Home Undergrads Graduates Visionaries
 
 
Robotic Graduate Level Courses

Course Number Course Name Offerings
16-720 Computer Vision Every Fall
Most recent offer: Fall 2012
16-722 Sensing and Sensors Every Spring
Most recent offer: Spring 2012

16-720 Computer Vision
 
 
Instructor: Martial Hebert  
University Units : 12  
Semester Offered:  
Every Fall. Most recent offer: Fall 2012  
Course Description  
This course deals with the science and engineering of computer vision, that is, the analysis of patterns in visual images of the world with the goal of reconstructing and understanding the objects and processes in the world that are producing them. The emphasis is on physical, mathematical, and information processing aspects of vision. Topics covered include image formation and representation, camera geometry and calibration, multi-scale analysis, segmentation, contour and region analysis, energy-based techniques, reconstruction of based on stereo, shading and motion, 3-D surface representation and projection, and analysis and recognition of objects and scenes using statistical and model-based techniques. The material is based on "Computer Vision, A Modern Approach" by Ponce & Forsyth augmented with research papers, as appropriate. The course involves considerable Matlab programming exercises. At the end of the term, each student completes a project that is defined based on recently published research papers in computer vision. Example project reports are available here.
 
Prerequisites:  
Linear Algebra, Calculus.
Topics Covered:  
  • Image formation: Geometry, radiometry
  • Filtering
  • Feature extraction: Edges, interest points, and invariant features
  • Motion: Tracking, motion analysis, optical flow
  • Multi-view: Multi-view geometry, stereo reconstruction, structure from motion
  • Image segmentation
  • Object recognition
   
Back to Top

16-722 Sensing and Sensors
 
 
Instractor: Mel Siegel  
University Units : 12  
Semester Offered:  
Every spring. Most recent offer: Spring 2012  
Course Description  

The principles and practices of quantitative perception (sensing) illustrated by the devices and algorithms (sensors) that implement them. Learn to critically examine the sensing requirements of proposed applications of robotics to real problems, to specify the required sensor characteristics, to analyze whether these specifications can be realized even in principle, to compare what can be realized in principle to what can actually be purchased, to understand the engineering factors that account for the discrepancies, and to design transducing, digitizing, and computing systems that come tolerably close to realizing the actual capabilities of available sensors. To the extent that time and interest permit, in addition to the sensing requirements of robot function (manipulation, mobility) per se, illustrative applications will also be drawn from the domain of observations that robots are employed to make (e.g., noninvasively locating buried objects or skeletal features, or nondestructively characterizing natural or manufactured materials), and the domain of infrastructures that robotic applications depend on (e.g., broadcast communication and navigation signals).

 
Prerequisites:  
Linear Algebra, Calculus, Undergraduate or Graduate level Vision or Graphics.
Topics Covered:  
  • Measurements: combining multiple signal and noise sources
  • Data acquisition: getting signals into computers
  • Light and image sensors
  • Imaging and range-finding instruments
  • Sound and touch sensing
  • Navigation sensing
  • Chemical sensing
  • Sensing for security
  • Multi-component security systems
  • People sensing
 
Back to Top

 

 

RI_Vision Courses Webpage
 
School of computer science | Carnegie Mellon University