Research On Learning Based High Precision SLAM Algorithm

Simultaneous Localization and Mapping(SLAM)is a 3D reconstruction method.It is a method of self-localization and mapping in an unknown environment.SLAM has a wide range of applications in areas such as automatic driving and virtual reality.Among various SLAM algorithms,the LSD-SLAM algorithm is a method that can reconstruct large-scale scenes in real time.However,there is room for improvement in the LSD-SLAM algorithm.In recent years,learning-based methods have been active in various fields and have achieved good results.Therefore,this project attempts to use learning-based methods to improve the robustness of LSD-SLAM.The SLAM system consists of a sensor,a front-stage visual odometry,back-stage nonlinear optimization,loop closure,and mapping.Among them,the visual odometry part and the loop closure part can join the learning-based method.This subject has improved the LSD-SLAM algorithm from these two aspects.Firstly,this topic proposes a depth confidence estimation algorithm based on ground control points,which improves the visual odometry part of the LSD-SLAM.The confidence estimation algorithm uses a random forest algorithm to train the gorund control points prediction model.The model can use the features that can be calculated conveniently and quickly in the process of stereo matching,so that the model costs as little as possible while prediction.In the process of tracking estimation,an estimate of the depth confidence is obtained through the model,and the confidence is used as a weight into the depth estimation and the camera motion estimation to obtain a more accurate estimation result and improve the LSDSLAM algorithm in the front-stage visual odometry part accuracy,and then improve the reconstruction accuracy of the entire system.This topic also proposes a loop closure detection network model based on secondorder features.The model uses a deep convolutional network,based on the second-order information,to obtain high-precision loop closure detection results.The loss function used by the model is the triplet loss function.Through this kind of weakly supervised learning,the distance between the features of the same place is continuously reduced,and the feature distances of different locations are constantly increased,so that the features of the same place keep clustering.The proposed loop closure detection network model is put into the LSD-SLAM to improve the accuracy of the model in the loop closure detection make the reconstruction result more accurate.Using the above two models,the subject has improved the reconstruction accuracy and robustness of the LSD-SLAM algorithm,so that the algorithm can obtain better reconstruction results.