Adaptive Detection of Fast Moving Celestial Objects Using a Mixture of Experts and Physical-Inspired Neural Network
Peng Jia, Ge Li, Bafeng Cheng, Yushan Li, Rongyu Sun
TL;DR
The paper introduces a hybrid FMCB detection framework that blends physics-informed neural networks with a mixture-of-experts (MoE) approach to handle diverse space- and ground-based observing modes. A PiNN encodes telescope PSF and relative motion into the input, guiding detection to distinguish FMCB from background stars, while two specialized detectors (E1: YOLOX-based and E2: CenterNet-based) are fused by a gating network. Training on 3000 simulated images across three observation modes, the MoE achieves state-of-the-art performance (e.g., mAP up to 99.26% on validation and strong results on real data), demonstrating robustness to background variations and mode changes. The work offers a scalable path to FMCB detection in heterogeneous observational data and outlines future directions for expanding experts, handling cosmic-ray noise, and leveraging semi-supervised labeling to improve real-data performance.
Abstract
Fast moving celestial objects are characterized by velocities across the celestial sphere that significantly differ from the motions of background stars. In observational images, these objects exhibit distinct shapes, contrasting with the typical appearances of stars. Depending on the observational method employed, these celestial entities may be designated as near-Earth objects or asteroids. Historically, fast moving celestial objects have been observed using ground-based telescopes, where the relative stability of stars and Earth facilitated effective image differencing techniques alongside traditional fast moving celestial object detection and classification algorithms. However, the growing prevalence of space-based telescopes, along with their diverse observational modes, produces images with different properties, rendering conventional methods less effective. This paper presents a novel algorithm for detecting fast moving celestial objects within star fields. Our approach enhances state-of-the-art fast moving celestial object detection neural networks by transforming them into physical-inspired neural networks. These neural networks leverage the point spread function of the telescope and the specific observational mode as prior information; they can directly identify moving fast moving celestial objects within star fields without requiring additional training, thereby addressing the limitations of traditional techniques. Additionally, all neural networks are integrated using the mixture of experts technique, forming a comprehensive fast moving celestial object detection algorithm. We have evaluated our algorithm using simulated observational data that mimics various observations carried out by space based telescope scenarios and real observation images. Results demonstrate that our method effectively detects fast moving celestial objects across different observational modes.