Graphics enhanced version of this site

Vision for Safe Driving
This lab is no longer active.

Heads: Simon Baker and Takeo Kanade
Contact: Simon Baker

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

Associated center: VASC

We are developing a variety of computer vision algorithms and systems for use in automotive safe driving applications. The systems and algorithms can be divided into three main categories:

Car Interior Understanding

Techniques for driver monitoring.

Road Scene Understanding

Techniques to understand the world around the car, the road scene.

Sensor Design

Novel active vision sensors for automotive applications.

Name - Title <Email Address>
• Simon Baker - Adjunct Faculty (Adjunct)
• [Home] Peter Barnum - PhD Student, RI <pbarnum@andrew.cmu.edu>
• Adrian E Broadhurst - Project Scientist
• Robert Collins - Adjunct Faculty (Adjunct) <rcollins@andrew.cmu.edu>
• [Home] Ankur Datta - PhD Student, RI <adatta@andrew.cmu.edu>
• Hironobu Fujiyoshi - Visiting Research Scientist
• Junya Inada - Visiting Industrial Scholar
• Takahiro Ishikawa - Visiting Industrial Scholar
• [Home] Takeo Kanade - U.A. and Helen Whitaker University Prof. <tk@cs.cmu.edu>
• [Home] Qifa Ke - Systems Scientist, RI/CS
• [Home] James Kuffner - Assistant Professor <kuffner@cs.cmu.edu>
• [Home] Iain Matthews - Senior Systems Scientist <iainm@cs.cmu.edu (Currently On Leave)>
• [Home] Andreas Nowatzyk - Associate Professor, RI/ECE
• Hiroshi Sakai - Visiting Industrial Scholar
• [Home] John J Sprouse - PhD Student, RI
• Matthew Zucker - PhD Student, RI <mzucker@andrew.cmu.edu>

• AAM Fitting Algorithms - Many varieties of algorithms for fitting Cootes and Taylor's "Active Appearance Models" are developed.
• Car Tracking - Algorithms for tracking cars and generating "bird's eye views" of the surrounding road scene.
• Gaze Estimation - Algorithms for estimating where someone is looking
• Prediction & Planning - This project analyses the safety and interaction of moving objects in complex road scenes.
• Setting Low-Level Vision Parameters - Techniques for feeding back information from high-level vision modules to low-level modules to improve the performance of the overall system.
• Template Update - We are developing an algorithm to update template tracking that avoids the "drifting" problem of the naive update algorithm.

• Approximating State-Space Obstacles for Non-Holonomic Motion Planning
  M. Zucker
  tech. report CMU-RI-TR-06-27, Robotics Institute, Carnegie Mellon University, May, 2006. [Abstract]
  Download: pdf [172 KB] copyrighted

• Evaluating Error Functions for Robust Active Appearance Models
  B. Theobald, I. Matthews, and S. Baker
  Proceedings of the International Conference on Automatic Face and Gesture Recognition, April, 2006, pp. 149 - 154. [Abstract]
  Download: pdf [229 KB] copyrighted

• On the Dimensionality of Deformable Face Models
  I. Matthews, J. Xiao, and S. Baker
  tech. report CMU-RI-TR-06-12, Robotics Institute, Carnegie Mellon University, March, 2006. [Abstract]
  Download: pdf [1489 KB] copyrighted

• Active Appearance Models with Occlusion
  R. Gross, I. Matthews, and S. Baker
  Image and Vision Computing, Vol. 24, No. 6, 2006, pp. 593-604. [Abstract]
  Download: pdf [3404 KB] copyrighted

• Generic vs. person specific active appearance models
  R. Gross, I. Matthews, and S. Baker
  Image and Vision Computing, Vol. 23, No. 11, November, 2005, pp. 1080-1093. [Abstract]
  Download: pdf [2086 KB] copyrighted

• Multi-View AAM Fitting and Camera Calibration
  S.C. Koterba, S. Baker, I. Matthews, C. Hu, J. Xiao, J. Cohn, and T. Kanade
  Proc. International Conference on Computer Vision, Vol. 1, October, 2005, pp. 511 - 518. [Abstract]
  Download: pdf [2053 KB] copyrighted

• Monte Carlo Road Safety Reasoning
  A.E. Broadhurst, S. Baker, and T. Kanade
  IEEE Intelligent Vehicle Symposium (IV2005), IEEE, June, 2005, pp. 319 - 324. [Abstract]
  Download: pdf [294 KB] copyrighted

• Active Appearance Models Revisited
  I. Matthews and S. Baker
  International Journal of Computer Vision, Vol. 60, No. 2, November, 2004, pp. 135 - 164. [Abstract]
  Download: pdf [759 KB] copyrighted

• A Prediction and Planning Framework for Road Safety Analysis, Obstacle Avoidance and Driver Information
  A.E. Broadhurst, S. Baker, and T. Kanade
  Proceedings of the 11th World Congress on Intelligent Transportation Systems, October, 2004. [Abstract]
  Download: pdf [311 KB] copyrighted

• Passive Driver Gaze Tracking with Active Appearance Models
  T. Ishikawa, S. Baker, I. Matthews, and T. Kanade
  Proceedings of the 11th World Congress on Intelligent Transportation Systems, October, 2004. [Abstract]
  Download: pdf [1907 KB] copyrighted