Rene Vidal, PhD


Primary Appointments

Professor, Department of Biomedical Engineering

Professor, Institute for Computational Medicine

Professor, Center for Imaging Science

Director, Vision Dynamics and Learning Lab

Secondary Appointments

Department of Electrical and Computer Engineering

Department of Computer Science

Department of Mechanical Engineering

Office: Clark 302B
Lab: Vision, Dynamics and Learning Lab


B.S., Electrical Engineering, Pontificia Universidad Católica de Chile, 1997
M.S., Electrical Engineering and Computer Sciences, University of California at Berkeley, 2000
Ph.D., Electrical Engineering and Computer Sciences, University of California at Berkeley, 2003

Research Interests

In addition to Rene Vidal’s appointment as JHU BME associate professor, he also directs the Center for imaging Science’s Vision Dynamics and Learning Lab. Research centers around several key areas:

  • Biomedical image analysis: Surgical gesture and skill recognition, analysis of high angular resolution diffusion imaging (HARDI), classification of stem cell derived cardiac myocites, interactive medical image segmentation
  • Computer vision:
    camera sensor networks,
    activity recognition,
    dynamic texture segmentation and recognition, 3D motion segmentation,
    non-rigid shape and motion analysis, structure from motion and multiple view geometry, omnidirectional vision
  • Machine learning:
    manifold clustering, kernels on dynamical systems, GPCA, kernel GPCA, dynamic GPCA
  • Dynamical systems:
    observability, identification, realization, metrics and topology for hybrid systems
  • Robotics:
    formation control of teams of non-holonomic robots,
    coordination and control of multiple autonomous vehicles for pursuit-evasion games,
    multiple view motion estimation and control for landing an unmanned aerial vehicle
  • Signal processing:
    consensus on manifolds, distributed optimization, compressive sensing.

Keen focus on the development of computational methods includes: 1) inferring models from images (image/video segmentation, motion segmentation), static data (subspace clustering) or dynamic data (identification of hybrid systems); and 2) using these models to accomplish a complex task — such as tracking fibers in the brain, recognizing actions in videos, landing a helicopter on a moving platform, pursuing a team of evaders, or following a formation.

Selected Publications

From Pub Med   |   Google Scholar Profile

Publications Search

B. Bejar, L. Zappella, and R. Vidal. Surgical Gesture Classification from Video Data. Medical Image Computing and Computer Assisted Interventions, 2012.

L. Tao, E. Elhamifar, S. Khudanpur, G. Hager, and R. Vidal. Sparse Hidden Markov Models for Surgical Gesture Classification and Skill Evaluation. Information Processing in Computed Assisted Interventions, 2012.

H. E. Cetingul, B. Afsari, M. Wright, P. Thompson, and R. Vidal. Group action induced averaging for HARDI processing. In IEEE International Symposium on Biomedical Imaging, 2012.

A. Goh, C. Lenglet, P. Thompson, and R. Vidal. A Nonparametric Riemannian Framework for Processing High Angular Resolution Diffusion Images and its Applications to ODF-based Morphometry. Neuroimage, 47(3):608–613, 2011.

A. Goh, C. Lenglet, P. Thompson and R. Vidal. Estimating Orientation Distribution Functions with Probability Density Constraints and Spatial Regularity. International Conference on Medical Image Computing and Computer Assisted Intervention, 2009.