Cheng‐Yu Ho
Papers
1
Total Citations
4
H-Index
1
About
Cheng‐Yu Ho is a researcher whose work lies at the intersection of computer vision and neural computation, with a particular focus on stereo matching algorithms. His most cited contribution, "Neural network based stereo matching algorithm utilizing vertical disparity" (2010), introduces an innovative approach to solving the correspondence problem in stereo vision. The paper presents SMAVD, a stereo matching algorithm that leverages vertical disparity and employs a two-dimensional Hopfield neural network (HNN) to match stereo pairs. By developing an energy function that incorporates three key constraints, Ho's work addresses a fundamental challenge in depth perception from binocular images. While his citation count of 4 reflects the specialized nature of this early work, the research demonstrates a sophisticated integration of neural network principles with geometric computer vision. Ho's contribution is particularly notable for its novel use of vertical disparity—a less commonly exploited cue in stereo matching—and its application of Hopfield networks, which were emerging as powerful tools for optimization problems in vision. This work represents a meaningful step in advancing automated depth estimation, with potential applications in robotics, 3D reconstruction, and autonomous navigation.
Research Focus
Key Achievements
Top Papers
- 1