Yanhua Jiang

MSc Beijing Institute of Technology

Robotics and Perception Group

Department of Informatics

University of Zurich

Email: jiangyanhuabituzh (at) gmail (dot) com

Office: Haidian District, South Zhongguancun Street 5

Phone: +86 68 91 86 52

I am a Ph.D. candiate at Beijing Institute of Technology for Intelligent Vehicle in Beijing, China, in Prof. Huiyan Chen's Intelligent vehicle research center. Otherwise, I worked as a visiting Ph.D. student with the Robotics and Perception Group led by Prof. Davide Scaramuzza from October 2012 to October 2013.



Research Interests

Stereo Visual Odometry for Ground Vehicle

My current research is in the context of Stereo Visual Odometry for Wheeled Vehicles. Supervised by prof. Davide Scaramuzza, we recently proposed a new algorithm for the ego-motion estimation of a ground wheeled vehicle moving in dynamic outdoor environments. The main contribution of our method is using model initialized ICP registration to select a set of "high quality" inliers. The performance of the approach has been evaluated on publicly-available datasets (KITTI and Devon Island) collected over several kilometers in both urban environments and challenging off-road terrains.


Previous Projects

Monocular Visual Odometry

We present a novel method to realize monocular visual odometry system. Vehicular kinematic constraints are used in the motion estimation algorithms. By virtue of appropriate simplification, the close-form solution of motion parameters can be obtained only need to find real roots of a cubic equation. We also developed a simulation platform conducted by CarSim and Matlab to validate the performance of our visual odometry algorithm. Real-time vehicle status parameters including velocity, pitch, roll and yaw are generated by CarSim, meanwhile the positions of the car are also recorded and used as ground truth. Experiments on both simulation platform and real car test achieved promising results.

References

Y. Jiang, H. Chen, G. Xiong, J. Gong, and Y. Jiang. Kinematic Constraints in Visual Odometry of Intelligent Vehicles, IV'12, IEEE, Intelligent Vehicle Symposium, 2012.
Y. Jiang, G. Xiong, Y. Jiang, H. Chen. Design of Simulation Platform of Intelligent Vehicular Visual Odometry Based on CarSim and Matlab, JOURNAL OF MECHANICAL ENGINEERING, Vol.48, No.22, 2012.

Image based Traffic Sign Detection and Recognition

During the Master stage of my direct PhD program at Intelligent Vehicle Research Center at the Beijing Institute of Technology, I developed a traffic sign detection and recognition algorithm based on Ridge Regression and OTSU Method. The algorithm has been implemented and successfully applied in our BIT-III autonomous car, which attended Intelligent Vehicle Future Challenge from 2009 to 2012 and achieved good ranking.

Reference

Y. Jiang, S. Zhou, et.al. Traffic Sign Recognition Using Ridge Regression and OTSU Method, IV'11, IEEE Intelligent Vehicle Symposium, 2011.

Contact information

Address

Yanhua Jiang

Intelligent Vehicle Research Center

School of Mechanical Engineering

Beijing Institute of Technology

South Zhongguancun Street, 5, Haidian District

100081 Beijing

China

Office

Room: Vehicle of the State Key Laboratory, 313

Web

Email: price (at) bit (dot) edu (dot) cn