Abstract
Detecting weak celestial source signals from massive radio data is a very challenging task because the radiation received by radio telescope is very weak and prone to disturbances. In order to detect these weak signals, we propose a two-stage object detection method that performs more finely in computer vision tasks. The novelty of the proposed method is to combine traditional soft thresholding denoising methods with attention mechanisms in deep neural networks. We propose a channel attention shrinkage network as the backbone of the object detection model to extract the features of weak signals from celestial sources by removing noise-related information. Moreover, targeting the characteristics of celestial source fringes in phase images, we propose a cluster-based anchor boxes generation algorithm to improve the accuracy of fringes position detection. We also introduce the CIoU loss function to improve the performance of the model because of the large aspect ratio of the celestial source fringes in the phase image. We generate simulated celestial source fringes data based on the parameters of the observation system to train our model and conduct experiments to evaluate the performance of the proposed algorithm. Our model obtains satisfactory detection accuracy and accurate for the location of celestial source fringes.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
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.