<abstract xmlns="http://www.w3.org/1999/xhtml"><p>In view of the uncontrollable process of traditional GAN generating remote sensing target images, the shortcomings of generated samples are similar, and lack diversity. This paper proposes a generative confrontation network model based on background conditions. First, the computer vision attention mechanism is introduced into the generative confrontation network. Choose a learning target model so that the GAN network only learns the target model during training, and ignores other non-target information. Reduce the dependence on the number of samples in the GAN training process; secondly, use the U-net network as a generator to restore other non-target information when generating the remote sensing image of the target as much as possible; again, distinguish by different colors of the conditional mask The category of the generated target; at the same time, the L1 regularization loss is added to the loss term of the generator model, and finally, the remote sensing target image is generated. The experimental results show that the peak signal-to-noise ratio (PSNR) of the remote sensing image generation algorithm proposed in this paper reached 18.512, and the structural similarity (SSIM) reached 88.47%, which is better than the comparison test model where the generator is an ordinary autoencoder.</p></abstract>

In view of the uncontrollable process of traditional GAN generating remote sensing target images, the shortcomings of generated samples are similar, and lack diversity. This paper proposes a generative confrontation network model based on background conditions. First, the computer vision attention mechanism is introduced into the generative confrontation network. Choose a learning target model so that the GAN network only learns the target model during training, and ignores other non-target information. Reduce the dependence on the number of samples in the GAN training process; secondly, use the U-net network as a generator to restore other non-target information when generating the remote sensing image of the target as much as possible; again, distinguish by different colors of the conditional mask The category of the generated target; at the same time, the L1 regularization loss is added to the loss term of the generator model, and finally, the remote sensing target image is generated. The experimental results show that the peak signal-to-noise ratio (PSNR) of the remote sensing image generation algorithm proposed in this paper reached 18.512, and the structural similarity (SSIM) reached 88.47%, which is better than the comparison test model where the generator is an ordinary autoencoder.

Conditional GAN-based Remote Sensing Target Image Generation Method

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Conditional GAN-based Remote Sensing Target Image Generation Method"}

In view of the uncontrollable process of traditional GAN generating remote sensing target images, the shortcomings of generated samples are similar, and lack...

Image generation network	SSIM
The method of this paper	88.47%
A generation model with nine residual blocks	81.65%
A generating model with six residual blocks	76.31%

Inputs	Type	Kernel	Batch Normalization	Activation Function	Outputs
256x256	conv	4x4	YES	LeakyReLU	128x128
128x128	conv	4x4	YES	LeakyReLU	64x64
64x64	conv	4x4	YES	LeakyReLU	32x32
32x32	conv	4x4	YES	LeakyReLU	31x31
31x31	conv	4x4	YES	LeakyReLU	30x30

Operating system	Ubuntu 18.04 LTS 64bit
CPU	Intel(R )Xeon(R) Gold 5118 CPU@2.30GHz
GPU	Nvidia GeForece TITAN Xp
Memory	32G
programing language	Python3.6.1
compiler	Pycharm2018.3
Deep learning framework	pytorch 0.4

Inputs	Type	Kernel	Batch Normalization	Activation Function	Outputs
256x256	conv	4x4	YES	RELU	128x128
128x128	conv	4x4	YES	RELU	64x64
64x64	conv	4x4	YES	RELU	32x32
32x32	conv	4x4	YES	RELU	16x16
16x16	conv	4x4	YES	RELU	8x8
8x8	conv	4x4	YES	RELU	4x4
4x4	conv	4x4	YES	RELU	2x2
2x2	conv	4x4	YES	RELU	1x1
1x1	deconv	4x4	YES	RELU	2x2
2x2	deconv	4x4	YES	RELU	4x4
4x4	deconv	4x4	YES	RELU	8x8
8x8	deconv	4x4	YES	RELU	16x16
16x16	deconv	4x4	YES	RELU	32x32
32x32	deconv	4x4	YES	RELU	64x64
64x64	deconv	4x4	YES	RELU	128x128
128x128	deconv	4x4	YES	RELU	256x256

Conditional GAN-based Remote Sensing Target Image Generation Method

Publié en ligne: 11 janv. 2021

Pages: 66 - 74

DOI: https://doi.org/10.21307/ijanmc-2020-039

Mots clés
Remote Sensing Target Image, Conditional GAN, U-net, Conditional Mask

© 2020 Haoyang Liu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

COMPARISON OF PSNR EVALUATION RESULTS

DISCRIMINATOR MODEL NETWORK STRUCTURE PARAMETER TABLE

EXPERIMENTAL ENVIRONMENT

GENERATOR MODEL NETWORK STRUCTURE PARAMETER TABLE

Conditional GAN-based Remote Sensing Target Image Generation Method

Publié en ligne: 11 janv. 2021

Pages: 66 - 74

DOI: https://doi.org/10.21307/ijanmc-2020-039

Mots clésRemote Sensing Target Image, Conditional GAN, U-net, Conditional Mask

© 2020 Haoyang Liu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Figure 11.

COMPARISON OF PSNR EVALUATION RESULTS

DISCRIMINATOR MODEL NETWORK STRUCTURE PARAMETER TABLE

EXPERIMENTAL ENVIRONMENT

GENERATOR MODEL NETWORK STRUCTURE PARAMETER TABLE

Mots clés
Remote Sensing Target Image, Conditional GAN, U-net, Conditional Mask