Visual Simultaneous Localization Research Articles

DMOT-SLAM: Visual SLAM in Dynamic Environments with Moving Object Tracking

Abstract Visual simultaneous localization and mapping (SLAM) in dynamic environments has received significant attention in recent years, and accurate segmentation of real dynamic objects is the key to enhancing the accuracy of pose estimation in such environments. In this study, we propose a visual SLAM approach based on ORB-SLAM3, namely DMOT-SLAM, which can accurately estimate the camera’s pose in dynamic environments while tracking the trajectories of moving objects. We introduce a spatial point correlation constraint and combine it with instance segmentation and epipolar constraint to identify dynamic objects. We integrate the proposed motion check method into DeepSort, an object tracking algorithm, to facilitate inter-frame tracking of dynamic objects. This integration not only enhances the stability of dynamic features detection but also enables the estimation of global motion trajectories for dynamic objects and the construction of object-level semi-dense semantic maps. We evaluate our approach on the public TUM, Bonn, and KITTI dataset, and the results show that our approach has a significant improvement over ORB-SLAM3 in dynamic scenes and performs better compared to other state-of-the-art SLAM approaches. Moreover, experiments in real-world scenarios further substantiate the effectiveness of our approach.

FFD-SLAM: A Real-Time Visual SLAM Toward Dynamic Scenes with Semantic and Optical Flow Information

To solve the problem of poor localization accuracy and robustness of visual simultaneous localization and mapping (SLAM) systems in highly dynamic environments, this paper proposes a dynamic visual SLAM algorithm called FFD-SLAM that fuses the target detection network with the optical flow method. The algorithm considers ORB-SLAM2 as the basic framework, joins the semantic thread in parallel with its tracking thread, initially obtains the set of feature points through the real-time detection of dynamic objects in the environment through YOLOv5 in the semantic thread, then filters the set of feature points obtained in the semantic thread through the optical flow module, and finally utilizes the remaining static feature points for the matching calculation. Experiments showed that the proposed algorithm showed an improvement of approximately 97% in the localization accuracy compared with the ORB-SLAM2 algorithm in a highly dynamic environment, which effectively improves the localization accuracy and robustness of the system. The proposed algorithm also showed a higher real-time performance compared with some excellent dynamic SLAM algorithms.

CPR-SLAM: RGB-D SLAM in dynamic environment using sub-point cloud correlations

Abstract The early applications of Visual Simultaneous Localization and Mapping (VSLAM) technology were primarily focused on static environments, relying on the static nature of the environment for map construction and localization. However, in practical applications, we often encounter various dynamic environments, such as city streets, where moving objects are present. These dynamic objects can make it challenging for robots to accurately understand their own position. This paper proposes a real-time localization and mapping method tailored for dynamic environments to effectively deal with the interference of moving objects in such settings. Firstly, depth images are clustered, and they are subdivided into sub-point clouds to obtain clearer local information. Secondly, when processing regular frames, we fully exploit the structural invariance of static sub-point clouds and their relative relationships. Among these, the concept of the sub-point cloud is introduced as novel idea in this paper. By utilizing the results computed based on sub-poses, we can effectively quantify the disparities between regular frames and reference frames. This enables us to accurately detect dynamic areas within the regular frames. Furthermore, by refining the dynamic areas of keyframes using historical observation data, the robustness of the system is further enhanced. We conducted comprehensive experimental evaluations on challenging dynamic sequences from the TUM dataset and compared our approach with state-of-the-art dynamic VSLAM systems. The experimental results demonstrate that our method significantly enhances the accuracy and robustness of pose estimation. Additionally, we validated the effectiveness of the system in dynamic environments through real-world scenario tests.

SLM-SLAM: A Visual SLAM System Based on Segmented Large-Scale Model in Dynamic Scenes and Zero-shot Conditions

Abstract In the real world, the presence of various dynamic objects can impact the localization accuracy of the majority of typical Visual Simultaneous Localization and Mapping (VSLAM) systems. Simultaneously, many dynamic VSLAM systems based on neural networks require pre-training for specific application scenarios. We present SLM-SLAM, the first VSLAM system that implements zero-shot processing of dynamic scenes. It achieves the capability to handle various dynamic objects without the necessity for pre-training, enabling straightforward adaptation to different application scenarios. Firstly, we designed an open-world semantic segmentation module based on a segmented large-scale model to acquire semantic information in the scene. Subsequently, we devised a label-based strategy for selecting feature points, jointly optimizing poses with the weighted labels provided by both semantic and geometric information. Finally, we refined the keyframe selection strategy of ORB-SLAM3 to prevent matching errors caused by an insufficient number of remaining static feature points in the scene. We conducted experiments on the TUM dataset, the KITTI dataset, and real world scenarios. The results indicate that in dynamic scenes, our SLM-SLAM significantly improves localization accuracy compared to ORB-SLAM3, and its performance is comparable to state-of-the-art dynamic VSLAM systems.

TKO‐SLAM: Visual SLAM algorithm based on time‐delay feature regression and keyframe pose optimization

AbstractThis paper addresses the challenge of generating clear image frames and minimizing the loss of keyframes by a robot engaging in rapid large viewing angle motion. These issues often lead to detrimental consequences such as trajectory drifting and loss during the construction of curved motion trajectories. To tackle this, we proposed a novel visual simultaneous localization and mapping (SLAM) algorithm, TKO‐SLAM, which is based on time‐delay feature regression and keyframe position optimization. TKO‐SLAM uses a multiscale recurrent neural network to rectify object deformation and image motion smear. This network effectively repairs the time‐delay image features caused by the rapid movement of the robot, thereby enhancing visual clarity. Simultaneously, inspired by the keyframe selection strategy of the ORB‐SLAM3 algorithm, we introduced a grayscale motion‐based image processing method to supplement keyframes that may be omitted due to the robot's rapid large viewing angle motion. To further refine the algorithm, the time‐delay feature regression image keyframes and adjacent secondary keyframes were used as dual measurement constraints to optimize camera poses and restore robot trajectories. The results of experiments on the benchmark RGB‐D data set TUM and real‐world scenarios show that TKO‐SLAM algorithm achieves more than 10% better localization accuracy than the PKS‐SLAM algorithm in the rapid large viewing angle motion scenario, and has advantages over the SOTA algorithms.

Development of a combined harvester navigation control system based on visual simultaneous localization and mapping-inertial guidance fusion

Recently, the existing unmanned systems of combine harvesters mostly adopts satellite navigation scheme, lacking real-time observation of harvesting adjustment. To improve the operational efficiency of combine harvester assisted navigation operation, this paper designs a combine harvester navigation control system based on vision simultaneous localization and mapping (SLAM)-inertial guidance fusion. The system acquires field image information and extracts the crop boundary line as the navigation datum by binocular camera. First, the system acquires field image information through binocular camera and extracts the crop boundary line as the navigation datum. Second, fusing camera and inertial guidance information to obtain the real-time relative position of a combine harvester. Third, constrained optimization of image and inertial guidance information is achieved through a sliding window optimization method based on tightly coupled nonlinear optimization. Finally, obtain the position of the combine harvester relative to the navigation datum line, and output a signal to the steering mechanism to realize the combine harvester in the field intelligent positioning navigation control. The system consists of binocular camera, inertial measurement unit, motorized steering wheel, monitor display, angle sensor and microcontroller. During field testing, the system underwent repetitive harvesting trials over a distance of 25 m.. The testing machine performs field operations at a speed of 0.9-1.5 m/s, with an average lateral deviation range of 2.21-8.62 cm, a standard deviation range of 0.13-4.21 cm and an average cutting rate range of 92.2%-96.0%, achieving the expected harvesting effect.

Monocular Visual Simultaneous Localization and Mapping: (R)Evolution From Geometry to Deep Learning-Based Pipelines

Monocular Visual Simultaneous Localization and Mapping: (R)Evolution From Geometry to Deep Learning-Based Pipelines

A comprehensive overview of core modules in visual SLAM framework

Visual Simultaneous Localization and Mapping (VSLAM) technology has become a key technology in autonomous driving and robot navigation. Relying on camera sensors, VSLAM can provide a richer and more precise perception means, and its advancement has accelerated in recent years. However, current review studies are often limited to in-depth analysis of a specific module and lack a comprehensive review of the entire VSLAM framework. The VSLAM system consists of five core components: (1) The camera sensor module is responsible for capturing visual information about the surrounding environment. (2) The front-end module uses image data to roughly estimate the camera’s position and orientation. (3) The back-end module optimizes and processes the pose information estimated by the front-end. (4) The loop detection module is used to correct accumulated errors in the system. (5) The mapping module is responsible for generating environmental maps. This review provides a systematic and comprehensive analysis of the SLAM framework by taking the core components of VSLAM as the entry point. Deep learning brings new development opportunities for VSLAM, but it still needs to solve the problems of data dependence, cost and real-time in practical application. We deeply explore the challenges of combining VSLAM with deep learning and feasible solutions. This review provides a valuable reference for the development of VSLAM. This will help push VSLAM technology to become smarter and more efficient. Thus, it can better meet the needs of future intelligent autonomous systems in multiple fields.

MDP-SLAM: A Visual SLAM towards a Dynamic Indoor Scene Based on Adaptive Mask Dilation and Dynamic Probability

Visual simultaneous localization and mapping (SLAM) algorithms in dynamic scenes will apply the moving feature points to the camera pose’s calculation, which will cause the continuous accumulation of errors. As a target-detection tool, mask R-CNN, which is often used in combination with the former, due to the limited training datasets, easily results in the semantic mask being incomplete and deformed, which will increase the error. In order to solve the above problems, we propose in this paper a visual SLAM algorithm based on an adaptive mask dilation strategy and the dynamic probability of the feature points, named MDP-SLAM. Firstly, we use the mask R-CNN target-detection algorithm to obtain the initial mask of the dynamic target. On this basis, an adaptive mask-dilation algorithm is used to obtain a mask that can completely cover the dynamic target and part of the surrounding scene. Then, we use the K-means clustering algorithm to segment the depth image information in the mask coverage area into absolute dynamic regions and relative dynamic regions. Combined with the epipolar constraint and the semantic constraint, the dynamic probability of the feature points is calculated, and then, the highly dynamic possible feature points are removed to solve an accurate final pose of the camera. Finally, the method is tested on the TUM RGB-D dataset. The results show that the MDP-SLAM algorithm proposed in this paper can effectively improve the accuracy of attitude estimation and has high accuracy and robustness in dynamic indoor scenes.

A review of visual SLAM for robotics: evolution, properties, and future applications.

Visual simultaneous localization and mapping (V-SLAM) plays a crucial role in the field of robotic systems, especially for interactive and collaborative mobile robots. The growing reliance on robotics has increased complexity in task execution in real-world applications. Consequently, several types of V-SLAM methods have been revealed to facilitate and streamline the functions of robots. This work aims to showcase the latest V-SLAM methodologies, offering clear selection criteria for researchers and developers to choose the right approach for their robotic applications. It chronologically presents the evolution of SLAM methods, highlighting key principles and providing comparative analyses between them. The paper focuses on the integration of the robotic ecosystem with a robot operating system (ROS) as Middleware, explores essential V-SLAM benchmark datasets, and presents demonstrative figures for each method's workflow.

MAM[formula omitted]SLAM: Towards underwater-robust multi-agent visual SLAM

Some underwater applications involve deploying multiple underwater Remotely Operated Vehicles in a common area. Such applications require the localization of these vehicles, not only with respect to each other but also with respect to a previously unknown environment. To this end, this work presents MAM3SLAM, a new fully centralized multi-agent and multi-map monocular Visual Simultaneous Localization And Mapping (VSLAM) framework. Multi-agent evaluation metrics are introduced to provide an extensive evaluation of MAM3SLAM compared to the state-of-the-art multi-agent VSLAM on four two-agent scenarios: one standard airborne dataset and three new underwater datasets recorded in a pool and the sea. The results show that MAM3SLAM is robust to underwater visual conditions and tracking failures, outperforms the other evaluated methods in estimating the individual and relative poses of the agents and in collaborative mapping accuracy. MAM3SLAM successfully estimates the individual and relative localization of the agents with an error lower than 5 cm on three out of the four test sequences, and is twice as accurate as competing multi-agent works in challenging visual conditions with frequent visual dropouts, poor textures, low framerate and fast motion. MAM3SLAM’s source code is made available, as are the underwater datasets.

An unsupervised low-light image enhancement method for improving V-SLAM localization in uneven low-light construction sites

Construction robots have been increasingly adopted in construction projects to improve productivity, reduce risk, and speed up work cycles. Visual Simultaneous Localization and Mapping (V-SLAM) technology is widely used in construction robots due to its lightweight weight, cost-effectiveness, and provision of semantic information. On real construction sites, lighting conditions are often challenging due to factors such as uneven lighting intensity, inadequate exposure, or robots in backlit positions (e.g. roughcast houses without artificial lighting, underground car parks), which cause images captured under these conditions to exhibit low signal-to-noise ratio, uneven lighting, color distortion, noise, and other problems. These challenges make the extraction and matching of feature points in V-SLAM difficult, resulting in significant positioning errors or the inability to generate positioning trajectories for construction robotics. Although existing methods for enhancing low-light images can certainly improve image brightness, they still cannot effectively address the localization challenges brought about by low-light construction scenes with uneven illumination and noise. To address the interference of uneven and changing lighting conditions on V-SLAM localization in construction sites, this paper proposes the Unsupervised Reflectance Retinex and Noise model (URRN-Net) to enhance low-light construction images. By using a CNN model based on the Retinex theory to decompose the illumination characteristics of images, we achieve effective brightness restoration of uneven low-light images by utilizing unsupervised loss functions. URRE-Net can reduce the root mean square localization error by >65% compared to low-light images in the ORB-SLAM3 method, and the maximum error is reduced by >71% in on-site experiments. The proposed URRE-Net can be integrated with existing V-SLAM algorithms to provide more robust localization services for low-light construction site applications such as building operations (e.g., interior wall spraying robotic) or construction management tasks (e.g., automatic tunnel inspection).

Evaluation and analysis of feature point detection methods based on vSLAM systems

Feature point detection is identified as a significant issue in the field of computer vision. Quantitative conclusions have been established regarding the performance evaluation of feature point detection using manually annotated datasets. However, these datasets, obtained through affine transformations with preset parameters on images, exhibit limitations in terms of variety, quantity, and challenges, differing from real-world application scenarios. In actual scenes, Vision Simultaneous Localization and Mapping (vSLAM) systems are extensively applied, and the precision of their localization and mapping is directly linked to the performance of feature points. To profoundly understand the performance of feature point detection in practical applications, vSLAM systems are chosen for evaluation in this study. More diverse and challenging datasets are utilized, encompassing real datasets covering variations in lighting, rotation, occlusion, and camera angle changes, as well as synthetic datasets reflecting complex conditions such as time, season, motion patterns, and environmental textures. Based on the evaluation results, the applicability of various feature point detection methods in different environments is thoroughly discussed, and the underlying principles are analyzed (Table 13). The conclusions drawn from this research provide references for the development of new feature point detection methods, the selection of such methods in vSLAM systems, and other related studies in the field of computer vision.

Dense surface reconstruction using a learning-based monocular vSLAM model for laparoscopic surgery.

Augmented reality (AR) has seen increased interest and attention for its application in surgical procedures. AR-guided surgical systems can overlay segmented anatomy from pre-operative imaging onto the user's environment to delineate hard-to-see structures and subsurface lesions intraoperatively. While previous works have utilized pre-operative imaging such as computed tomography or magnetic resonance images, registration methods still lack the ability to accurately register deformable anatomical structures without fiducial markers across modalities and dimensionalities. This is especially true of minimally invasive abdominal surgical techniques, which often employ a monocular laparoscope, due to inherent limitations. Surgical scene reconstruction is a critical component towards accurate registrations needed for AR-guided surgery and other downstream AR applications such as remote assistance or surgical simulation. In this work, we utilize a state-of-the-art (SOTA) deep-learning-based visual simultaneous localization and mapping (vSLAM) algorithm to generate a dense 3D reconstruction with camera pose estimations and depth maps from video obtained with a monocular laparoscope. The proposed method can robustly reconstruct surgical scenes using real-time data and provide camera pose estimations without stereo or additional sensors, which increases its usability and is less intrusive. We also demonstrate a framework to evaluate current vSLAM algorithms on non-Lambertian, low-texture surfaces and explore using its outputs on downstream tasks. We expect these evaluation methods can be utilized for the continual refinement of newer algorithms for AR-guided surgery.

RU-SLAM: A Robust Deep-Learning Visual Simultaneous Localization and Mapping (SLAM) System for Weakly Textured Underwater Environments.

Accurate and robust simultaneous localization and mapping (SLAM) systems are crucial for autonomous underwater vehicles (AUVs) to perform missions in unknown environments. However, directly applying deep learning-based SLAM methods to underwater environments poses challenges due to weak textures, image degradation, and the inability to accurately annotate keypoints. In this paper, a robust deep-learning visual SLAM system is proposed. First, a feature generator named UWNet is designed to address weak texture and image degradation problems and extract more accurate keypoint features and their descriptors. Further, the idea of knowledge distillation is introduced based on an improved underwater imaging physical model to train the network in a self-supervised manner. Finally, UWNet is integrated into the ORB-SLAM3 to replace the traditional feature extractor. The extracted local and global features are respectively utilized in the feature tracking and closed-loop detection modules. Experimental results on public datasets and self-collected pool datasets verify that the proposed system maintains high accuracy and robustness in complex scenarios.

SiLK-SLAM: accurate, robust and versatile visual SLAM with simple learned keypoints

PurposeWeak repeatability is observed in handcrafted keypoints, leading to tracking failures in visual simultaneous localization and mapping (SLAM) systems under challenging scenarios such as illumination change, rapid rotation and large angle of view variation. In contrast, learning-based keypoints exhibit higher repetition but entail considerable computational costs. This paper proposes an innovative algorithm for keypoint extraction, aiming to strike an equilibrium between precision and efficiency. This paper aims to attain accurate, robust and versatile visual localization in scenes of formidable complexity.Design/methodology/approachSiLK-SLAM initially refines the cutting-edge learning-based extractor, SiLK, and introduces an innovative postprocessing algorithm for keypoint homogenization and operational efficiency. Furthermore, SiLK-SLAM devises a reliable relocalization strategy called PCPnP, leveraging progressive and consistent sampling, thereby bolstering its robustness.FindingsEmpirical evaluations conducted on TUM, KITTI and EuRoC data sets substantiate SiLK-SLAM’s superior localization accuracy compared to ORB-SLAM3 and other methods. Compared to ORB-SLAM3, SiLK-SLAM demonstrates an enhancement in localization accuracy even by 70.99%, 87.20% and 85.27% across the three data sets. The relocalization experiments demonstrate SiLK-SLAM’s capability in producing precise and repeatable keypoints, showcasing its robustness in challenging environments.Originality/valueThe SiLK-SLAM achieves exceedingly elevated localization accuracy and resilience in formidable scenarios, holding paramount importance in enhancing the autonomy of robots navigating intricate environments. Code is available at https://github.com/Pepper-FlavoredChewingGum/SiLK-SLAM.

A Synchronous Localization Method for Multiple Mobile Robots Based on Visual SLAM Algorithm in the Context of the Internet of Things

Abstract Aiming at the problem that traditional methods cannot meet the problem of synchronous positioning of multi-mobile robots in different motion states, a synchronous positioning method of multi-mobile robots based on visual simultaneous localization and mapping (SLAM) algorithm is proposed. Analyze the general model of SLAM problem, realize visual SLAM feature detection through scale invariant feature transform algorithm, and match image features based on active vision. A multi-mobile robot motion state estimation model is constructed, an octree model is used to construct a multi-robot synchronous localization map, and the camera pose tracking is realized by using the oriented fast accelerated segment test and rotated binary robust independent elementary features points that are not in the target bounding box. The three-dimensional points in the environment recovered by visual SLAM separate the background target and the moving target, and match the corresponding target in the previous frame through the feature to realize the synchronous positioning of the multi-mobile robot. The experimental results show that the method can realize the synchronous positioning of multi-robots under the state of multi-robot linear motion, curvilinear motion and mixed motion, and the positioning accuracy is high.

Visual Simultaneous Localization and Mapping Optimization Method Based on Object Detection in Dynamic Scene

SLAM (Simultaneous Localization and Mapping), as one of the basic functions of mobile robots, has become a hot topic in the field of robotics this year. The majority of SLAM systems in use today, however, disregard the impact of dynamic objects on the system by defining the external environment as static. A SLAM system suitable for dynamic scenes is proposed, aiming at the issue that dynamic objects in real scenes can affect the localization accuracy and map effect of traditional visual SLAM systems. Initially, the enhanced lightweight YOLOv5s target detection algorithm is employed to detect dynamic objects in each frame of the image. Simultaneously, an assessment is conducted on the feature points present on dynamic objects to determine their potential impact on system accuracy, subsequently guiding the decision to retain or exclude these feature points. The preserved static feature points are then utilized for pose estimation and map construction. Experiments on the publicly available TUM dataset and the KITTI dataset are conducted to compare the system in this paper with ORB-SLAM 3, DS-SLAM, and DynaSLAM, and the algorithm is verified to have better performance.

V-SLAM-AIDED PHOTOGRAMMETRY TO PROCESS FISHEYE MULTI-CAMERA SYSTEMS SEQUENCES

Abstract. The advent of mobile mapping systems (MMSs) and computer vision algorithms has enriched a wide range of navigation and mapping tasks such as localisation, 3D motion estimation and 3D mapping. This study focuses on Visual Simultaneous Localisation and Mapping (V-SLAM) in the context of two in-houses MMSs: Ant3D, a patented five-fisheye multi-camera rig and GeoRizon, a high-resolution stereo fisheye rig. The aim is to leverage V-SLAM to enhance the systems performance in near-real-time and non-real-time 3D reconstruction applications. The research investigates both Monocular and Stereo V-SLAM applied to both MMSs and tackles the challenge of combining the V-SLAM estimated trajectory of one or a pair of cameras with known multi-camera relative orientation. We propose a state-of-the-art code that serves as a flexible and extensible platform for MMSs image acquisition and processing, along with an adapted version of the well-established ORB-SLAM3.0. Evaluation is performed in a cultural heritage challenging setup: the Minguzzi spiral staircase in the Duomo di Milano Cathedral. Performed tests highlight that introducing V-SLAM trajectories as well as pre-calibrated interior orientation and multi-camera constraints improve speed, applicability and accuracy of 3D surveys.

An Enhancement of Outdoor Location-Based Augmented Reality Anchor Precision through VSLAM and Google Street View.

Outdoor Location-Based Augmented Reality (LAR) applications require precise positioning for seamless integrations of virtual content into immersive experiences. However, common solutions in outdoor LAR applications rely on traditional smartphone sensor fusion methods, such as the Global Positioning System (GPS) and compasses, which often lack the accuracy needed for precise AR content alignments. In this paper, we introduce an innovative approach to enhance LAR anchor precision in outdoor environments. We leveraged Visual Simultaneous Localization and Mapping (VSLAM) technology, in combination with innovative cloud-based methodologies, and harnessed the extensive visual reference database of Google Street View (GSV), to address the accuracy limitation problems. For the evaluation, 10 Point of Interest (POI) locations were used as anchor point coordinates in the experiments. We compared the accuracies between our approach and the common sensor fusion LAR solution comprehensively involving accuracy benchmarking and running load performance testing. The results demonstrate substantial enhancements in overall positioning accuracies compared to conventional GPS-based approaches for aligning AR anchor content in the real world.