Oscar Rahnama

Papers

Total Citations

H-Index

About

Oscar Rahnama is a researcher specializing in computer vision, embedded systems, and real-time depth perception for robotics applications. His work focuses on bridging the gap between computationally intensive stereo vision algorithms and the practical constraints of low-power embedded platforms — a critical challenge in modern autonomous systems. Rahnama's most notable contribution is his 2018 paper, "Real-Time Dense Stereo Matching With ELAS on FPGA-Accelerated Embedded Devices," which has garnered 38 citations and represents a significant advancement in making dense stereo matching viable for resource-constrained robotic systems. By leveraging FPGA acceleration, his work demonstrates how passive stereo cameras — cheaper and more versatile than active sensors like LiDAR — can produce real-time depth maps without sacrificing performance. This work addresses one of stereo vision's fundamental limitations: the computational burden of depth map generation. His earlier 2017 paper on real-time depth processing further establishes his commitment to practical, efficient solutions for embedded platforms. Together, these contributions make Rahnama a valuable voice in the robotics and computer vision communities, particularly for researchers seeking power-efficient, cost-effective alternatives to active depth sensing technologies.