The battlefield situation is rapidly changing, and effectively distinguishing the types of enemy aircraft used for military operations using visible light images is of great significance for seizing information dominance. In response to the issue of low target recognition accuracy caused by the diverse postures, inconsistent observation angles, and background occlusion in military aircraft, a coordinate channel attention deep learning network (VMamba-Coordinate Attention, VMamba-CA) for military aircraft recognition is proposed. This method utilizes the global receptive field characteristics of VMamba to extract features under different postures and introduces the CA (Coordinate Attention) mechanism to design the CAVSS module, enhancing the network's detailed perception ability for aircraft targets. Experimental results show that compared with traditional military aircraft recognition methods and other deep learning models, the VMamba-CA network significantly improves the classification accuracy, with an overall accuracy reaching 75%, and effectively enhancing our military's ability to classify enemy aircraft, thereby enhancing our military situational awareness capability.
Military aircraft identification algorithm based on coordinate channel attention mechanism
International Conference on Remote Sensing, Mapping, and Image Processing (RSMIP 2025) ; 2025 ; Sanya, China
Proc. SPIE ; 13650 ; 1365016
28.05.2025
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Small Target Spillage Detection Algorithm Based on Spatial Attention and Channel Attention Mechanism
Springer Verlag | 2025
|Allocation mechanism of military aircraft spares based on PHM
British Library Online Contents | 2011
|Engineering Index Backfile | 1961
Engineering Index Backfile | 1950
|