Acta Optica Sinica, Volume. 40, Issue 2, 0215002(2020)
SAR Ship Detection Based on Convolutional Neural Network with Deep Multiscale Feature Fusion
Fig. 1. Network structure of DMFFCNN
Fig. 2. Diagram of feature fusion. (a) The first feature fusion; (b) the second feature fusion
Fig. 3. Feature prediction map generator
Fig. 4. Classification loss function for different λ
Fig. 5. Intensive ship slices in complex background
Fig. 6. Curves of AP
Fig. 7. Comparison of detection results
Fig. 8. Comparison of detection results of DMFFCNN when λ=0 and λ=3. (a) Detection results of SAR surface ships in scene interference when λ=0 ; (b) detection results of SAR surface ships in scene interference when λ=3; (c) detection results of SAR inshore ships in scene interference when λ=0; (d) detection results of SAR inshore ships in scene interference when λ=3
|
|
|
Get Citation
Copy Citation Text
Long Yang, Juan Su, Hua Huang, Xiang Li. SAR Ship Detection Based on Convolutional Neural Network with Deep Multiscale Feature Fusion[J]. Acta Optica Sinica, 2020, 40(2): 0215002
Category: Machine Vision
Received: Jul. 30, 2019
Accepted: Sep. 9, 2019
Published Online: Jan. 2, 2020
The Author Email: Su Juan (yangl03@mail.nwpu.edu.cn)