Dynamic Simultaneous Localization and Mapping(SLAM)in visual scenes is currently a major research area in fields such as robot navigation and autonomous driving.However,in the face of complex real-world envi-ronments,...Dynamic Simultaneous Localization and Mapping(SLAM)in visual scenes is currently a major research area in fields such as robot navigation and autonomous driving.However,in the face of complex real-world envi-ronments,current dynamic SLAM systems struggle to achieve precise localization and map construction.With the advancement of deep learning,there has been increasing interest in the development of deep learning-based dynamic SLAM visual odometry in recent years,and more researchers are turning to deep learning techniques to address the challenges of dynamic SLAM.Compared to dynamic SLAM systems based on deep learning methods such as object detection and semantic segmentation,dynamic SLAM systems based on instance segmentation can not only detect dynamic objects in the scene but also distinguish different instances of the same type of object,thereby reducing the impact of dynamic objects on the SLAM system’s positioning.This article not only introduces traditional dynamic SLAM systems based on mathematical models but also provides a comprehensive analysis of existing instance segmentation algorithms and dynamic SLAM systems based on instance segmentation,comparing and summarizing their advantages and disadvantages.Through comparisons on datasets,it is found that instance segmentation-based methods have significant advantages in accuracy and robustness in dynamic environments.However,the real-time performance of instance segmentation algorithms hinders the widespread application of dynamic SLAM systems.In recent years,the rapid development of single-stage instance segmentationmethods has brought hope for the widespread application of dynamic SLAM systems based on instance segmentation.Finally,possible future research directions and improvementmeasures are discussed for reference by relevant professionals.展开更多
We propose a dynamic simultaneous localization and mapping technology for unsupervised motion removal(UMR-SLAM),which is a deep learning-based dynamic RGBD SLAM.It is the first time that a scheme combining scene flow ...We propose a dynamic simultaneous localization and mapping technology for unsupervised motion removal(UMR-SLAM),which is a deep learning-based dynamic RGBD SLAM.It is the first time that a scheme combining scene flow and deep learning SLAM is proposed to improve the accuracy of SLAM in dynamic scenes,in response to the situation where dynamic objects cause pose changes.The entire process does not require explicit object segmentation as supervisory information.We also propose a loop detection scheme that combines optical flow and feature similarity in the backend optimization section of the SLAM system to improve the accuracy of loop detection.UMR-SLAM is rewritten based on the DROID-SLAM code architecture.Through experiments on different datasets,it has been proven that our scheme has higher pose accuracy in dynamic scenarios compared with the current advanced SLAM algorithm.展开更多
Background As visual simultaneous localization and mapping(SLAM)is primarily based on the assumption of a static scene,the presence of dynamic objects in the frame causes problems such as a deterioration of system rob...Background As visual simultaneous localization and mapping(SLAM)is primarily based on the assumption of a static scene,the presence of dynamic objects in the frame causes problems such as a deterioration of system robustness and inaccurate position estimation.In this study,we propose a YGC-SLAM for indoor dynamic environments based on the ORB-SLAM2 framework combined with semantic and geometric constraints to improve the positioning accuracy and robustness of the system.Methods First,the recognition accuracy of YOLOv5 was improved by introducing the convolution block attention model and the improved EIOU loss function,whereby the prediction frame converges quickly for better detection.The improved YOLOv5 was then added to the tracking thread for dynamic target detection to eliminate dynamic points.Subsequently,multi-view geometric constraints were used for re-judging to further eliminate dynamic points while enabling more useful feature points to be retained and preventing the semantic approach from over-eliminating feature points,causing a failure of map building.The K-means clustering algorithm was used to accelerate this process and quickly calculate and determine the motion state of each cluster of pixel points.Finally,a strategy for drawing keyframes with de-redundancy was implemented to construct a clear 3D dense static point-cloud map.Results Through testing on TUM dataset and a real environment,the experimental results show that our algorithm reduces the absolute trajectory error by 98.22%and the relative trajectory error by 97.98%compared with the original ORBSLAM2,which is more accurate and has better real-time performance than similar algorithms,such as DynaSLAM and DS-SLAM.Conclusions The YGC-SLAM proposed in this study can effectively eliminate the adverse effects of dynamic objects,and the system can better complete positioning and map building tasks in complex environments.展开更多
Dynamic visual SLAM (Simultaneous Localization and Mapping) is an important research area, but existing methods struggle to balance real-time performance and accuracy in removing dynamic feature points, especially whe...Dynamic visual SLAM (Simultaneous Localization and Mapping) is an important research area, but existing methods struggle to balance real-time performance and accuracy in removing dynamic feature points, especially when semantic information is missing. This paper presents a novel dynamic SLAM system that uses optical flow tracking and epipolar geometry to identify dynamic feature points and applies a regional dynamic probability method to improve removal accuracy. We developed two innovative algorithms for precise pruning of dynamic regions: first, using optical flow and epipolar geometry to identify and prune dynamic areas while preserving static regions on stationary dynamic objects to optimize tracking performance;second, propagating dynamic probabilities across frames to mitigate the impact of semantic information loss in some frames. Experiments show that our system significantly reduces trajectory and pose errors in dynamic scenes, achieving dynamic feature point removal accuracy close to that of semantic segmentation methods, while maintaining high real-time performance. Our system performs exceptionally well in highly dynamic environments, especially where complex dynamic objects are present, demonstrating its advantage in handling dynamic scenarios. The experiments also show that while traditional methods may fail in tracking when semantic information is lost, our approach effectively reduces the misidentification of dynamic regions caused by such loss, thus improving system robustness and accuracy.展开更多
Simultaneous localization and mapping(SLAM) technology is a research hotspot in the field of intelligent mobile robot, and many researchers have developed many classic systems in the past few decades. However, most of...Simultaneous localization and mapping(SLAM) technology is a research hotspot in the field of intelligent mobile robot, and many researchers have developed many classic systems in the past few decades. However, most of the existing SLAM methods assume that the environment of the robot is static, which results in the performance of the system being greatly reduced in the dynamic environment. To solve this problem, a new dynamic object detection method based on point cloud motion analysis is proposed and incorporated into ORB-SLAM2. First, the method is regarded as a preprocessing stage, detecting moving objects in the scene, and then removing the moving objects to enhance the performance of the SLAM system. Experiments performed on a public RGB-D dataset show that the motion cancellation method proposed in this paper can effectively improve the performance of ORB-SLAM2 in a highly dynamic environment.展开更多
We present a practical backend for stereo visual SLAM which can simultaneously discover individual rigid bodies and compute their motions in dynamic environments.While recent factor graph based state optimization algo...We present a practical backend for stereo visual SLAM which can simultaneously discover individual rigid bodies and compute their motions in dynamic environments.While recent factor graph based state optimization algorithms have shown their ability to robustly solve SLAM problems by treating dynamic objects as outliers,their dynamic motions are rarely considered.In this paper,we exploit the consensus of 3 D motions for landmarks extracted from the same rigid body for clustering,and to identify static and dynamic objects in a unified manner.Specifically,our algorithm builds a noise-aware motion affinity matrix from landmarks,and uses agglomerative clustering to distinguish rigid bodies.Using decoupled factor graph optimization to revise their shapes and trajectories,we obtain an iterative scheme to update both cluster assignments and motion estimation reciprocally.Evaluations on both synthetic scenes and KITTI demonstrate the capability of our approach,and further experiments considering online efficiency also show the effectiveness of our method for simultaneously tracking ego-motion and multiple objects.展开更多
基金the National Natural Science Foundation of China(No.62063006)the Natural Science Foundation of Guangxi Province(No.2023GXNS-FAA026025)+3 种基金the Innovation Fund of Chinese Universities Industry-University-Research(ID:2021RYC06005)the Research Project for Young andMiddle-Aged Teachers in Guangxi Universi-ties(ID:2020KY15013)the Special Research Project of Hechi University(ID:2021GCC028)financially supported by the Project of Outstanding Thousand Young Teachers’Training in Higher Education Institutions of Guangxi,Guangxi Colleges and Universities Key Laboratory of AI and Information Processing(Hechi University),Education Department of Guangxi Zhuang Autonomous Region.
文摘Dynamic Simultaneous Localization and Mapping(SLAM)in visual scenes is currently a major research area in fields such as robot navigation and autonomous driving.However,in the face of complex real-world envi-ronments,current dynamic SLAM systems struggle to achieve precise localization and map construction.With the advancement of deep learning,there has been increasing interest in the development of deep learning-based dynamic SLAM visual odometry in recent years,and more researchers are turning to deep learning techniques to address the challenges of dynamic SLAM.Compared to dynamic SLAM systems based on deep learning methods such as object detection and semantic segmentation,dynamic SLAM systems based on instance segmentation can not only detect dynamic objects in the scene but also distinguish different instances of the same type of object,thereby reducing the impact of dynamic objects on the SLAM system’s positioning.This article not only introduces traditional dynamic SLAM systems based on mathematical models but also provides a comprehensive analysis of existing instance segmentation algorithms and dynamic SLAM systems based on instance segmentation,comparing and summarizing their advantages and disadvantages.Through comparisons on datasets,it is found that instance segmentation-based methods have significant advantages in accuracy and robustness in dynamic environments.However,the real-time performance of instance segmentation algorithms hinders the widespread application of dynamic SLAM systems.In recent years,the rapid development of single-stage instance segmentationmethods has brought hope for the widespread application of dynamic SLAM systems based on instance segmentation.Finally,possible future research directions and improvementmeasures are discussed for reference by relevant professionals.
文摘We propose a dynamic simultaneous localization and mapping technology for unsupervised motion removal(UMR-SLAM),which is a deep learning-based dynamic RGBD SLAM.It is the first time that a scheme combining scene flow and deep learning SLAM is proposed to improve the accuracy of SLAM in dynamic scenes,in response to the situation where dynamic objects cause pose changes.The entire process does not require explicit object segmentation as supervisory information.We also propose a loop detection scheme that combines optical flow and feature similarity in the backend optimization section of the SLAM system to improve the accuracy of loop detection.UMR-SLAM is rewritten based on the DROID-SLAM code architecture.Through experiments on different datasets,it has been proven that our scheme has higher pose accuracy in dynamic scenarios compared with the current advanced SLAM algorithm.
基金Supported by Jiangsu Key R&D Program(BE2021622)Jiangsu Postgraduate Practice and Innovation Program(SJCX23_0395).
文摘Background As visual simultaneous localization and mapping(SLAM)is primarily based on the assumption of a static scene,the presence of dynamic objects in the frame causes problems such as a deterioration of system robustness and inaccurate position estimation.In this study,we propose a YGC-SLAM for indoor dynamic environments based on the ORB-SLAM2 framework combined with semantic and geometric constraints to improve the positioning accuracy and robustness of the system.Methods First,the recognition accuracy of YOLOv5 was improved by introducing the convolution block attention model and the improved EIOU loss function,whereby the prediction frame converges quickly for better detection.The improved YOLOv5 was then added to the tracking thread for dynamic target detection to eliminate dynamic points.Subsequently,multi-view geometric constraints were used for re-judging to further eliminate dynamic points while enabling more useful feature points to be retained and preventing the semantic approach from over-eliminating feature points,causing a failure of map building.The K-means clustering algorithm was used to accelerate this process and quickly calculate and determine the motion state of each cluster of pixel points.Finally,a strategy for drawing keyframes with de-redundancy was implemented to construct a clear 3D dense static point-cloud map.Results Through testing on TUM dataset and a real environment,the experimental results show that our algorithm reduces the absolute trajectory error by 98.22%and the relative trajectory error by 97.98%compared with the original ORBSLAM2,which is more accurate and has better real-time performance than similar algorithms,such as DynaSLAM and DS-SLAM.Conclusions The YGC-SLAM proposed in this study can effectively eliminate the adverse effects of dynamic objects,and the system can better complete positioning and map building tasks in complex environments.
基金the National Natural Science Foundation of China(No.62063006)to the Guangxi Natural Science Foundation under Grant(Nos.2023GXNSFAA026025,AA24010001)+4 种基金to the Innovation Fund of Chinese Universities Industry-University-Research(ID:2023RY018)to the Special Guangxi Industry and Information Technology Department,Textile and Pharmaceutical Division(ID:2021 No.231)to the Special Research Project of Hechi University(ID:2021GCC028)to the Key Laboratory of AI and Information Processing,Education Department of Guangxi Zhuang Autonomous Region(Hechi University)No.2024GXZDSY009.
文摘Dynamic visual SLAM (Simultaneous Localization and Mapping) is an important research area, but existing methods struggle to balance real-time performance and accuracy in removing dynamic feature points, especially when semantic information is missing. This paper presents a novel dynamic SLAM system that uses optical flow tracking and epipolar geometry to identify dynamic feature points and applies a regional dynamic probability method to improve removal accuracy. We developed two innovative algorithms for precise pruning of dynamic regions: first, using optical flow and epipolar geometry to identify and prune dynamic areas while preserving static regions on stationary dynamic objects to optimize tracking performance;second, propagating dynamic probabilities across frames to mitigate the impact of semantic information loss in some frames. Experiments show that our system significantly reduces trajectory and pose errors in dynamic scenes, achieving dynamic feature point removal accuracy close to that of semantic segmentation methods, while maintaining high real-time performance. Our system performs exceptionally well in highly dynamic environments, especially where complex dynamic objects are present, demonstrating its advantage in handling dynamic scenarios. The experiments also show that while traditional methods may fail in tracking when semantic information is lost, our approach effectively reduces the misidentification of dynamic regions caused by such loss, thus improving system robustness and accuracy.
基金supported by the National Natural Science Foundation of China (No.61876167)the Natural Science Foundation of Zhejiang Province (No.LY20F030017)。
文摘Simultaneous localization and mapping(SLAM) technology is a research hotspot in the field of intelligent mobile robot, and many researchers have developed many classic systems in the past few decades. However, most of the existing SLAM methods assume that the environment of the robot is static, which results in the performance of the system being greatly reduced in the dynamic environment. To solve this problem, a new dynamic object detection method based on point cloud motion analysis is proposed and incorporated into ORB-SLAM2. First, the method is regarded as a preprocessing stage, detecting moving objects in the scene, and then removing the moving objects to enhance the performance of the SLAM system. Experiments performed on a public RGB-D dataset show that the motion cancellation method proposed in this paper can effectively improve the performance of ORB-SLAM2 in a highly dynamic environment.
基金supported by the National Key Technology R&D Program(Project No.2017YFB1002604)the Joint NSFC-DFG Research Program(Project No.61761136018)the National Natural Science Foundation of China(Project No.61521002)。
文摘We present a practical backend for stereo visual SLAM which can simultaneously discover individual rigid bodies and compute their motions in dynamic environments.While recent factor graph based state optimization algorithms have shown their ability to robustly solve SLAM problems by treating dynamic objects as outliers,their dynamic motions are rarely considered.In this paper,we exploit the consensus of 3 D motions for landmarks extracted from the same rigid body for clustering,and to identify static and dynamic objects in a unified manner.Specifically,our algorithm builds a noise-aware motion affinity matrix from landmarks,and uses agglomerative clustering to distinguish rigid bodies.Using decoupled factor graph optimization to revise their shapes and trajectories,we obtain an iterative scheme to update both cluster assignments and motion estimation reciprocally.Evaluations on both synthetic scenes and KITTI demonstrate the capability of our approach,and further experiments considering online efficiency also show the effectiveness of our method for simultaneously tracking ego-motion and multiple objects.
