Crossterm-free time-frequency representation exploiting deep convolutional neural network

Zhang, Shuimei; Pavel, Md. Saidur Rahman; Zhang, Yimin D.

doi:10.1016/j.sigpro.2021.108372

Cited by 22 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…12 for four desired angles. The estimated rotation angles, δR of the SAR images synthesized with c 1 calculated by (26), is given in this panel, as well, and we can see that it is close to the desired ones, δ Rd .…”

Section: Real Sar Images With Suppressed Backgroundsupporting

confidence: 55%

“…To know a target or scene for analysis, detection, or classification, it is desirable to have its SAR image acquired from different positions [26], [27]. Different relative viewing angles (resulting from changes of flight direction or target movement in different revisits) results in a kind of target rotation in SAR image.…”

Section: A Basic Sar Principlesmentioning

confidence: 99%

“…The InfoGAN described above (Tables I and II values, c 1 , for these rotations are calculated using (26). Then the InfoGAN produced the synthesized SAR images, shown in Fig.…”

Section: A Simulated Sar Imagesmentioning

confidence: 99%

“…6. For each case, we have synthesized SAR images for four desired δ Rd , δ Sd , and δ Ad , respectively, using c 1 calculated by (26). The estimated properties of the synthesized SAR images, δ R , δ S , and δ A are measured by (19).…”

Section: B Real Object From a Sar Image With Simulated Propertiesmentioning

confidence: 99%

“…3) Two properties -Two latent codes: In this experiment, we consider two entangled properties emerging in each training SAR image simultaneously. Firstly, we generate three (26) for four desired δ Rd , δ Sd , and δ Ad . The estimated properties of the synthesized SAR images, δ R , δ S , and δ A are measured by (19).…”

Section: B Real Object From a Sar Image With Simulated Propertiesmentioning

confidence: 99%

See 4 more Smart Citations

Analytical Interpretation of Latent Codes in InfoGAN with SAR Images

Feng¹,

Daković²,

Ji³

et al. 2022

Preprint

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) can synthesize abundant photo-realistic synthetic aperture radar (SAR) images. Some recent GANs (e.g., InfoGAN), are even able to edit specific properties of the synthesized images by introducing latent codes. It is crucial for SAR image synthesis since the targets in real SAR images are with different properties due to the imaging mechanism. Despite the success of InfoGAN in manipulating properties, there still lacks a clear explanation of how these latent codes affect synthesized properties, thus editing specific properties usually relies on empirical trials, unreliable and time-consuming. In this paper, we show that latent codes are disentangled to affect the properties of SAR images in a non-linear manner. By introducing some property estimators for latent codes, we are able to provide a completely analytical nonlinear model to decompose the entangled causality between latent codes and different properties. The qualitative and quantitative experimental results further reveal that the properties can be calculated by latent codes, inversely, the satisfying latent codes can be estimated given desired properties. In this case, properties can be manipulated by latent codes as we expect.

show abstract

Section: Real Sar Images With Suppressed Backgroundsupporting

confidence: 55%

Section: A Basic Sar Principlesmentioning

confidence: 99%

“…The InfoGAN described above (Tables I and II values, c 1 , for these rotations are calculated using (26). Then the InfoGAN produced the synthesized SAR images, shown in Fig.…”

Section: A Simulated Sar Imagesmentioning

confidence: 99%

Section: B Real Object From a Sar Image With Simulated Propertiesmentioning

confidence: 99%

Section: B Real Object From a Sar Image With Simulated Propertiesmentioning

confidence: 99%

See 3 more Smart Citations