Laser & Optoelectronics Progress, Volume. 60, Issue 20, 2028004(2023)
Remote Sensing Target Detection Based on Multilevel Self-Attention Enhancement
Fig. 1. Schematic of midpoint offset representation method
Fig. 2. Schematic of Rotated RoIAlign
Fig. 3. Overall framework of the proposed algorithm
Fig. 4. Swin Transformer Block structure
Fig. 5. Comparison between MSA principle and W-MSA principle
Fig. 6. Comparison betwwen W-MSA principle and SW-MSA principle
Fig. 7. Some samples in DOTA dataset
Fig. 8. Some samples in HRSC2016 dataset
Fig. 9. Detection results of different algorithms on DOTA dataset
Fig. 10. Detection results of different algorithms on HRSC2016 dataset
Fig. 11. Detection speed and accuracy of different algorithms on DOTA dataset
|
|
|
|
|
Get Citation
Copy Citation Text
Xiegen Wei, Lin Cao, Shu Tian, Kangning Du, Peiran Song, Yanan Guo. Remote Sensing Target Detection Based on Multilevel Self-Attention Enhancement[J]. Laser & Optoelectronics Progress, 2023, 60(20): 2028004
Category: Remote Sensing and Sensors
Received: Nov. 14, 2022
Accepted: Jan. 4, 2023
Published Online: Sep. 28, 2023
The Author Email: Tian Shu (tianshu_0202@126.com)