Image Preprocessing Framework for Time-domain Astronomy in the Artificial Intelligence Era

Abstract The rapid advancement of image analysis methods in time-domain astronomy, particularly those leveraging artificial intelligence (AI) algorithms, has highlighted efficient image preprocessing as a critical bottleneck affecting algorithm performance. Image preprocessing, which involves standardizing images for training or deployment of various AI algorithms, encompasses essential steps such as image quality evaluation, alignment, stacking, background extraction, gray-scale transformation, cropping, source detection, astrometry, and photometry. Historically, these algorithms were developed independently by different research groups, primarily based on central processing unit (CPU) architecture for small-scale data processing. This paper introduces a novel framework for image preprocessing that integrates key algorithms specifically modified for graphics processing unit architecture, enabling large-scale image preprocessing for different algorithms. To prepare for the new algorithm design paradigm in the AI era, we have implemented two operational modes in the framework for different application scenarios: eager mode and pipeline mode. The Eager mode facilitates real-time feedback and flexible adjustments, which could be used for parameter tuning and algorithm development. The pipeline mode is primarily designed for large-scale data processing, which could be used for training or deploying of AI models. We have tested the performance of our framework using simulated and real observation images. Results demonstrate that our framework significantly enhances image preprocessing speed while maintaining accuracy levels comparable to CPU-based algorithms. To promote accessibility and ease of use, a Docker version of our framework is available for download in the PaperData Repository powered by China-VO, compatible with various AI algorithms developed for time-domain astronomy research.