A Mobile Robot Visual SLAM System With Enhanced Semantics Segmentation

  title={A Mobile Robot Visual SLAM System With Enhanced Semantics Segmentation},
  author={Feng Li and Weijun Li and Wenfeng Chen and Weifeng Xu and Linqing Huang and Dan Li and Shuting Cai and Ming Yang and Xiaoming Xiong and Yuan Liu},
  journal={IEEE Access},
Traditional visual simultaneous localization and mapping (SLAM) systems mostly based on small-area static environments. In recent years, some studies focused on combining semantic information with visual SLAM. However, most of them are hard to obtain better performance in the large-scale dynamic environment. And the accuracy, rapidity of the system still needs to strengthen. In this paper, we develop a more efficient semantic SLAM system in the two-wheeled mobile robot by using semantic… 
4 Citations
A Robot Pose Estimation Optimized Visual SLAM Algorithm Based on CO-HDC Instance Segmentation Network for Dynamic Scenes
A contour optimization hybrid dilated convolutional neural network (CO-HDC) algorithm, which can perform a lightweight calculation on the basis of improving the accuracy of contour segmentation, and the Beetle Antennae Search Douglas–Peucker algorithm is proposed to lighten the contour extraction.
SLAM; definition and evolution
An Enhanced Pedestrian Visual-Inertial SLAM System Aided with Vanishing Point in Indoor Environments
A novel pedestrian dead reckoning (PDR)-aided visual-inertial SLAM is presented, taking advantage of the enhanced vanishing point (VP) observation, to enhance the proposed system’s robustness and the positioning accuracy.
Adaptive Fuzzy Output Feedback Simultaneous Posture Stabilization and Tracking Control of Wheeled Mobile Robots With Kinematic and Dynamic Disturbances
The proposed AFOFTC method can maintain satisfactory posture stabilization and tracking control performance despite the kinematic and dynamic disturbances, and a stability analysis and experimental results are provided to validate the proposed scheme.


DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments
  • Chao Yu, Zuxin Liu, F. Qiao
  • Computer Science
    2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2018
A robust semantic visual SLAM towards dynamic environments named DS-SLAM is proposed, which combines semantic segmentation network with moving consistency check method to reduce the impact of dynamic objects, and thus the localization accuracy is highly improved in dynamic environments.
A Compatible Framework for RGB-D SLAM in Dynamic Scenes
This paper proposes a workflow to segment the objects accurately, which will be marked as the potentially dynamic-object area based on the semantic information, and integrates the semantics-based motion detection and the segmentation approach with an RGB-D SLAM system.
Semantic SLAM Based on Object Detection and Improved Octomap
A Semantic SLAM system which builds the semantic maps with object-level entities, and it is integrated into the RGB-D SLAM framework, and an improved Octomap based on the Fast Line Rasterization Algorithm is constructed to improve the computational efficiency.
A dense semantic mapping system based on CRF-RNN network
This work develops a novel system to build 3-D Visual maps annotated with semantic information, employing the CRF-RNN algorithm for semantic segmentation, and integrating the semantic algorithm with ORB-SLAM to achieve the semantic mapping.
Robust Semantic Mapping in Challenging Environments
This work combines the deep neural network with the visual SLAM system to conduct semantic mapping, and uses an optical-flow-based method to deal with the moving objects such that the method is capable of working robustly in dynamic environments.
DRE-SLAM: Dynamic RGB-D Encoder SLAM for a Differential-Drive Robot
By fusing the information of an RGB-D camera and two encoders that are mounted on a differential-drive robot, a tightly coupled feature-based method is proposed to fuse the two types of information based on the optimization to construct a static background OctoMap in both dynamic and static environments.
Motion removal for reliable RGB-D SLAM in dynamic environments
Improving RGB-D SLAM in dynamic environments: A motion removal approach
ORB-SLAM: A Versatile and Accurate Monocular SLAM System
A survival of the fittest strategy that selects the points and keyframes of the reconstruction leads to excellent robustness and generates a compact and trackable map that only grows if the scene content changes, allowing lifelong operation.
A Novel Approach for Lidar-Based Robot Localization in a Scale-Drifted Map Constructed Using Monocular SLAM
A 2D-LRF-based localization algorithm which allows the robot to locate itself and resolve the scale of the local map simultaneously and is able to globally localize the robot in real-time.