Tsuhan Chen
Papers
6
Total Citations
173
H-Index
5
About
Tsuhan Chen is a leading researcher in computer vision and robotics, with a focus on holistic scene understanding, stereo vision, and human-robot interaction. His major contributions include pioneering work on feedback-enabled cascaded classification models for scene understanding, which integrate subtasks like scene categorization, depth estimation, and object detection to improve overall performance—a concept that has garnered over 100 combined citations. Chen also advanced real-time stereo vision by designing high-performance algorithms for massively data parallel platforms, such as GPUs, enabling efficient 3-D reconstruction for robot navigation. His research extends to robotic object detection, where he developed methods to improve classifiers using sparse graphs for path planning, and human pointing estimation, creating efficient calibration techniques for gesture-based robot interaction. With a distributed vision-based infrastructure for multi-robot navigation, Chen has addressed key challenges in autonomous navigation. His work, cited over 170 times, demonstrates significant impact in enabling robots to perceive and interact with complex environments, making him a notable figure in the intersection of computer vision and robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5An efficient method for human pointing estimation for robot interaction10 citations · 2014
- 6A distributed vision-based infrastructure for multi-robot navigation2 citations · 2010