SAR target identification method based on auxiliary classification generative adversarial network
A target recognition and network technology, which is applied in scene recognition, character and pattern recognition, instruments, etc., can solve the problems of insufficient samples and excessive dependence on label samples, and achieve the effects of improving recognition performance, improving network recognition rate, and improving recognition accuracy
Active Publication Date: 2020-04-17
NORTHWESTERN POLYTECHNICAL UNIV +1
View PDF5 Cites 26 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The above-mentioned SAR target recognition methods can achieve certain results, but these methods are all supervised learning, and there are problems of insufficient samples and over-reliance on label samples.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] Building a Multi-Classification Model Based on Auxiliary Classification Generative Adversarial Networks
[0032] The functional block diagram of multi-classification model based on AC-GAN is as follows: figure 1 shown. figure 1 The AC-GAN in AC-GAN consists of a discriminator D and a generator G. The present invention proposes to change the upsampling convolutional neural network in the generator G to a deconvolutional neural network. The input is the category label C distribution of the sample and the independent Based on the random noise z vector of the category label C, using ACGAN to add label constraints can improve the quality characteristics of the generated image. The generator G can output a high-resolution multi-category forged image that is very close to the real image by learning the characteristics of the real image; the discriminator D The Leaky ReLU non-linear output CNN network is used, and the real sample X real and fake generated sample X fake The ima...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention relates to a new SAR image synthesis and SAR target recognition method based on an auxiliary classification generative adversarial network, and the method comprises the steps: carrying out the expansion of a training sample library in a process of generating a high-resolution SAR image through employing the auxiliary classification generative adversarial network of a generator basedon a deconvolution neural network. According to the method, the discrimination network of the auxiliary classification generative adversarial network not only can identify the authenticity of the SARimage to obtain the category label of the corresponding SAR image, but also can generate a large number of high-resolution SAR image samples containing category labels on the basis of improving the network identification rate in the process of adversarial training of the generative network.
Description
technical field [0001] The invention relates to a synthetic aperture radar (Synthetic Aperture Radar, SAR) target recognition method, which can be applied to an image processing system. Background technique [0002] In modern high-tech warfare, the timely and accurate acquisition of battlefield information and the efficient assessment of the battlefield situation play a very important role in the struggle for military dominance on the battlefield. SAR has a certain ability to penetrate the ground and vegetation, which is helpful to find man-made construction targets such as airports, ports, bridges, and roads, as well as military targets such as aircraft, tanks, and ships. As an important microwave imaging sensor, SAR images are widely used in the fields of environmental monitoring, resource exploration, national defense and military affairs. SAR target recognition uses SAR image information to realize the determination of target types, models and other attributes. It has c...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/13G06F18/22G06F18/214G06F18/241
Inventor 王健秦春霞杨珂任萍
Owner NORTHWESTERN POLYTECHNICAL UNIV