Ting On Chan
Papers
2
Total Citations
26
H-Index
2
About
Ting On Chan is a researcher specializing in 3D point cloud processing, LiDAR sensor calibration, and planar feature segmentation for robotics and computer vision. His most notable contribution is the development of a temporal analysis and automatic calibration method for the Velodyne HDL-32E LiDAR system, a widely used sensor in autonomous navigation and high-accuracy surveying. Published in 2013, this work has garnered 23 citations, reflecting its foundational role in improving LiDAR accuracy for real-world applications. More recently, Chan advanced planar segmentation in 3D point clouds by enhancing the RANSAC algorithm with normal vector and maximum principal curvature clustering. This 2024 work, though newly published with 3 citations, addresses a critical challenge in extracting planar features from noisy data—essential for tasks like mapping and object recognition. By combining geometric insights with robust statistical methods, Chan’s research bridges practical sensor calibration and algorithmic innovation, offering tools that improve both the reliability and precision of 3D sensing systems. His work continues to support the growing demand for efficient, accurate point cloud analysis in autonomous systems and computer vision.
Research Focus
Key Achievements
Top Papers
- 1
- 2