Summary
Mohammad Mehralian is a founder and seasoned computer vision engineer with over 10 years building production-grade CV systems for surveillance, ITS, and embedded platforms. He combines deep theoretical expertise in multiple-view geometry, SLAM/VO and a novel EKFPnP contribution from his research with hands-on skills in modern deep learning (TensorFlow, YOLO) and high-performance C++ development. Mohammad has delivered real-time, high-uptime video analytics—counting millions of vehicles—optimizing inference with TensorRT and deploying on Jetson Xavier NX. He is comfortable across the stack: algorithm design, multi-threaded C++11+ systems, Qt/ImGui GUIs, and cloud-based analytics. Based in Tehran, he bridges academia and industry, having moved ideas from a MATLAB 3D-reconstruction prototype into robust commercial products. Beyond code, he brings an engineer’s depth in math and system design that helps turn complex geometric problems into reliable, deployable solutions.
10 years of coding experience
11 years of employment as a software developer
Amirkabir University of Technology
Doctor of Philosophy (PhD), Artificial Intelligence and Robotic, Doctor of Philosophy (PhD), Artificial Intelligence and Robotic at Iran University of Science and Technology
English, Arabic, Persian