http://arxiv.org/abs/2002.09211
Wide field small aperture telescopes are widely used in optical transient observations. Detection and classification of astronomical targets are important steps during data post-processing stage. In this paper, we propose an astronomical targets detection and classification framework based on deep neural networks for images obtained by wide field small aperture telescopes. Our framework adopts the concept of the Faster R-CNN and we further propose to use a modified Resnet-50 as backbone network and a Feature Pyramid Network architecture in our framework. To improve the effectiveness of our framework and reduce requirements of large training set, we propose to use simulated images to train our framework at first and then modify weights of our framework with only a small amount of training data through transfer-learning. We have tested our framework with simulated and real observation data. Comparing with the traditional source detection and classification framework, our framework has better detection ability, particularly for dim astronomical targets. To unleash the transient detection ability of wide field small aperture telescopes, we further propose to install our framework in embedded devices to achieve real-time astronomical targets detection abilities.
P. Jia, Q. Liu and Y. Sun
Mon, 24 Feb 20
3/49
Comments: Submitted to AAS journal. The complete code can be downloaded from this https URL This code can be directly used to process images obtained by WFSATs. Images obtained by ordinary sky survey telescopes can also be processed with this code, however more annotated images are required to train the neural network