shown in Top-1 classification results is 89.5%and 95.4%respectively.The experimental results are 1.0%and 0.3%higher than those of the 2S-AGCN model respectively.The superiority of this method is also proved by the experimental results.

Association Strategy Graph Convolutional Neural Network for Human Skeletal Behavior Recognition

Aiming at the problem that the joint point partition strategy expresses the important information of the human body in the human body behavior recognition of bones cannot fully express the behavior,anRCTR-GCNhuman bone behavior recognition model of the correlation strategy is proposed.First,by adding an association strategy of a refined graph convolutional network model(CTR-GCN)of the smart channel topology,it can dynamically learn different topological structures and efficiently amplify the characteristics of the connection points in different channels while improving the key joint points of associated characteristics.Then,the network model redefines each channel by learning a shared topology and uses a specific channel relationship to unify the model through theoretical analysis;finally,redefining the model structure effectively reflects the associated information of local nodeswithin the channel.Action recognition has stronger aggregation capabilities.The results show that the recognition accuracy in the commonly used NTU RGB+D and NW-UCLA datasets reaches 93.6%(X-View),97.6%(XSub),and 97.2%,respectively.The experimental results show that the accuracy rate is improved.