Opto-Electronic Engineering, Volume. 50, Issue 12, 230242-1(2024)
A multi-target semantic segmentation method for millimetre wave SAR images based on a dual-branch multi-scale fusion network
Fig. 1. DBMFnet network structure diagram
Fig. 2. Feature fusion process
Fig. 3. Different feature fusion methods. (a) FCM; (b) FDM; (c) MSFM
Fig. 4. HM-SAR security images. (a) Back scanning image of the human body; (b) Frontal scanning image of the human body
Fig. 5. DBMFnet thermal diagram
Fig. 6. Test results of each model. Each row represents the test results of the same picture, and each column represents the test results of the same model. Black denotes the background, green denotes the wrench, yellow denotes the pistol, red denotes the hammer, and blue denotes the knife
Fig. 7. Baseline model
|
|
|
|
|
Get Citation
Copy Citation Text
Junhua Ding, Minghui Yuan. A multi-target semantic segmentation method for millimetre wave SAR images based on a dual-branch multi-scale fusion network[J]. Opto-Electronic Engineering, 2024, 50(12): 230242-1
Category: Research Articles
Received: Sep. 28, 2023
Accepted: Nov. 30, 2023
Published Online: Mar. 26, 2024
The Author Email: Yuan Minghui (袁明辉)