Abstract

Inverse synthetic aperture radar (ISAR) image offers geometric and structural characteristics information of target objects. Thus, It is an important research topic to recognize radar targets based on ISAR images. ISAR imaging offers the advantages of all-day, all-weather, and ultra-long- distance imaging; however, ISAR image quality is affected by attitude angle, defocusing noise, resolution and other factors, resulting in inferior recognition performance. In contrast, optical images require more stringent imaging conditions, but they provide more feature diversity, resulting in a better recognition effect. Combining the advantages of ISAR images and optical images, the transformation from target ISAR images to optical images greatly improves the target recognition performance. In this study, an ISAR-to-optical image generation method was developed. Combined with two attention mechanisms and the SSIM loss function, a conditional generative adversarial network was constructed to transform ISAR images into optical images so that the generative model can realistically restore the details of the target images. In addition, a comparative test was conducted on a simulated aircraft target, and the performance of the proposed architecture was evaluated in terms of visual effects and quantitative indicators. The results show that the proposed method yields better generation effect. Furthermore, the target recognition case shows that the recognition rate obtained using the generated optical images is considerably higher than that obtained using the original ISAR images, further verifying the effectiveness of the generated image for target recognition.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.