WF-SLAM: A Robust VSLAM for Dynamic Scenarios via Weighted Features

Dynamic targets in the environment can seriously affect the accuracy of SLAM systems. This article proposes a novel dynamic visual SLAM method with IMU and deep learning for indoor dynamic blurred scenes, which improves the front end of ORB-SLAM2, combining deep learning with geometric constraint to make the dynamic feature points elimination more reasonable and robust. First, a multi-directional superposition blur augmentation algorithm is added to the YOLOv5s network to compensate for errors caused by fast-moving targets, camera shake and camera focus. Then, the fine-tuned YOLOv5s model is used to detect potential dynamic regions. Afterward, IMU measurements are introduced for rotation compensation to calculate the feature point velocity and estimate the motion speed of the camera, in order to estimate the real motion state of potential dynamic targets. Finally, real dynamic points will be removed and potential dynamic points will be reserved for subsequent pose estimation. Experiments are conducted on TUM dynamic dataset and in the real world. The results demonstrate that the proposed method has significant improvement compared with ORB-SLAM2, and has a more robust performance over some other state-of-the-art dynamic visual SLAM systems.

Section: Methods Independent Of the Camera Motion Modelmentioning

confidence: 99%

A visual SLAM method assisted by IMU and deep learning in indoor dynamic blurred scenes

Liu,

Cao,

Cheng

et al. 2023

“…However, the computation of correlation geometric constraints is relatively complex and can lead to computational delays in scenarios that require real-time processing of large amounts of data. Zhong et al [28] introduced a robust visual SLAM system that utilizes weighted features (WF-SLAM) that uses the epipolar constraints to assign different weights to each feature point, and uses the weight information to initialize the camera pose and mitigate the effect of dynamic feature points on the camera pose. However, the polar constraint alone cannot filter all dynamic feature points, and the method fails if the dynamic object moves along the polar direction.…”

Section: Related Workmentioning

confidence: 99%

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

Gong,

Sun,

Zou

et al. 2024

Within the realm of autonomous robotic navigation, Simultaneous Localization and Mapping (SLAM) serves as a critical perception technology, drawing heightened attention in contemporary research. The traditional SLAM systems perform well in static environments, but in the real physical world, dynamic objects can destroy the static geometric constraints of the SLAM system, further limiting its practical application in the real world. In this paper, a robust dynamic RGB-D SLAM system is proposed to expand the number of static points in the scene by combining with YOLO-Fastest to ensure the effectiveness of the geometric constraints model construction, and then based on that, a new thresholding model is designed to differentiate the dynamic features in the objection bounding box, which takes advantage of the double polyline constraints and the residuals after reprojection to filter the dynamic feature points. In addition, two Gaussian models are constructed to segment the moving objects in the bounding box in the depth image to achieve the effect similar to the instance segmentation under the premise of ensuring the computational speed. In this paper, experiments are conducted on dynamic sequences provided by the TUM dataset to evaluate the performance of the proposed method, and the results show that the RMSE (Root mean squared error) metric of the absolute trajectory error of the algorithm of this paper has at least 80% improvement compared to ORB-SLAM2. Higher robustness in dynamic environments with both high and low dynamic sequences compared to DS-SLAM and Dynaslam, and can effectively provide intelligent localization and navigation for mobile robots.

“…The matrices F and H are calculated based on the fine matching result of the current frame using the algorithms ( findFundamentalMat function for F and findHomography function for H) provided by OpenCV4. The algorithm implementation details can be found in the OpenCV4 manual 6 . For matrix H, the remapping distance d H between a pair of matching points is calculated by…”

Section: Scenario Classificationmentioning

confidence: 99%

“…To eliminate the negative impact of moving objects and obtain clean maps, a number of vSLAM systems based on moving object segmentation have been proposed, such as geometry-based vSLAM [3,4], and learning-based vSLAM [5,6]. Although the above methods achieves accurate tracking by segmenting moving objects, the improvement of tracking accuracy is limited in some scenarios (e.g.…”

Section: Introductionmentioning

confidence: 99%

RGB-D SLAM in indoor dynamic environments with two channels based on scenario classification

Zhou

Tao

et al. 2023

In visual simultaneous localization and mapping (SLAM) systems, the limitations of the assumption of scene rigidity are usually broken by using learning-based or geometry-based methods. However, learning-based methods usually have a high time cost, and geometry-based methods usually do not result in clean maps which are useful for advanced robotic applications. In this paper, an RGB-D SLAM in indoor dynamic environments with two channels that classiﬁes frames as slightly and highly dynamic scenarios based on matching accuracy is proposed. And a geometric constraint based on Hamming distance is proposed to improve the eﬀectiveness of matching accuracy as a basis for scenario classiﬁcation. Dynamic features are detected by aﬃne consistency constraint and semantic method. The semantic method is only used for highly dynamic scenarios to reduce the time cost of dynamic feature detection and provide a basis for mapping. Furthermore, an improved adaptive threshold algorithm is proposed to improve the robustness of feature matching. The proposed method is evaluated in the TUM RGB-D dataset and a real scenario. The experimental results demonstrate that the proposed method achieves highly accurate tracking with appreciable time cost in both slightly and highly indoor dynamic environments while obtaining eﬀective maps.