Aolong Zha

The University of Tokyo, National Institute of Advanced Industrial Science and Technology

Papers

Total Citations

H-Index

About

Aolong Zha is a researcher specializing in efficient stereo vision and depth estimation for embedded systems, with a focus on enabling high-performance computer vision on resource-constrained platforms like embedded GPUs. His major contributions center on developing fast and accurate stereo matching algorithms that overcome the computational limitations of mobile and embedded devices. Notably, his 2021 paper "Efficient stereo matching on embedded GPUs with zero-means cross correlation" has garnered 23 citations, demonstrating its impact on the field. Zha introduced innovative techniques such as ZigZag scanning-based zero-means normalized cross correlation (Z2-ZNCC) in 2020, which significantly accelerates stereo matching without sacrificing accuracy. His recent work, "TinyStereo: A Tiny Coarse-to-Fine Framework for Vision-Based Depth Estimation on Embedded GPUs" (2024), further advances this line of research by proposing a compact framework that balances speed and precision for applications in robotics vision and autonomous driving. Through these contributions, Zha has addressed critical hardware limitations, making real-time depth estimation feasible on low-power platforms, and his work continues to influence the development of efficient vision systems for autonomous systems.