Visual–inertial SLAM algorithms empower robots to autonomously explore and navigate unknown scenes. However, most existing SLAM systems heavily rely on the assumption of static environments, making them ineffective when confronted with dynamic objects in the real world. To enhance the robustness and localization accuracy of SLAM systems in dynamic scenes, this paper introduces a visual–inertial SLAM framework that integrates semantic and geometric information, called D-VINS. This paper begins by presenting a method for dynamic object classification based on the current motion state of features, enabling the identification of temporary static features within the environment. Subsequently, a feature dynamic check module is devised, which utilizes inertial measurement unit (IMU) prior information and geometric constraints from adjacent frames to calculate dynamic factors. This module also validates the classification outcomes of the temporary static features. Finally, a dynamic adaptive bundle adjustment module is developed, utilizing the dynamic factors of the features to adjust their weights during the nonlinear optimization process. The proposed methodology is evaluated using both public datasets and a dataset created specifically for this study. The experimental results demonstrate that D-VINS stands as one of the most real-time, accurate, and robust systems for dynamic scenes, showcasing its effectiveness in challenging real-world scenes.
It is a major challenge for a visual SLAM system to maintain a highly precise and robust mapping and localization ability in an environment with low texture. In this paper, a bundle adjustment method for deeply exploring the spatial constraints based on the Manhattan hypothesis is proposed. First, an energy function for filtering the feature set and segmenting the point cloud is given, and a semantic graph is formed with the minimum energy. Then, a novel factor graph for back-end bundle adjustment is designed to include points, edges, planes, and spatial constraints to improve the stability and positioning accuracy of the system. After that, the corresponding error items of those spatial constraints for bundle adjustment are designed according to the Manhattan hypothesis. Finally, comparison tests are designed to evaluate the performance of the given approach using TUM RGB-D datasets in different scenes. Test results show that the proposed method provides better positioning ability, with the positioning accuracy improved by 18.07% on average compared with that of existing mainstream approaches.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.