# Complex-Scene SAR Aircraft Recognition Combining Attention Mechanism and Inner Convolution Operator

## TL;DR

This paper introduces a new model for identifying aircraft in SAR images using attention mechanisms and inner convolution to improve accuracy and speed in complex backgrounds.

## Contribution

The novel YOLOv7-MTI model combines attention mechanisms and involution for enhanced aircraft recognition in SAR images.

## Key findings

- The YOLOv7-MTI model achieved 93.51% mAP and 96.45% mRecall on the SAR-AIRcraft-1.0 dataset.
- It outperformed Faster R-CNN, SSD, YOLOv5, YOLOv7, and YOLOv8 in both accuracy and speed.
- The model improved mAP by 1.47% and FPS by 8.27% compared to the basic YOLOv7.

## Abstract

Synthetic aperture radar (SAR), as an active microwave imaging system, has the capability of all-weather and all-time observation. In response to the challenges of aircraft detection in SAR images due to the complex background interference caused by the continuous scattering of airport buildings and the demand for real-time processing, this paper proposes a YOLOv7-MTI recognition model that combines the attention mechanism and involution. By integrating the MTCN module and involution, performance is enhanced. The Multi-TASP-Conv network (MTCN) module aims to effectively extract low-level semantic and spatial information using a shared lightweight attention gate structure to achieve cross-dimensional interaction between “channels and space” with very few parameters, capturing the dependencies among multiple dimensions and improving feature representation ability. Involution helps the model adaptively adjust the weights of spatial positions through dynamic parameterized convolution kernels, strengthening the discrete strong scattering points specific to aircraft and suppressing the continuous scattering of the background, thereby alleviating the interference of complex backgrounds. Experiments on the SAR-AIRcraft-1.0 dataset, which includes seven categories such as A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and others, show that the mAP and mRecall of YOLOv7-MTI reach 93.51% and 96.45%, respectively, outperforming Faster R-CNN, SSD, YOLOv5, YOLOv7, and YOLOv8. Compared with the basic YOLOv7, mAP is improved by 1.47%, mRecall by 1.64%, and FPS by 8.27%, achieving an effective balance between accuracy and speed, providing research ideas for SAR aircraft recognition.