Abstract
As visual simultaneous localization and mapping (vSLAM) is easy disturbed by the changes of camera viewpoint and scene appearance when building a globally consistent map, the robustness and real-time performance of key frame image selections cannot meet the requirements. To solve this problem, a real-time closed-loop detection method based on a dynamic Siamese networks is proposed in this paper. First, a dynamic Siamese network-based fast conversion learning model is constructed to handle the impact of external changes on key frame judgments, and an elementwise convergence strategy is adopted to ensure the accurate positioning of key frames in the closed-loop judgment process. Second, a joint training strategy is designed to ensure the model parameters can be learned offline in parallel from tagged video sequences, which can effectively improve the speed of closed-loop detection. Finally, the proposed method is applied experimentally to three typical closed-loop detection scenario datasets and the experimental results demonstrate the effectiveness and robustness of the proposed method under the interference of complex scenes.
Highlights
SLAM is one of the core problems in mobile robot research [1,2], which can incrementally build a continuous map of the surrounding environment in an unknown environment
In order to verify the performance of the visual simultaneous localization and mapping (vSLAM) real-time closed-loop detection method based on the dynamic Siamese network, three datasets of Gardens Point, Nordland, and Mapillary were used for the experimental analysis
The accuracy of this method was compared with the closed-loop detection method based on bag of visual word (BoVW), PlaceCNN, generalized search tree (GiST), SS_PlaceCNN(Sliding window-based PlaceCNN) and AutoEncoder
Summary
Closed-loop detection [6,7] judges whether the mobile robot has returned to the visited position and obtains an accurate position of the robot through the constructed map, whose core goal is to select accurate key frame images. The dataset was collected on the campus of the University of Queensland (QUT), including three subdatasets in two days and one night. The dataset has two characteristics: viewing angle change and illumination change. (1) Changes in weather conditions (sun, rain, snow, fog, haze) and photographing time (dawn, day, dusk, night);. Through werelayer the parameters of depth feature network f l trained and theaselementwise mapping and the regularization parameters λm CNN model such
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
