Manifold Regularization Graph Structure Auto-Encoder to Detect Loop Closure for Visual SLAM

Loop closure detection plays a vital role in the visual simultaneous localization and mapping (SLAM) systems. In order to overcome the shortcomings of the artificial design algorithm to extract insufficient features, this paper proposes a graph-regularization stacked denoising auto-encoder (G-SDAE) network that achieves high detection accuracy and improve reliability. This method is based on the SDAE and the manifold learning graph regularization structure. The G-SDAE preserves the local abstract geometry structure between features through spatial mapping in manifold learning, and the G-SDAE network can automatically extract abstract features, avoiding relying on empirical design algorithms to extract low-quality visual features. Compared with the bag-of-words (BoW) method, the OpenFABMAP algorithm, and the traditional SDAE method, extensive experiments show that the proposed algorithm achieves superior performances and provides a feasible solution for the loop closure detection part of the visual SLAM.