Simultaneous location and mapping (SLAM) technology is key in robot autonomous navigation. Most visual SLAM (VSLAM) algorithms for dynamic environments cannot achieve sufficient positioning accuracy and real-time performance simultaneously. When the dynamic object proportion is too high, the VSLAM algorithm will collapse. To solve the above problems, this paper proposes an indoor dynamic VSLAM algorithm called YDD-SLAM based on ORB-SLAM3, which introduces the YOLOv5 object detection algorithm and integrates deep information. Firstly, the objects detected by YOLOv5 are divided into eight subcategories according to their motion characteristics and depth values. Secondly, the depth ranges of the dynamic object and potentially dynamic object in the moving state in the scene are calculated. Simultaneously, the depth value of the feature point in the detection box is compared with that of the feature point in the detection box to determine whether the point is a dynamic feature point; if it is, the dynamic feature point is eliminated. Further, multiple feature point optimization strategies were developed for VSLAM in dynamic environments. A public data set and an actual dynamic scenario were used for testing. The accuracy of the proposed algorithm was significantly improved compared to that of ORB-SLAM3. This work provides a theoretical foundation for the practical application of a dynamic VSLAM algorithm.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10708714 | PMC |
| http://dx.doi.org/10.3390/s23239592 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Mycosis fungoides and Sézary syndrome - Simplifying the approach for dermatologists. Part 1: Etiopathogenesis, clinical features and evaluation.
Indian J Dermatol Venereol Leprol
January 2025
Department of Nuclear Medicine, Army Hospital Research and Referral, New Delhi, India.
Cutaneous T-cell lymphomas (CTCL) are a heterogeneous group of extranodal non-Hodgkin's lymphomas characterised by a cutaneous infiltration of malignant monoclonal T lymphocytes. While this broad spectrum of disease with its varied etiopathogenesis, clinical features and management options are well characterised, an approach from a dermatologist's perspective is lacking in the literature. We strive to elucidate the approach from a clinician's point of view, especially in respect of clinical examination, investigations, staging and management options that are available in the realm of the dermatologists.
View Article and Find Full Text PDFA Spatiotemporal Feature-Based Approach for the Detection of Unlicensed Taxis in Urban Areas.
Sensors (Basel)
December 2024
School of Urban Construction and Transportation, Hefei University, Hefei 230601, China.
Unlicensed taxis seriously disrupt the transportation market order, and threaten passenger safety. Therefore, this paper proposes a method for identifying unlicensed taxis based on travel characteristics. First, the vehicle mileage and operation time are calculated using traffic surveillance bayonet data, and variance analysis is applied to identification indicators for unlicensed taxis.
View Article and Find Full Text PDFEGNet: 3D Semantic Segmentation Through Point-Voxel-Mesh Data for Euclidean-Geodesic Feature Fusion.
Sensors (Basel)
December 2024
School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China.
With the advancement of service robot technology, the demand for higher boundary precision in indoor semantic segmentation has increased. Traditional methods of extracting Euclidean features using point cloud and voxel data often neglect geodesic information, reducing boundary accuracy for adjacent objects and consuming significant computational resources. This study proposes a novel network, the Euclidean-geodesic network (EGNet), which uses point cloud-voxel-mesh data to characterize detail, contour, and geodesic features, respectively.
View Article and Find Full Text PDFInCrowd-VI: A Realistic Visual-Inertial Dataset for Evaluating Simultaneous Localization and Mapping in Indoor Pedestrian-Rich Spaces for Human Navigation.
Sensors (Basel)
December 2024
Institute of Computer Science, Zurich University of Applied Sciences, 8400 Winterthur, Switzerland.
Simultaneous localization and mapping (SLAM) techniques can be used to navigate the visually impaired, but the development of robust SLAM solutions for crowded spaces is limited by the lack of realistic datasets. To address this, we introduce InCrowd-VI, a novel visual-inertial dataset specifically designed for human navigation in indoor pedestrian-rich environments. Recorded using Meta Aria Project glasses, it captures realistic scenarios without environmental control.
View Article and Find Full Text PDFMambaPose: A Human Pose Estimation Based on Gated Feedforward Network and Mamba.
Sensors (Basel)
December 2024
School of Electronic Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China.
Human pose estimation is an important research direction in the field of computer vision, which aims to accurately identify the position and posture of keypoints of the human body through images or videos. However, multi-person pose estimation yields false detection or missed detection in dense crowds, and it is still difficult to detect small targets. In this paper, we propose a Mamba-based human pose estimation.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!