基于多维特征的舰载机舰面作业识别OA

[Objective]To address the challenges brought by unique flight operational scenarios and insuffi-cient public data for carrier flight deck operations,this study proposes a recognition method based on multi-dimensional features.[Methods]First,key points such as deck passage boundaries and static obstacles are accurately selected to represent the environmental information.Interactions between dynamic operational par-ticipants and static deck facilities are modelled using graph convolutional networks to explore their underlying connections of deck operation interaction relationships.Then,a multi-scale spatio-temporal feature extraction(MS-STFE)module is designed,incorporating a dilated attention mechanism that captures key individual in-teractions at both global and local levels by applying different dilation rates.At the same time,temporal con-volutional networks(TCN)combined with the attention mechanism are employed to extract temporal interac-tion features,efficiently capturing dynamic relationships across both long and short sequences.Finally,the MS-STFE module is stacked multiple times to adaptively extract multi-dimensional features,thereby improv-ing the recognition accuracy of carrier flight deck operations.[Results]Experiments conducted on a self-constructed dataset featuring multi-perspective carrier flight deck operation scenarios involving heterogeneous deck operation entities demonstrate that the proposed method significantly outperforms existing group activity recognition models such as ARG,DIN,AT,and GroupFormer,achieving an accuracy of 97.8%.[Conclusion]This study provides a valuable reference for the high-accuracy recognition of carrier flight deck operations.