Dynamic SLAM Visual Odometry Based on Instance Segmentation:A Comprehensive Review

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.

A dynamic detection method to improve SLAM performance

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.

ClusterSLAM:A SLAM backend for simultaneous rigid body clustering and motion estimation

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.