Josh Weberruss

Papers

Total Citations

H-Index

About

Josh Weberruss is a researcher whose work sits at the intersection of computer vision, robotics, and reconfigurable computing. His most influential contribution is the first multilevel implementation of the Harris-Stephens corner detector and the ORB feature extractor on FPGA hardware, detailed in his 2017 paper "FPGA acceleration of multilevel ORB feature extraction for computer vision." This work addresses a critical bottleneck in robotics: ORB features are essential for tasks like visual odometry and SLAM, but their computational demands often exceed the capabilities of general-purpose processors. By accelerating this pipeline on FPGA, Weberruss demonstrated a path to real-time, low-power feature extraction—a key enabler for autonomous systems operating in the field. With 31 citations, this paper has become a foundational reference for researchers exploring hardware acceleration in vision-based robotics. His work stands out for bridging the gap between algorithmic efficiency and practical hardware constraints, offering a tangible solution for embedded and mobile robotic platforms. Weberruss’s contributions highlight the growing importance of domain-specific architectures in making advanced computer vision algorithms feasible for real-world deployment.