A5025704189- Robotics and Sensor-Based Localization
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Underwater Vehicles and Communication Systems
- UAV Applications and Optimization
- Image Enhancement Techniques
- Advanced Image and Video Retrieval Techniques
- Indoor and Outdoor Localization Technologies
Civil Aviation Flight University of China
2022-2025
Nighttime semantic segmentation represents a challenging frontier in computer vision, made particularly difficult by severe low-light conditions, pronounced noise, and complex illumination patterns. These challenges intensify when dealing with Unmanned Aerial Vehicle (UAV) imagery, where varying camera angles altitudes compound the difficulty. In this paper, we introduce NoctuDroneNet (Nocturnal UAV Drone Network, hereinafter referred to as NoctuDroneNet), real-time model tailored...
With the accelerated growth of UAV industry, researchers are paying close attention to flight safety UAVs. When a loses its GPS signal or encounters unusual conditions, it must perform an emergency landing. Therefore, real-time recognition landing zones on ground is important research topic. This paper employs semantic segmentation approach for recognizing zones. First, we created dataset aerial images, denoted as UAV-City. A total 600 images were densely annotated with 12 categories. Given...
Object detection for aerial images is a crucial and challenging task in the field of computer vision. Previous CNN-based methods face problems related to extreme variation object scales complex background images, which vary significantly from natural scenes. On other hand, great many existing detectors highly rely on computational performance cannot handle real-time tasks. To address this problems, we propose lightweight network named VC-YOLO. In backbone part, introduce receptive extended...
This study was designed to address the challenges of autonomous navigation facing UAVs in urban air mobility environments without GPS. Unlike traditional localization methods that rely heavily on GPS and pre-mapped routes, Mamba-VNPS leverages a self-supervised learning framework advanced feature extraction techniques achieve robust real-time external signal dependence. The results show significantly outperforms across multiple aspects, including error. These innovations provide scalable...