Papers
7
Total Citations
67
H-Index
5
About
Qiong Chang is a researcher at the intersection of embedded computer vision, robotics, and bioinspired sensing. Their work focuses on enabling real-time, high-accuracy depth estimation and motion generation on resource-constrained platforms, particularly embedded GPUs. Chang’s major contributions include developing efficient stereo matching algorithms—such as the zero-means normalized cross correlation (ZNCC) and the TinyStereo coarse-to-fine framework—which achieve significant speedups while maintaining precision, with applications in autonomous driving and robotics. Their most cited paper, “Efficient stereo matching on embedded GPUs with zero-means cross correlation” (23 citations), demonstrates this impact. In robotics, Chang has advanced realistic motion generation through deep learning and keyframeless imitation methods using multivariate empirical mode decomposition, addressing the uncanny valley effect. Notably, their work on “Advanced Bioinspired Organic Sensors for Future‐Oriented Intelligent Applications” (2023) extends into flexible, self-adaptive sensing systems. With over 65 total citations across seven publications, Chang’s research is shaping the future of intelligent, low-power embedded systems for vision and robotics.
Research Focus
Key Achievements
Top Papers
- 1Efficient stereo matching on embedded GPUs with zero-means cross correlation23 citations · 2021
- 2A deep learning framework for realistic robot motion generation20 citations · 2021
- 3
- 4
- 5
- 6Acceleration of video stabilization using embedded GPU4 citations · 2022
- 7