Application of Ghost-DeblurGAN to Fiducial Marker Detection
This addresses motion blur issues for robotic applications using fiducial markers, but is incremental as it adapts existing deblurring methods to a specific domain.
The paper tackles the problem of fiducial marker detection failure due to motion blur in robotics by developing Ghost-DeblurGAN, a lightweight GAN for real-time deblurring, and introduces the YorkTag dataset, showing that it significantly improves marker detection.
Feature extraction or localization based on the fiducial marker could fail due to motion blur in real-world robotic applications. To solve this problem, a lightweight generative adversarial network, named Ghost-DeblurGAN, for real-time motion deblurring is developed in this paper. Furthermore, on account that there is no existing deblurring benchmark for such task, a new large-scale dataset, YorkTag, is proposed that provides pairs of sharp/blurred images containing fiducial markers. With the proposed model trained and tested on YorkTag, it is demonstrated that when applied along with fiducial marker systems to motion-blurred images, Ghost-DeblurGAN improves the marker detection significantly. The datasets and codes used in this paper are available at: https://github.com/York-SDCNLab/Ghost-DeblurGAN.