A5102719113- Traffic Prediction and Management Techniques
- Robotics and Sensor-Based Localization
- UAV Applications and Optimization
- Transportation Planning and Optimization
- Air Traffic Management and Optimization
- Advanced Image and Video Retrieval Techniques
- Robotic Path Planning Algorithms
- Software Reliability and Analysis Research
- Software System Performance and Reliability
- Multimodal Machine Learning Applications
- Advanced Image Fusion Techniques
- 3D Surveying and Cultural Heritage
- Indoor and Outdoor Localization Technologies
- Electrostatic Discharge in Electronics
- Neural Networks and Applications
- Image Enhancement Techniques
- Human Mobility and Location-Based Analysis
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Software Engineering Research
- Advanced Vision and Imaging
- Urban and Freight Transport Logistics
- AI and HR Technologies
- Visual Attention and Saliency Detection
- Automated Road and Building Extraction
Civil Aviation Flight University of China
2023-2025
Beihang University
2024
Shandong Institute of Business and Technology
2024
The rapid development of the drone industry has facilitated emergence concepts such as urban air mobility (UAM), driving a wave logistics in very low-level (VLL) airspace. However, existing trajectory planning algorithms do not adequately consider ground risks and secondary conflicts arising from high-density operations VLL To address these challenges, this paper proposes two-stage hierarchical 4D method to minimize multiple risks. Specifically, consists risk-aware global module (RAGPM) for...
Pedestrian Attribute Recognition (PAR) is one of the indispensable tasks in human-centered research. However, existing datasets neglect different domains (e.g., environments, times, populations, and data sources), only conducting simple random splits, performance these has already approached saturation. In past five years, no large-scale dataset been opened to public. To address this issue, paper proposes a new large-scale, cross-domain pedestrian attribute recognition fill gap, termed...
The open-vocabulary understanding of UAV aerial images plays a crucial role in enhancing the intelligence level remote sensing applications, such as disaster assessment, precision agriculture, and urban planning. In this paper, we propose an innovative model for images, which combines vision–language methods to achieve efficient recognition segmentation unseen categories by generating multi-view image descriptions feature extraction. To enhance generalization ability robustness model,...
The successful application of new technologies such as remotely piloted aircraft systems, distributed electric propulsion and automatic control systems on vertical take-off landing(eVTOL) has prompted Urban Air Mobility (UAM) to be mentioned frequently. UAM is a newly raised transport mode using eVTOL people cargo in urban areas, which thought share some the traffic ground. One prerequisites for operate regular basis that its demand can support operating costs, so forecasting necessary. We...
Air logistics transportation has become one of the most promising markets for civil drone industry. However, large flow, high density, and complex environmental characteristics urban scenes make tactical conflict resolution very challenging. Existing methods are limited by insufficient collision avoidance success rates when considering non-cooperative targets fail to take temporal constraints pre-defined 4D trajectory into consideration. In this paper, a novel reinforcement learning-based...
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...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Pedestrian Attribute Recognition (PAR) is one of the indispensable tasks in human-centered research. However, existing datasets neglect different domains (e.g., environments, times, populations, and data sources), only conducting simple random splits, performance these has already approached saturation. In past five years, no large-scale dataset been opened to public. To address this issue, paper proposes a new large-scale, cross-domain pedestrian attribute recognition fill gap, termed...
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...
Neural-networks-driven intelligent data-plane (NN-driven IDP) is becoming an emerging topic for excellent accuracy and high performance. Meanwhile we argue that NN-driven IDP should satisfy three design goals: the flexibility to support various NNs models, low-latency-high-throughput inference performance, data-plane-unawareness harming no performance functionality. Unfortunately, existing work either over-modify IDP, or insert inline pipelined accelerators into data-plane, failing meet...