An Effective Lunar Crater Recognition Algorithm Based on Convolutional Neural Network

The lunar crater recognition plays a key role in lunar exploration. Traditional crater recognition methods are mainly based on the human observation that is usually combined with classical machine learning methods. These methods have some drawbacks, such as lacking the objective criterion. Moreover, they can hardly achieve desirable recognition results in small or overlapping craters. To address these problems, we propose a new convolutional neural network termed effective residual U-Net (ERU-Net) to recognize craters from lunar digital elevation model (DEM) images. ERU-Net first detects crater edges in lunar DEM data. Then, it uses template matching to compute the position and size of craters. ERU-Net is based on U-Net and uses the residual convolution block instead of the traditional convolution, which combines the advantages of U-Net and residual network. In ERU-Net, the size of the input image is the same as that of the output image. Since our network uses residual units, the training process of ERU-Net is simple, and the proposed model can be easily optimized. ERU-Net gets better recognition results when its network structure is deepened. The method targets at the rim of the crater, and it can recognize overlap craters. In theory, our proposed network can recognize all kinds of impact craters. In the lunar crater recognition, our model achieves high recall (83.59%) and precision (84.80%) on DEM. The recall of our method is higher than those of other deep learning methods. The experiment results show that it is feasible to exploit our network to recognize craters from the lunar DEM.