2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA), Journal Year: 2024, Volume and Issue: 3, P. 1 - 8
Published: Sept. 10, 2024
Language: Английский
AIAA SCITECH 2022 Forum, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 3, 2025
Language: Английский
Citations
0
Remote Sensing, Journal Year: 2025, Volume and Issue: 17(5), P. 735 - 735
Published: Feb. 20, 2025
This paper focuses on the problem of ground-motion target localization tracking and motion state estimation for high-altitude reconnaissance using fixed-wing UAVs. Our goal is to accurately locate track ground-moving targets estimate their visible light images, laser measurements distance, UAV position attitude information. Firstly, this uses detection model YOLOv8 obtain pixel positions, combined with measurement data, establish geolocalization target. Secondly, a algorithm hierarchical filtering proposed, performs optoelectronic loads separately. Using range sensor as constraints, load angle quantities are involved together in estimating ground state, resulting improved accuracy estimation. The experimental data show that reduces error by at least 7.5 m 0.8 m/s compared other algorithms.
Language: Английский
Citations
0
PLoS ONE, Journal Year: 2025, Volume and Issue: 20(2), P. e0319071 - e0319071
Published: Feb. 25, 2025
This study addresses the limitations of linear mapping in two-dimensional gimbal control for moving target tracking, which results significant errors and slow response times. To overcome these issues, we propose a nonlinear method that enhances success rate light source tracking systems. Using Raspberry Pi 4B OpenCV, system performs real-time recognition rectangular frames laser spot images. The system, includes an OpenMV H7 Plus camera, captures processes path. Both systems are connected to STM32F407ZGT6 microcontroller drive 42-step stepper motor with precise control. By adjusting parameter c curve, optimize system's performance, balancing speed stability. Our show improvement accuracy, miss 3.3%, average error 0.188% at 1.25 m, 100% tracking. proposed offers substantial advancements systems, demonstrating its potential broader application intelligent fields.
Language: Английский
Citations
0
ACM Transactions on Human-Robot Interaction, Journal Year: 2025, Volume and Issue: unknown
Published: March 12, 2025
Human-robot teams in dynamic environments have the potential to leverage robot sensing and intelligence augment human performance through motion suggestions. More specifically, we examine how humans can use external sensors (fixed or robotic) a planning algorithm help them navigate with obstacles. The novel human-centric velocity-obstacle (HCVO) suggests feasible goal-oriented action while avoiding Participants were placed custom virtual reality (VR) environment tasked follow goal collisions. We demonstrate, over N=10 participants, that HCVO algorithm’s guidance significantly improves safety compared base VO algorithm. then of N=15 participants three conditions: 1) no assistance/control, 2) top-down drone-view entire environment, 3) planner-informed core contributions this research include (1) introducing tuning algorithm, (2) demonstrating benefits (3) standard overhead drone view. Long term, deployment effective planners make people safer from workplace warzone. Code: https://github.com/ROAMR-GT/HCVO-Game . Video: https://www.youtube.com/watch?v=9ITD1GBBz24
Language: Английский
Citations
0
Sensors, Journal Year: 2025, Volume and Issue: 25(7), P. 2190 - 2190
Published: March 30, 2025
Drone-based object detection faces critical challenges, including tiny objects, complex urban backgrounds, dramatic scale variations, and high-frequency detail loss during feature propagation. Current methods struggle to address these challenges while maintaining computational efficiency effectively. We propose Scale-Frequency Detection Transformer (SF-DETR), a novel end-to-end framework for drone-view scenarios. SF-DETR introduces lightweight ScaleFormerNet backbone with Dual Scale Vision modules, Bilateral Interactive Feature Enhancement Module, Multi-Scale Frequency-Fused Network. Extensive experiments on the VisDrone2019 dataset demonstrate SF-DETR's superior performance, achieving 51.0% mAP50 31.8% mAP50:95, surpassing state-of-the-art like YOLOv9m RTDETR-r18 by 6.2% 4.0%, respectively. Further validation of HIT-UAV confirms model's generalization capability. Our work establishes new benchmark provides architecture suitable embedded device deployment in real-world aerial surveillance applications.
Language: Английский
Citations
0
Cluster Computing, Journal Year: 2025, Volume and Issue: 28(5)
Published: April 28, 2025
Language: Английский
Citations
0
Physical Communication, Journal Year: 2025, Volume and Issue: unknown, P. 102691 - 102691
Published: May 1, 2025
Language: Английский
Citations
0
International Journal of Cognitive Computing in Engineering, Journal Year: 2024, Volume and Issue: 5, P. 367 - 378
Published: Jan. 1, 2024
Unmanned Aerial Vehicle (UAV) technology is proposed to improve social safety, provide specialized services, and overall well-being in crowded indoor spaces. The deployment of drones environments can emergency response time, offer various wireless allow efficient tracking, awareness scenarios. In this paper, we propose a UAV-based tracking framework that relies on energy-limited UAVs attempts determine the appropriate placement UAV charging stations (CHSs) design path planning strategy effectively carry out detection/tracking tasks uncertain phenomena. comprises CHS method algorithm. find optimal given number available CHSs so energy consumed by reach nearest reduced. This, consequently, preserves UAV's energy, reducing time required return period none-tracking during CHS. This extend mission enhance detection performance. Based obtained placement, reinforcement learning (RL)–based trajectory algorithm detect track target (event interest) with unknown behavior. RL-based leverages long-term spatio-temporal behavior knowledge targets (i.e., observed learned events) accuracy. Improving leads better decision-making, faster responses, improved security, efficiency applications such as surveillance, defense, search rescue. simulation results demonstrate superior accuracy achieved framework. Compared reference approach, achieves up 65% higher symmetric monitored areas 20% increased asymmetric areas.
Language: Английский
Citations
3
Published: Aug. 16, 2024
The integration of drone technology into healthcare logistics presents a significant opportunity to enhance the speed, reliability, and efficiency medical sample transportation. This study inves-tigates current advancements in technology, focusing on its application rapid secure delivery samples, particularly urban remote regions where traditional transportation methods often face challenges. Utilizing combination recent technological de-velopments such as AI-driven navigation systems, real-time monitoring, payload management, examines how drones can mitigate logistical barriers like traffic conges-tion geographical isolation. research methodology includes comprehensive review case studies from various regions, illustrating practical applications benefits healthcare. results demonstrate substantial reduction time costs, along with improved accessibility services underserved areas. concludes that, while challenges regulatory hurdles privacy concerns remain, on-going supportive frameworks have poten-tial revolutionize logistics, ultimately improving patient outcomes de-livery.
Language: Английский
Citations
3
IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 119464 - 119487
Published: Jan. 1, 2024
Language: Английский
Citations
3