Improving detection accuracy of low-resolution objects remains a challenging task in the field of photoelectric detection, and image super-resolution (SR) is one of the vital processing methods that contribute to improving detection accuracy. Current infrared SR algorithms are mostly based on fixed integer scaling factors, but in practical applications, the ability to represent images at arbitrary resolutions is crucial for object detection. This study proposes a method named YOLOArbSR based on arbitrary-scale SR reconstruction to address the problem of low detection accuracy in low-resolution shortwave infrared images. We optimized the super-resolution algorithm to accommodate arbitrary scale factor for detecting infrared targets using the implicit representation function. Furthermore, we introduce a local texture estimator (LTE) and tune the network hyperparameters. Experiments on the practical dataset obtained from the experimental infrared system show that our proposed method is superior to existing technologies in improving the accuracy of infrared detection.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.