Fangyu Li

Fangyu Li is a senior system software engineer at NVIDIA. He conducts research and development for computer vision and machine learning projects, with a focus on video understanding (including multi-object tracking) and 3D reconstruction. His work at NVIDIA has been applied in efficient and scalable intelligent video AI systems to enable applications in smart transportation, IOT, and robotics. He received the best paper award at the 2021 IEEE Intelligent Vehicles Symposium. He has several publications in top computer vision and robotics conferences and holds three pending and issued patents. He obtained a M.Sc. in computer vision from Carnegie Mellon University in 2019 and a B.E. from Tsinghua University.
Avatar photo

Posts by Fangyu Li

Computer Vision / Video Analytics

Mitigating Occlusions in Visual Perception Using Single-View 3D Tracking in NVIDIA DeepStream

When it comes to perception for Intelligent Video Analytics (IVA) applications such as traffic monitoring, warehouse safety, and retail shopper analytics, one... 8 MIN READ
Computer Vision / Video Analytics

State-of-the-Art Real-time Multi-Object Trackers with NVIDIA DeepStream SDK 6.2

When you observe something over a period of time, you can find trends or patterns that enable predictions. With predictions, you can, for example, proactively... 9 MIN READ