sábado, 30 de marzo de 2013

Computer Vision - OPENCV GSOC 2013

LineMod - 3D object recognition software

Next important dates:
  • March 18th-29th: Organization Application deadline.
  • April 8th: Announcement of GSoC Mentoring Orgs. (whether we're in or out)
  • April 9th-21st: POTENTIAL INTERNS: Discuss project ideas with us 
  • April 22-May 3rd: Application period
  • May 8th: Slot allocations published
  • May 22nd 12-1PST Dedup meeting
  • May 27th Final project decisions are made
  • June 17th: Let's start coding !!!

Project Idea summary

April 9th-21st: Discuss projects below or other ideas with us 
Students may propose their own projects


- Mobile vision app development
Clear "hello world" type of example to make it easier for the rest to start developing mobile vision applications. ios o android examples

-Computational Photography
SUpport mobile cameras on tablets and phones
  • noise estimation and reduction,
  • tilt-shift images and movies,
  • multi-focal point images,
  • high dynamic range images by composition with different shutter times

Vision Applications:
working functionality.

OpenCL Optmization

Mech Turk Interface
  • Easily label images for train test in OpenCV ???

1D and 2D Barcode readers
- We have a basic datamatrix reader. Expand to other kinds of barcodes (1D, other 2D).

Natural barcodes
OpenCV can read calibration patterns. Calibrate a camera, rectify it's output. Put a picture next to a calibration pattern in a scene. Find 2D interest points with features2D. Measure them in the image using the calibration pattern. Use the pattern of interest points and their measures to turn the picture into a calibration pattern/barcode so that the computer recognizes the picture and knows where it is in relation to the iamge.

  • Stretch goal, embeded and retrieve watermarks in the image.

Python examples

Tutorials
Continue with OpenCV Tutorials

Inverted index
create an inverted index of functionality to functions  ---- FACIL

more Qt integration ----PREGUNTAS


SfM integration:
  • Ceres integration (we need some BA stuff). It depends on Eigen but they just changed their license and that could be a micro-module

Matlab integration:  --- PREGUNTAR
  • we could have somebody writing samples/testing the latest wrapper. Needs: OpenCV knowledge a bit, Python knowledge. Write a script
    that takes output from parser (list of classes/methods/functions) and generates C code that is Matlab wrappers (mex knowledge). Find solution to deal with row-major/col major
multi-camera calibration:
  • that should be its own micro-module

RGBD functions:   ---PREGUNTAR
  • We already have normal, plane finder, ICP, we could have more maybe: octrees, plane-plane ICP, depth cleaner ...
Full LINE-MOD implementation:   ----- NO
  • That would focus on the ACCV paper for pre/post processing

Course-ware:   --- PREGUNTAR
  • We want to start offering vision courses using OpenCV.
    • If you are expert in a topic (say it's your area of graduate research, or you've just finished a project or course in a particular topic and can explain it well)
    • Write up the topic, the math and then develop a step by step example of it using OpenCV.

Generic numerical optimization module:
  • We want to have the package of general purpose optimization methods that can be easily used in computer vision algorithms (ex. downhill simplex method, annealing particle filter).
  • This will require a mathematically inclined student and/or one who has taken course work in the area obviously

PYTHON
Expose OpenCV GPU functionality into Python API 
  • Current Python OpenCV wrappers use cv::Mat <=> Numpy array mapping for passing data between C++ and Python worlds. Aim of this project is to adopt PyCuda GPUArray as a counterpart of GpuMat.
  • This would allow to extend cv2 wrapper generator to expose CUDA-powered OpenCV functions.
  • Project requires good knowledge of C++ and Python and willingness to dive into the internals of OpenCV, Python and PyCuda.
  • Expect all sorts of gotchas, subtle issues and design discussion with mentors.
  • The resulting design decisions can be used to wrap the OpenCV's OpenCL functionality with PyOpenCL

GSOC OPENCV APPLICATION - ORG


MENTORES

Anatoly Baksheev
 Researcher, Vision Algorithms on GPU
 Argus/Itseez
 
Serge J. Belongie
 Professor Computer Science and Engineering 
 University of California, San Diego 
 
Alexander Bovyrin
  PhD, Senior Researcher
  Argus/Itseez founder
  NNU Lecturer
  
Gary Bradski
 Founder, Industrial Perception Inc.
 Consulting Prof. Stanford U.
 OpenCV Founder, Technical Content Owner, GSoC Admin
 Co-author of Learning OpenCV Book
 http://www.willowgarage.com/pages/people/gary-bradski-senior-researcher
 
Victor Eruhimov
 OpenCV founding team/Senior Researcher
 Argus/Itseez founder
 NNU Lecturer
 
Adrian Kaehler
 Principle Engineer, Applied Minds
 Co-author of Learning OpenCV Book.
 
Peter Karasev
 PhD Student, MINERVA Research Group
 Georgia Tech
 
Kurt Konolige
 Founder, Industrial Perception Inc
 Consulting Professor, Stanford CS
 
Caroline Pantofaru 
 Researcher Scientist in perceiving people
 http://www.willowgarage.com/pages/people/caroline-pantofaru-research-scientist
 
Vadim Pisarevsky
 OpenCV founding team/Czar
 
Vincent Rabaud
 Research Engineer/Perception, Willow Garage
 
Ethan Rublee
  Founder, Industrial Perception Inc
 Ported OpenCV to Android
 See Android vision apps under "Robot view" or "the vegan robot" 
 
Eric Christiansen
 PhD Student, UCSD
 

Back up Mentors

Mark Asbach
 Fraunhofer IAIS
 Schloss Birlinghoven
 Sankt Augustin, Germany
 http://mmprec.iais.fraunhofer.de/asbach.html
 
Nicolas Saunier, Ph.D.
 Assistant Professor
 Civil, Geological and Mining Department (CGM)
 École Polytechnique de Montréal
 http://nicolas.saunier.confins.net
 
Alexander Mordvintsev
 Software Engineer
 http://znah.net
 

No hay comentarios:

Publicar un comentario