AUTHOR=Tang Yumin , Fan Jing , Qu Jinshuai TITLE=High-quality facial-expression image generation for UAV pedestrian detection JOURNAL=Frontiers in Space Technologies VOLUME=3 YEAR=2022 URL=https://www.frontiersin.org/journals/space-technologies/articles/10.3389/frspt.2022.1014183 DOI=10.3389/frspt.2022.1014183 ISSN=2673-5075 ABSTRACT=

For UAV pedestrian detection in the wild with perturbed parameters, such as lighting, distance, poor pixel and uneven distribution, traditional methods of image generation cannot accurately generate facial-expression images for UAV pedestrian detection. In this study, we propose an improved PR-SGAN (perceptual-remix-star generative adversarial network) method, which combines the improved interpolation method, perceptual loss function, and StarGAN to achieve high-quality facial-expression image generation. Experimental results show that the proposed method for discriminator-parameter update improves the generated facial-expression images in terms of image-generation evaluation indexes (5.80 dB in PSNR and 24% in SSIM); the generated images for generator-parameter update have high robustness against color. Compared to the traditional StarGAN method, the generated images are significantly improved in high frequency details and textures.