Papers
13
Total Citations
380
H-Index
5
About
Yandong Tang is a leading researcher in computer vision and robotics, whose work bridges the gap between 3D perception and autonomous systems. His primary research areas include semantic segmentation, 3D object recognition, and real-time vision for robotic navigation. Tang’s most impactful contribution is his comprehensive review on semantic segmentation methods and datasets, which has garnered 278 citations and serves as a foundational resource for the field. He has also made significant strides in 3D object recognition, developing efficient frameworks that preserve geometric information—a key challenge for robot vision. Inspired by human 3D perception, Tang pioneered obstacle classification and 3D measurement in unstructured environments using Time-of-Flight cameras, achieving 32 citations for its practical application in robotic navigation. His work on short-baseline binocular vision for humanoid ping-pong robots demonstrates his ability to integrate theory with real-time, dynamic systems. More recently, Tang has explored deep learning for volumetric representation and compressed neural networks, addressing the need for efficient object identification in resource-constrained settings. With over 370 total citations and a portfolio spanning from battlefield robotics to sports automation, Tang’s research continues to shape how machines perceive and interact with complex, unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1Methods and datasets on semantic segmentation: A review278 citations · 2018
- 2Efficient 3D object recognition via geometric information preservation37 citations · 2019
- 3
- 4Short-Baseline Binocular Vision System for a Humanoid Ping-Pong Robot6 citations · 2011
- 5
- 6Deep learning of volumetric representation for 3D object recognition5 citations · 2017
- 7
- 8
- 9Fast Ball Detection Method for Ping-Pong Playing Robots3 citations · 2009
- 10