PLDS-SLAM: Point and Line Features SLAM in Dynamic Environment

Abstract

Visual simultaneous localization and mapping (SLAM), based on point features, achieves high localization accuracy and map construction. They primarily perform simultaneous localization and mapping based on static features. Despite their efficiency and high precision, they are prone to instability and even failure in complex environments. In a dynamic environment, it is easy to keep track of failures and even failures in work. The dynamic object elimination method, based on semantic segmentation, often recognizes dynamic objects and static objects without distinction. If there are many semantic segmentation objects or the distribution of segmentation objects is uneven in the camera view, this may result in feature offset and deficiency for map matching and motion tracking, which will lead to problems, such as reduced system accuracy, tracking failure, and track loss. To address these issues, we propose a novel point-line SLAM system based on dynamic environments. The method we propose obtains the prior dynamic region features by detecting and segmenting the dynamic region. It realizes the separation of dynamic and static objects by proposing a geometric constraint method for matching line segments, combined with the epipolar constraint method of feature points. Additionally, a dynamic feature tracking method based on Bayesian theory is proposed to eliminate the dynamic noise of points and lines and improve the robustness and accuracy of the SLAM system. We have performed extensive experiments on the KITTI and HPatches datasets to verify these claims. The experimental results show that our proposed method has excellent performance in dynamic and complex scenes.

SLM-SLAM: a visual SLAM system based on segmented large-scale model in dynamic scenes and zero-shot conditions

“…Huang et al [11] employ three-dimensional motion consistency of feature points extracted from the same rigid body for clustering, aiming to distinguish between static and dynamic objects. Yuan et al [22] combined point and line features in images to compute dynamic objects in the scene. Geometric-based methods exhibit high real-time performance but typically assume simple rigid-body motion models, which is a challenge when dealing with non-rigid dynamic objects.…”

Real-time visual SLAM based YOLO-Fastest for dynamic scenes

“…At the same time, it has been observed in this study that a single epipolar constraint is not sufficient to remove all moving feature points. When a feature point moves along the direction of the epipolar line, the reprojected points of the moving map point still fall on the epipolar line, resulting in zero epipolar residuals in such cases [43,44]. To address the limitations of the epipolar constraint, reprojection residuals δ p and depth residuals δ d are introduced to further eliminate dynamic feature points.…”

Robust depth-verified RGB-D visual odometry with structural regularities for indoor environments

“…It integrates coupled features derived from both point and line features and introduces corresponding coupling residuals for optimization. PLDS-SLAM [16] proposes a line segment matching method based on geometric constraints and combines the pole constraints of point features to separate dynamic and static objects in the scene, which improves the robustness. Plane features have also been employed to enhance the robustness of visual SLAM in low-textured scenes.…”