Results 71 to 80 of about 1,847 (173)
IET Radar, Sonar &Navigation, Volume 19, Issue 1, January/December 2025.This paper proposes spatio‐probabilistic models (SPMs) of high‐rise architectural landmarks as a novel radar‐based method for robust UAV navigation in urban environments. Utilising kernel density estimation on real radar echoes received by a custom‐designed X‐band ENAVI radar, our approach enables independent and reliable landmark detection and ...
Urszula Libal, Pawel Biernacki
wiley +1 more source
IEEE Access, 2022 The Visual Simultaneous Localization and Mapping (VSLAM) is a system based on the scene’s features to estimate a map and the system pose. Commonly, VSLAM algorithms are focused on a static environment; however, some dynamic objects are present in ...
Daniela Esparza, Gerardo Flores
doaj +1 more source
IET Intelligent Transport Systems, Volume 18, Issue S1, Page 2827-2855, December 2024.Sporadic deployment of unmanned aerial vehicles for priority‐based logistics demands inclusive safety‐driven and security smartness to address the myriads of associated risks. The incremental integration of explainable AI, blockchain, and zero trust cybersecurity paradigms is essential to achieving this, albeit with several requirements and ...
Simeon Okechukwu Ajakwe +1 more
wiley +1 more source
A photogrammetric approach for real‐time visual SLAM applied to an omnidirectional system
The Photogrammetric Record, Volume 39, Issue 187, Page 577-599, September 2024.This study presents a real‐time vSLAM for omnidirectional systems, adapting ORB‐SLAM with a rigorous equisolid‐angle projection model. Analysing a 140 m trajectory, it shows fewer discrepancies using hyperhemispherical images, outperforming a generic model like EUCM. Accuracy started at sub‐0.12 m, reaching metre‐level at the end.
Thaisa Aline Correia Garcia +3 more
wiley +1 more source
Wireless schedulers with future sight via real-time 3D environment mapping [PDF]
, 2010 This paper proposes a new wireless scheduling methodology which takes advantage of future predictions of data rate for the several users competing for physical access. Based on a system which allows low-cost 3D mapping of an environment in real-time, the
Beach, MA, Doufexi, A, Han, C, Webb, MW
core +3 more sources
Knowledge Distillation for Feature Extraction in Underwater VSLAM
2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 Accepted by IEEE International Conference on Robotics and Automation (ICRA 2023),6 ...
Yang, Jinghe +5 more
openaire +2 more sources
IET Image Processing, Volume 18, Issue 1, Page 13-21, 10 January 2024.In order to effectively integrate consistent information between the multiple layers of the Swin Transformer, the model conducts parameter self‐ensemble of the internal blocks of the Swin Transformer. Abstract The Swin‐Transformer is a variant of the Vision Transformer, which constructs a hierarchical Transformer that computes representations with ...
Yixuan Xu +3 more
wiley +1 more source
Improved ORB-SLAM3 Based on MCMCC for Mobile Robot Navigation
Taiyuan Ligong Daxue xuebaoPurposes The sparse feature map established by using VSLAM cannot be directly used for navigation, and the existing methods of converting sparse feature maps into grid maps for navigation suffer from low accuracy of map construction, resulting in the ...
ZHAO Liang +4 more
doaj +1 more source
J-MOD$^{2}$: Joint Monocular Obstacle Detection and Depth Estimation
, 2017 In this work, we propose an end-to-end deep architecture that jointly learns to detect obstacles and estimate their depth for MAV flight applications.
Ciarfuglia, Thomas A. +3 more
core +1 more source
Low-feedback multiple-access and scheduling via location and geometry information [PDF]
, 2010 This paper exploits the use of location information of wireless terminals to improve the performance of a beamforming system and support multiple access. Based on a system providing real-time 3D coordinate information of all terminals in the environment,
Beach, MA, Doufexi, A, Han, C, Webb, MW
core +2 more sources