Masoud Dehyadegari
Papers
1
Total Citations
2
H-Index
1
About
Masoud Dehyadegari is a researcher whose work sits at the intersection of high-performance computing and computer vision, with a particular focus on accelerating computationally intensive algorithms. His key research areas include parallel processing architectures, GPU computing, and real-time stereo vision systems. Dehyadegari’s major contribution lies in demonstrating how modern CPU instruction sets—such as SSE3 and AVX2—and CUDA-based GPU acceleration can dramatically speed up stereo matching algorithms, which are critical for applications in robotics, autonomous vehicles, and aerial surveying. His 2017 paper, "Accelerating stereo vision algorithm using SSE3, AVX2, and CUDA," addresses the computational bottleneck of depth detection in real-time systems, offering practical optimization strategies that balance performance and accuracy. While his citation count (2) reflects a niche but focused impact, his work provides a valuable bridge between theoretical parallel computing and real-world vision tasks. Dehyadegari’s research is particularly notable for its hands-on, implementation-driven approach, making it a useful reference for engineers and students seeking to deploy stereo vision in latency-sensitive environments.
Research Focus
Key Achievements
Top Papers
- 1Accelerating stereo vision algorithm using SSE3, AVX2, and CUDA2 citations · 2017