Eliminating short-term dynamic elements for robust visual simultaneous localization and mapping using a coarse-to-fine strategy

Visual Simultaneous Localization and Mapping (VSLAM) is a critical technology for intelligent mobile robots, enabling simultaneous environmental mapping and self-localization. However, reflective ground in indoor environments presents significant challenges to VSLAM systems, as it introduces noisy virtual landmarks that degrade both map accuracy and localization precision. To address these challenges, we propose a novel RGB-D VSLAM system specifically designed for these environments. Our approach begins with a carefully designed point-line-plane-based VSLAM framework, which mitigates the limitations caused by sparse point features in indoor settings. Then we analyze how reflective ground degrades VSLAM performance and propose a reflective ground feature removal strategy that integrates semantic and geometric information. To enhance robustness in highly reflective environments, we incorporate a monocular depth estimation network as a complementary module. Extensive experiments on public datasets demonstrate that our framework achieves state-of-the-art performance. And evaluations on an author-collected dataset highlight the system’s superior mapping and localization capabilities in reflective indoor environments. Furthermore, ablation studies validate the effectiveness of each proposed component, and latency tests confirm the system’s suitability for real-time applications.

Visual Simultaneous Localization and Mapping (SLAM) is crucial to many applications such as self-driving vehicles and robot tasks. However, it is still challenging for existing visual SLAM approaches to achieve good performance in low-texture or illumination-changing scenes. In recent years, some researchers have turned to edge-based SLAM approaches to deal with the challenging scenes, which are more robust than feature-based and direct SLAM methods. Nevertheless, existing edge-based methods are computationally expensive and inferior than other visual SLAM systems in terms of accuracy. In this study, we propose EdgeSLAM, a novel RGB-D edge-based SLAM approach to deal with challenging scenarios that is efficient, accurate, and robust. EdgeSLAM is built on two innovative modules: efficient edge selection and adaptive robust motion estimation. The edge selection module can efficiently select a small set of edge pixels, which significantly improves the computational efficiency without sacrificing the accuracy. The motion estimation module improves the system's accuracy and robustness by adaptively handling outliers in motion estimation. Extensive experiments were conducted on TUM RGBD, ICL-NUIM and ETH3D datasets, and experimental results show that EdgeSLAM significantly outperforms five state-of-the-art (SOTA) methods in terms of efficiency, accuracy, and robustness, which achieves 29.17% accuracy improvements with a high processing speed of up to 120 FPS and a high positioning success rate of 97.06%.

Visual simultaneous localization and mapping (VSLAM) is extensively utilized in the field of unmanned driving. Classical VSLAM typically postulates that the surroundings are stationary, and dynamic objects can seriously affect the accuracy of the system. However, detecting and tracking dynamic objects is beneficial for improving the autonomy and intelligence of robotics. In order to solve the problem of VSLAM distinguishing dynamic objects in dynamic scenes, a semantic VSLAM system based on the VDO-SLAM framework is proposed. The approach integrates semantic segmentation into the visual odometry and combines scene flow and geometric constraints to effectively reduce the negative impact of dynamic objects on system performance. Specifically, a transformer-based neural network architecture for optical flow estimation was employed, which effectively enhances the segmentation precision of foreground and background regions. And a geometric constraint was introduced to classify dynamic objects, which can reduction of erroneous segmentation of dynamic objects with effect. The data analysis results on the KITTI dataset demonstrate that our proposed algorithms can effectively enhance precision and stability of VSLAM system, reduce the tracking error of VSLAM in dynamic environments, and demonstrate good potential and application value.

A comprehensive overview of core modules in visual SLAM framework

Multi-camera visual SLAM for autonomous navigation of micro aerial vehicles

Visual simultaneous localization and mapping (VSLAM) is an essential technique used in areas such as robotics and augmented reality for pose estimation and 3D mapping. Research on VSLAM using both monocular and stereo cameras has grown significantly over the last two decades. There is, therefore, a need for emphasis on a comprehensive review of the evolving architecture of such algorithms in the literature. Although VSLAM algorithm pipelines share similar mathematical backbones, their implementations are individualized and the ad hoc nature of the interfacing between different modules of VSLAM pipelines complicates code reuseability and maintenance. This paper presents a software model for core components of VSLAM implementations and interfaces that govern data flow between them while also attempting to preserve the elements that offer performance improvements over the evolution of VSLAM architectures. The framework presented in this paper employs principles from model-driven engineering (MDE), which are used extensively in the development of large and complicated software systems. The presented VSLAM framework will assist researchers in improving the performance of individual modules of VSLAM while not having to spend time on system integration of those modules into VSLAM pipelines.

<p>Autonomous driving has spurred the development of sensor fusion techniques, which combine data from multiple sensors to improve system performance. In particular, a localization system based on sensor fusion, such as Visual Simultaneous Localization and Mapping (VSLAM), plays a crucial role in environment perception and serves as the foundation for decision-making and motion control in intelligent vehicles. The accuracy of extrinsic calibration parameters between the camera and IMU is of utmost importance for precise positioning in VSLAM systems. However, existing calibration methods are often time-consuming, rely on complex optimization techniques, and are sensitive to noise and outliers, leading to potential degradation in system performance. To address these challenges, this paper presents a fast and accurate camera-IMU calibration method based on space coordinate transformation constraints and SVD (Singular Value Decomposition) tricks. The method involves constructing constraint equations by ensuring the equality of rotation and transformation matrices between camera frames and IMU coordinates at different time instances. Subsequently, the external parameters of the camera-IMU system are solved using quaternion transformation and SVD techniques. To validate the proposed method, experiments were conducted using the ROS (Robot Operating System) platform, where camera images and velocity, acceleration, and angular velocity data from the IMU were recorded in a ROS bag file. The results demonstrate that the proposed method achieves reliable camera-IMU calibration parameters, requiring less tuning time and exhibiting reduced uncertainty.</p>

In recent years, the signihcant progress has been made in visual simultaneous localization and mapping(VSLAM). Many present geometric VSLAM systems rely on static and bright environment assumptions, which is not friendly to the generalization of VSLAM in the real world including a large number of challenging scenes. To cope with these challenges, a real-time and robust visual-inertial SLAM system was proposed, which integrates a neural network for moving object detection(MOD) and greatly reduces the negative influence of dynamic objects. We has performed an ablation study to validate the effectiveness and necessity of our proposal. In addition, empirical evaluations on typical datasets, as well as in some usual dynamic environments, show that our novel framework can favorably solve the tracking loss, yield pure point cloud and improve the accuracy of VSLAM.

Recent advances in event-based cameras have led to significant developments in robotics, particularly in visual simultaneous localization and mapping (VSLAM) applications. This technique enables real-time camera motion estimation and simultaneous environment mapping using visual sensors on mobile platforms. Event cameras offer several distinct advantages over frame-based cameras, including a high dynamic range, high temporal resolution, low power consumption, and low latency. These attributes make event cameras highly suitable for addressing performance issues in challenging scenarios such as high-speed motion and environments with high-range illumination. This review paper delves into event-based VSLAM (EVSLAM) algorithms, leveraging the advantages inherent in event streams for localization and mapping endeavors. The exposition commences by explaining the operational principles of event cameras, providing insights into the diverse event representations applied in event data preprocessing. A crucial facet of this survey is the systematic categorization of EVSLAM research into three key parts: event preprocessing, event tracking, and sensor fusion algorithms in EVSLAM. Each category undergoes meticulous examination, offering practical insights and guidance for comprehending each approach. Moreover, we thoroughly assess state-of-the-art (SOTA) methods, emphasizing conducting the evaluation on a specific dataset for enhanced comparability. This evaluation sheds light on current challenges and outlines promising avenues for future research, emphasizing the persisting obstacles and potential advancements in this dynamically evolving domain.

Visual Simultaneous Localization and Mapping (VSLAM) is a key technique that enables autonomous systems to localize themselves and incrementally build a map of an unknown environment using only visual information. Despite its importance, conventional VSLAM systems frequently experience drift and tracking failures in complex environments, which limits their overall effectiveness. Multi-camera systems have enhanced VSLAM accuracy by incorporating diverse viewpoints. However, they generally rely on synchronous data capture, restricting their applicability in multi-sensor setups where asynchronous data acquisition is necessary. To address this limitation, a continuous-time Asynchronous Multi-Camera SLAM (AMC-SLAM) framework is proposed, utilizing sparse Gaussian process regression. The method integrates outlier removal, continuous-time trajectory optimization, and multi-view loop closing to achieve robust pose estimation. Combining Gaussian process interpolation with bundle adjustment strengthens inter-camera data correlation and reduces the number of state variables, while the derived analytical Jacobians enhance optimization efficiency. Additionally, online estimation of multi-camera extrinsic parameters is incorporated to improve the system’s generality. Experimental results on the AMV-Bench dataset [1] demonstrate an absolute translation error of less than 0.5% over a 10 km trajectory, indicating significant improvements in accuracy over existing stereo and multi-camera SLAM systems. The method also exhibits robustness and generalizability on the New College Dataset [2] and in real-world scenarios. These findings underscore the potential of AMC-SLAM for high-precision, robust applications in challenging environments.

An Observer Design for Visual Simultaneous Localisation and Mapping with Output Equivariance

To solve the low accuracy of image feature matching in horticultural robot visual navigation, an innovative and effective image feature matching algorithm was proposed combining the improved Oriented FAST and Rotated BRIEF (ORB) and Lucas–Kanade (LK) optical flow algorithm. First, image feature points were extracted according to the adaptive threshold calculated using the Michelson contrast. Then, the extracted feature points were uniformed by the quadtree structure, which can reduce the calculated amount of feature matching, and the uniform ORB feature points were roughly matched to estimate the position of the feature points in the matched image using the improved LK optical flow. Finally, the Hamming distance between rough matching points was calculated for precise matching. Feature extraction and matching experiments were performed in four typical scenes: normal light, low light, high texture, and low texture. Compared with the traditional algorithm, the uniformity and accuracy of the feature points extracted by the proposed algorithm were enhanced by 0.22 and 50.47%, respectively. Meanwhile, the results revealed that the matching accuracy of the proposed algorithm increased by 14.59%, whereas the matching time and total time decreased by 39.18% and 44.79%, respectively. The proposed algorithm shows great potential for application in the visual simultaneous localization and mapping (V-SLAM) of horticultural robots to achieve higher accuracy of real-time positioning and map construction.

Building Information Modeling (BIM) has been widely adopted for construction inspections due to its ability to integrate multiple data sources. Engineers use BIM to identify and review site issues, yet inspection systems face several challenges. Firstly, positioning inspection areas on a construction site using BIM with Augmented Reality (AR) requires complex model manipulation. Additionally, signal or Internet connectivity issues may limit positioning technologies. Secondly, human error or interference is common in traditional inspection processes due to their complexity. To overcome these barriers, this research applied BIM and AR with Visual Simultaneous Localization and Mapping (VSLAM) to help inspectors quickly and effectively record construction defects as photographs with notes and their locations. An efficient approach is proposed to integrate BIM and AR with VSLAM, and a prototype is developed to validate and demonstrate how the proposed system can assist a site inspector in performing quality management, even offline. The system uses a two-phase indoor positioning method: initial localization via visual markers and real-time tracking with VSLAM, enabling precise defect tracking and efficient model adjustments. While significantly improving inspection accuracy and efficiency, its performance is affected by environmental factors like lighting and marker placement, providing insights for future refinement.

Current visual simultaneous localization and mapping (SLAM) systems have demonstrated commendable efficacy in static environments. However, the presence of dynamic objects in real-world settings frequently leads to system discrepancies, significantly impairing the accuracy and robustness of SLAM systems. Conventional visual SLAM approaches typically utilize epipolar constraints to mitigate the impact of outliers; nevertheless, they encounter limitations when confronted with a substantial number of dynamic or planar moving objects. To tackle these issues, this paper introduces a novel dynamic visual SLAM system, termed DEG-SLAM. Initially, the system employs the YOLOv5 object detection network to identify dynamic objects, subsequently relaying the semantic information to the tracking module. During the tracking phase, both semantic information and epipolar constraints are leveraged to filter out dynamic feature points. To address the challenges posed by the malfunctioning of epipolar constraints in degenerate scenes, DEG-SLAM incorporates a degenerate constraint mechanism aimed at further eliminating dynamic feature points. Furthermore, a reprojection constraint has been introduced to enhance the filtering of absent dynamic feature points that lie outside the detection boxes. Experimental findings reveal that DEG-SLAM significantly improves accuracy and robustness when compared to traditional ORB-SLAM3 in dynamic environments. The performance benefits of DEG-SLAM are particularly evident in degenerate scenarios, thereby affirming its practicality and reliability in complex settings.

Visual Simultaneous Localization and Mapping (VSLAM) has developed as the basic ability of robots in past few decades. There are a lot of open-sourced and impressive SLAM systems. However, the majority of the theories and approaches of SLAM systems at present are based on the static scene assumption, which is usually not practical in reality because moving objects are ubiquitous and inevitable under most circumstances. In this paper the DDL-SLAM (Dynamic Deep Learning SLAM) is proposed, a robust RGB-D SLAM system for dynamic scenarios that, based on ORB-SLAM2, adds the abilities of dynamic object segmentation and background inpainting. We are able to detect moving objects utilizing both semantic segmentation and multi-view geometry. Having a static scene map allows inpainting background of the frame which has been obscured by moving objects, therefore the localization accuracy is greatly improved in the dynamic environment. Experiment with a public RGB-D benchmark dataset, the results clarify that DDL-SLAM can significantly enhance the robustness and stability of the RGB-D SLAM system in the highly-dynamic environment.