A dense RGB-D SLAM algorithm based on convolutional neural network of multi-layer image invariant feature

Simultaneous localization and mapping (SLAM) is one of the key technologies used in sweepers, autonomous vehicles, virtual reality and other fields. This paper presents a dense three-channel color images composed of red, green and blue and depth images SLAM reconstruction algorithm based on convolutional neural network (CNN) of multi-layer image invariant feature transformation. The main contribution of the system lies in the construction of a CNN based on multi-layer image invariant feature, which optimized the extraction of Oriented FAST and Rotated Brief(ORB) feature points and the reconstruction effect. After the feature point matching, pose estimation, loop detection and other steps, the 3D point clouds were finally spliced to construct a complete and smooth spatial model. The system can improve the accuracy and robustness in feature point processing and pose estimation. Comparative experiments show that the optimized algorithm saves 0.093 s compared to the ordinary extraction algorithm while guaranteeing a high accuracy rate at the same time. The results of reconstruction experiments show that the spatial models have more clear details, smoother connection with no fault layers than the original ones. The reconstruction results are generally better than other common algorithms, such as Kintinuous, Elasticfusion and ORBSLAM2 dense reconstruction.

Automated summary

This paper presents a CNN-based SLAM reconstruction algorithm that optimizes feature point extraction and pose estimation, resulting in a complete and smooth spatial model.