Laser & Optoelectronics Progress, Volume. 57, Issue 24, 242805(2020)
Ship Object Detection of Remote Sensing Images Based on Adaptive Rotation Region Proposal Network
Fig. 1. Model structure of our network
Fig. 2. Structure diagram of MFPN. (a) Overall structure diagram; (b) specific connection diagram
Fig. 3. Structure diagram of AR-RPN
Fig. 4. Schematic diagram of deformable convolution
Fig. 5. Schematic diagram of IoU in an oblique frame. (a) Diagram1; (b) diagram2
Fig. 6. Loss function.(a) Anchor location loss;(b) anchor shape loss;(b) classification loss;(b)regression loss
Fig. 7. Test results of different methods. (a) RRPN; (b) AR-RPN; (c) MFPN
Fig. 8. Detection results of our method on different data sets. (a) HRSC2016 (b) DOTA
|
|
|
Get Citation
Copy Citation Text
Zhijing Xu, Ying Ding. Ship Object Detection of Remote Sensing Images Based on Adaptive Rotation Region Proposal Network[J]. Laser & Optoelectronics Progress, 2020, 57(24): 242805
Category: Remote Sensing and Sensors
Received: Jun. 15, 2020
Accepted: Jun. 24, 2020
Published Online: Dec. 1, 2020
The Author Email: Ding Ying (1405530454@qq.com)