Dense Small Crater Detection Model Based on Key Point Detection for Lunar Permanently Shadowed Region Images

The craters widely distributed on the lunar surface constitute important landforms for investigating the geological activities and evolutionary history of the Moon. Currently, deep learning models have made certain progress in detecting craters, but they still have limitations in identifying numerous small craters. To address these challenges, this article puts forward a CenterNet-based dense small crater detection model (DSCraterNet), which is designed to precisely detect craters within the permanently shadowed regions (PSRs) by leveraging the previously released enhanced PSR images. DSCraterNet achieves precise crater localization by predicting keypoint heatmap (location), size, and offset of craters. The model employs an encoder–decoder network architecture that combines various feature fusion and attention mechanisms. Feature fusion strategies include direct fusion between the encoder and decoder, multiscale encoder spatial feature fusion (MSF) structure, and multielement information fusion (MEF) structure. These fusion strategies balance the relationship between high-resolution features, strong semantic features, and multiscale spatial features according to craters’ characteristics. Furthermore, by reasonably configuring attention-based layers [like efficient multiscale attention (EMA)] at different stages, the utilization efficiency of robust features is improved. Ultimately, DSCraterNet successfully identified a large number of densely packed small craters in PSR, revealing the terrain features of the region. A series of thorough ablation and comparative experiments has confirmed that DSCraterNet surpasses existing crater detection models in terms of precision, recall, mean average precision (mAP), and $F1$ -score metrics. Our code is available at https://github.com/dl-zfq/DSCraterNet