Papers

1

Total Citations

5

H-Index

1

About

David Przewozny is a researcher at the forefront of edge computing and real-time computer vision, with a focus on optimizing neural networks for resource-constrained robotic systems. His most-cited work, "Data Fusion for Cross-Domain Real-Time Object Detection on the Edge" (2023, 5 citations), tackles a critical challenge in autonomous robotics: how to balance computational efficiency with detection accuracy when multiple neural networks compete for limited onboard resources. In this study, Przewozny demonstrated that a single YOLOv5 object-detection model can effectively serve multiple robotic tasks simultaneously, significantly reducing hardware demands without catastrophic performance loss. This contribution is particularly valuable for deploying intelligent systems on drones, mobile robots, and IoT devices where power and processing capacity are at a premium. By exploring the trade-offs between model consolidation and detection fidelity, Przewozny’s work provides a practical blueprint for engineers designing scalable, real-time perception pipelines. His research sits at the intersection of embedded AI, sensor fusion, and edge deployment, offering actionable insights for students and practitioners aiming to bring deep learning to the physical world.

Research Focus

Key Achievements

1
H-Index
1
Papers
5
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
Data Fusion for Cross-Domain Real-Time Object Detection on the Edge
5 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 4
🏛 Institutions: Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago