Abstract
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 segmentation to recognize people, chairs, and other objects in every keyframe. With a preliminary understanding of the environment, fusing the RGB-D camera and encoders information, to localization and creating a dense colored octree map without dynamic objects. Besides, for the incomplete identification of movable objects, we used image processing algorithms to enhance the semantic segmentation effect. In the proposed method, enhanced semantic segmentation in keyframes dramatically increases the efficiency of the system. Moreover, fusing the different sensors can highly raise localization accuracy. We conducted experiments on various datasets and in some real environments and compared them with DRE-SLAM, DS-SLAM, to evaluate the performance of the proposed approach. The results suggest we significantly improve the processing efficiency, robustness, and quality of the map.
Highlights
Visual simultaneous localization and mapping (SLAM) is a fundamental technique in the study of intelligent mobile robot by constructing or updating a map of an unknown environment while simultaneously keeping track of its pose
We propose a mobile robot visual SLAM system with enhanced semantic segmentation
The data fusion method derived from RTAB-Map [18], the feature extraction and matching algorithm of ORB-SLAM2 [3] was applied, a new system combined with enhanced semantics segmentation is proposed
Summary
Visual simultaneous localization and mapping (SLAM) is a fundamental technique in the study of intelligent mobile robot by constructing or updating a map of an unknown environment while simultaneously keeping track of its pose. The data fusion method derived from RTAB-Map [18], the feature extraction and matching algorithm of ORB-SLAM2 [3] was applied, a new system combined with enhanced semantics segmentation is proposed. The results defined by the edge-to-depth compensation search are compared to the unqualified results, as shown in Figure 7: In the process of enhanced semantic segmentation, our system first identifies the target in the color image and preprocesses the goal. If the dynamic objects are not processed, they will cause a massive interference to the constructed map and positioning results For invalid points, they have been filtered by the previous steps, where dynamic pixels are removed, and static pixels are left to use for optimization and map building. Given: The color image of edge extraction, kedg; The depth image of keyframes, kdep; The tag image, klab; The pixel of tag image, p; The depth threshold, dth; The dynamic object, Odyn; The depth value, dval
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
