Sonar image automatic target identification method based on neural network visualization
A technology for automatic target recognition and sonar images, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems affecting generalization ability, increase method labor costs, etc., and achieve the effect of reducing labor and time costs
- Application Information
AI Technical Summary
Problems solved by technology
 The present invention will be described in further detail below with reference to the accompanying drawings.
 like figure 1 As shown, the method for automatic target recognition of sonar images based on neural network visualization proposed by the present invention mainly includes four steps:
 1) Use the ResNet-18 classification backbone network and the Grad-CAM neural network to visually build an automatic target recognition model; wherein, the Grad-CAM module is placed in front of the fully connected layer of the ResNet-18 classification backbone network;
 2) Build a shape preference data set based on ImageNet optical data set and adaptive instance regularization style transfer technology, use the shape preference data set to pre-train the automatic target recognition model, and obtain pre-training parameters that are robust to shape features,
 3) Using the sonar images marked with the sample categories as the training set, retrain the...
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction