YL8C4Net: A Novel Algorithm for Target Source Detection and Classification in Astronomical Photometric Images

Abstract In the task of classifying massive celestial data, the accurate classification of galaxies, stars, and quasars usually relies on spectral labels. However, spectral data account for only a small fraction of all astronomical observation data, and the target source classification information in vast photometric data has not been accurately measured. To address this, we propose a novel deep learning-based algorithm, YL8C4Net, for the automatic detection and classification of target sources in photometric images. This algorithm combines the YOLOv8 detection network with the Conv4Net classification network. Additionally, we propose a novel magnitude-based labeling method for target source annotation. In the performance evaluation, the YOLOv8 achieves impressive performance with average precision scores of 0.824 for [email protected] and 0.795 for [email protected]:0.95. Meanwhile, the constructed Conv4Net attains an accuracy of 0.8895. Overall, YL8C4Net offers the advantages of fewer parameters, faster processing speed, and higher classification accuracy, making it particularly suitable for large-scale data processing tasks. Furthermore, we employed the YL8C4Net model to conduct target source detection and classification on photometric images from 20 sky regions in SDSS-DR17. As a result, a catalog containing about 9.39 million target source classification results has been preliminarily constructed, thereby providing valuable reference data for astronomical research.