Karina Ambrosch

About

Karina Ambrosch is a leading researcher in embedded computer vision, with a primary focus on real-time stereo matching systems. Her work bridges the gap between algorithmic efficiency and hardware implementation, particularly through the use of Field Programmable Gate Arrays (FPGAs). Her most impactful contribution, "SAD-Based Stereo Matching Using FPGAs" (2008, 43 citations), established a foundational approach for achieving high-speed depth perception on resource-constrained platforms, a critical need for autonomous robotics. She further advanced the field by extending non-parametric transforms for stereo matching on Bayer-filtered cameras (2008, 8 citations), enabling robust performance under challenging lighting conditions without sacrificing computational speed. Her 2009 work, "Embedded Stereo Vision," synthesizes these techniques into a cohesive framework for practical deployment. Ambrosch’s research has directly influenced the development of low-latency, power-efficient vision systems for mobile robots and autonomous vehicles, making her a key figure in the evolution of embedded perception technology.

Research Focus

Key Achievements

Top Papers

1. 1
   SAD-Based Stereo Matching Using FPGAs

   43 citations · 2008
2. 2
   Extending two non-parametric transforms for FPGA based stereo matching using bayer filtered cameras

   8 citations · 2008
3. 3
   Embedded Stereo Vision

   3 citations · 2009

Key Collaborators

Contact & Links