TY - GEN
T1 - MSMANET
T2 - 2024 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2024
AU - Chang, Hao
AU - Chang, Shibo
AU - Guan, Jialin
AU - Fu, Xiongjun
AU - Guo, Kunyi
AU - Dong, Jian
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - With the rapid development of Synthetic Aperture Radar (SAR), the number and resolution of SAR images are constantly increasing. As a high-value target, aircraft detection has become a research hotspot in the field of SAR image interpretation. SAR aircraft have diverse postures, complex backgrounds, and small differences among different types of aircraft, which can easily lead to false detections. Meanwhile, some SAR aircraft have incomplete structures and are accompanied by speckle noise, which can easily lead to missed detections. To address the above issues, we propose an ultra-lightweight SAR aircraft detection network based on multi-scale matching attention (MSMANET). Firstly, we propose an ultra-lightweight backbone that extracts SAR gradient features through parallel processing of traditional convolution and Ghost modules. Secondly, aiming to the scale, shape and background information of aircraft, Multi-Scale Matching Attention (MSMA) is designed. MSMA performs feature aggregation and cross channel feature matching on multi receptive field feature maps, making the network more focused on feature maps suitable for detection. The mean average precision (mAP) of MSMANET on the SAR-AIRcraft1.0 dataset is as high as 98.4%, with the 1.6 GFLOPS, 657K parameter and 55.1 FPS. Compared to existing advanced networks, the performance has reached SOTA.
AB - With the rapid development of Synthetic Aperture Radar (SAR), the number and resolution of SAR images are constantly increasing. As a high-value target, aircraft detection has become a research hotspot in the field of SAR image interpretation. SAR aircraft have diverse postures, complex backgrounds, and small differences among different types of aircraft, which can easily lead to false detections. Meanwhile, some SAR aircraft have incomplete structures and are accompanied by speckle noise, which can easily lead to missed detections. To address the above issues, we propose an ultra-lightweight SAR aircraft detection network based on multi-scale matching attention (MSMANET). Firstly, we propose an ultra-lightweight backbone that extracts SAR gradient features through parallel processing of traditional convolution and Ghost modules. Secondly, aiming to the scale, shape and background information of aircraft, Multi-Scale Matching Attention (MSMA) is designed. MSMA performs feature aggregation and cross channel feature matching on multi receptive field feature maps, making the network more focused on feature maps suitable for detection. The mean average precision (mAP) of MSMANET on the SAR-AIRcraft1.0 dataset is as high as 98.4%, with the 1.6 GFLOPS, 657K parameter and 55.1 FPS. Compared to existing advanced networks, the performance has reached SOTA.
KW - aircraft detection
KW - attention mechanism
KW - lightweight network
KW - multiscale detection
KW - Synthetic Aperture Radar (SAR)
UR - http://www.scopus.com/inward/record.url?scp=85204886370&partnerID=8YFLogxK
U2 - 10.1109/IGARSS53475.2024.10641514
DO - 10.1109/IGARSS53475.2024.10641514
M3 - Conference contribution
AN - SCOPUS:85204886370
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 7960
EP - 7963
BT - IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 7 July 2024 through 12 July 2024
ER -