Papers
4
Total Citations
39
H-Index
3
About
Yun Liang is a researcher specializing in real-time multimedia processing, high-performance computing, and GPU-accelerated signal processing, with notable contributions to both spatial audio localization and video enhancement technologies. Liang's most influential work centers on the real-time implementation and performance optimization of 3D sound localization on GPUs, a technically demanding challenge with broad applications in camera steering systems, robotics audition, and gunshot detection. By harnessing the parallel processing power of GPUs, this research demonstrated how computationally intensive three-dimensional audio algorithms could be made viable for real-world deployment, garnering over 30 citations across related publications. Beyond audio processing, Liang has extended expertise into video analytics, developing a component-based distributed framework for coherent, real-time video dehazing — addressing a critical preprocessing bottleneck that traditional image-based dehazing methods struggle to overcome at scale. This distributed architecture work reflects a broader commitment to building practical, scalable systems for challenging perceptual computing problems. Collectively, Liang's research sits at an important intersection of signal processing, parallel computing, and computer vision, offering meaningful contributions to researchers and engineers working on intelligent, real-time sensing and perception systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4A component-driven distributed framework for real-time video dehazing3 citations · 2017