Jonas Schorlemer
Papers
1
Total Citations
7
H-Index
1
About
Jonas Schorlemer is a researcher at the forefront of applying deep learning to humanitarian demining and embedded systems. His work centers on the intersection of computer vision, field-programmable gate arrays (FPGAs), and safety-critical AI, with a particular focus on detecting improvised explosive devices. His most cited paper, "Detecting Improvised Land-mines using Deep Neural Networks on GPR Image Dataset targeting FPGAs" (2022, 7 citations), introduces a novel approach that combines ground-penetrating radar imagery with deep neural networks optimized for FPGA deployment. This contribution is notable for addressing the real-world constraints of power, size, and latency in conflict zones, making AI-based mine detection more practical for field use. Schorlemer’s research directly tackles the enduring threat of unexploded ordnance in post-conflict regions, where thousands of lives remain at risk. By bridging the gap between high-accuracy neural networks and low-resource hardware, his work has implications for both humanitarian technology and edge AI. His achievements reflect a commitment to engineering solutions that save lives, positioning him as a rising voice in applied machine learning for social good.
Research Focus
Key Achievements
Top Papers
- 1