open source fpga stereo vision

http://danstrother.com/2011/06/10/fpga-stereo-vision-core-released/

http://danstrother.com/2011/01/24/fpga-stereo-vision-project/

Cameralink details

Details of Cameralink can be found here:
http://www.volkerschatz.com/hardware/clink.html

Cameralink cable extender
http://www.networkcable.com/PDF/BITMAXX_EQCL_3-19-09.pdf

http://forums.xilinx.com/t5/Spartan-Family-FPGAs/LVDS-SERDES-in-Spartan6-Camera-Link-or-DDR-style/td-p/313871

http://forums.xilinx.com/t5/Virtex-Family-FPGAs/camera-link-implementation-on-V-5/m-p/120150#M8821

http://www.xilinx.com/support/documentation/application_notes/xapp1071_V6_ADC_DAC_LVDS.pdf

Image Processing Courses

1. Stanford Course CS448F (HWs in C++)
http://www.stanford.edu/class/cs448f/

2. Purdue Course EE367 Video Lectures
https://engineering.purdue.edu/~bouman/ece637/

3. Image Processing Course at Utah
http://www.eng.utah.edu/~cs6640/
Video Lectures:

4. Pattern Recognition Class
http://www.youtube.com/playlist?list=PLuRaSnb3n4kRDZVU6wxPzGdx1CN12fn0w

5. Image Analysis Class
http://www.youtube.com/playlist?list=PLuRaSnb3n4kSgSV35vTPDRBH81YgnF3Dd

Computer Vision Material

Prerequisities for Computer Vision
a. Introduction to Computer Graphics
b. Computational Photography
c. Introduction to Machine Learning

1.Institute for Pure and Applied Mathematics (UCLA Summer School 2013)
http://www.ipam.ucla.edu/schedule.aspx?pc=GSS2013
Comments: Nice Videos from 2 weeks of workshop

2. Advances in Computer Vision (MIT Course)
http://people.csail.mit.edu/torralba/courses/6.869/6.869.computervision.htm
Comments: Nice ppt and exercises

3. CS143 Introduction to Computer Vision (Brown Univ Course)
http://cs.brown.edu/courses/cs143/
Comments: Teaches Intuitive Thinking about Images

4. Computational Photography
http://graphics.cs.cmu.edu/courses/15-463/2010_spring/463.html
Comments: Excellent Introduction to Computational Photography

5. 

Object Tracking

1. Background Detection using OpenCV
http://mateuszstankiewicz.eu/?p=189#!

Video Lectures on Image Procesing

1. UC Davis Image Processing Course
https://www.youtube.com/playlist?list=PLA64AFAE28B8DD0FD

2. Digital Image Processing by Charles Bouman (C++)
https://www.youtube.com/playlist?list=PL3ZrjaBngMS15UhKHUnNqW5wLBA4vlQeB

3. UC Berkeley Image Processing Course
http://www-video.eecs.berkeley.edu/~avz/video_225b.html

4.Good Image Processing Lectures
https://www.youtube.com/playlist?list=PLFF4241D8F970FA32

5. Computer Vision Lecture by UCF
https://www.youtube.com/watch?v=715uLCHt4jE&list=PLOUso-Fehhx1OAMR5UG9yHOGvX4SwO3X0

Linear Algebra Courses:
https://www.youtube.com/watch?v=f2eYLK6TpRs&list=PLD41890D674A5B2C7

Image Processing Algorithms to know

1. Canny Edge Detector, Sobel Edge Detector
https://www.youtube.com/watch?v=P35WsRDnTsU
Code:http://pythongeek.blogspot.com/2012/06/canny-edge-detection.html

2. Harris Corner Detector (What is the difference between canny and sobel)
https://www.youtube.com/watch?v=P35WsRDnTsU

Review Eigen Vectors in Linear Algebra

3. What is SIFT (Scale 
https://www.youtube.com/watch?v=NPcMS49V5hg

Pattern-matching algorithms, denoising algorithms

Vision Processing using FPGA - Apps

http://www.t3lab.it/en/progetti/vialab/
Missing Link Electronics

How to make a pinhole camera

1. http://www.exploratorium.edu/science_explorer/pringles_pinhole.html

2. http://www.mrpinhole.com/calcpinh.php

3. 

Topics I want to know

1) Imatest Master -- Testing Image Quality
such Dynamic Range Test etc.,

2) Bayer Coding, White Balance, Gamma Correction

3) Object Detection, Recognition, Tracking in low Signal to Noise Ratio Conditions

4) Pin Hole Camera, FOV, Aperture, Shutter Speed

5) OCR, Biometrics, Depth Estimation

6) Defocussed Lens

7) Textures, Video Textures

Image Processing 2- Apply Filters to Images

Convolution:

Things to remember:
a) Reverse kernel horizontally and vertically before applying
b) Output Image Size.rows = InputImageSize.rows - KernelImageSize.rows + 1
Output Image Size.rows = InputImageSize.cols- KernelImageSize.cols+ 1
c) Normalize the kernel so that overflows won't happen
d) Truncate Pixels >255 to 255 and pixels <0 (negative) to 0

def convolve(image, kernel):
  '''Convolve the given image and kernel

  Inputs:

  image - a single channel (rows, cols) image with dtype uint8

  kernel - a matrix of shape (d, d) and dtype float

  Outputs:

  output - an output array of the same dtype as image, and of shape
  (rows - d + 1, cols - d + 1)
 
  Every element of output should contain the application of the kernel to the
  corresponding location in the image.

  Output elements that result in values that are greater than 255 should be 
  cropped to 255, and output values less than 0 should be set to 0.
  '''
  oimage = None
  # Insert your code here.----------------------------------------------------
  # Get size of kernel, image and initialize output array
  kernel_row= kernel.shape[0]
  kernel_col= kernel.shape[1]
  iimage_row= image.shape[0]
  iimage_col= image.shape[1]
  print image.shape
  print kernel.shape
  
  oimage_row= iimage_row-kernel_row +1
  oimage_col= iimage_col-kernel_col +1
  #Initialize array as UINT8
  oimage = np.zeros((oimage_row,oimage_col),dtype=np.uint8)
  print oimage.shape

  # Reverse kernel; Use Special trick of -1
  rkernel = kernel[::-1,::-1]

  #Perform Convolution: Product and Sum
  for i in range(0,oimage_row):
    for j in range(0,oimage_col):
      image_buf= image[i:i+kernel_row,j:j+kernel_col]
      image_buf_prod=image_buf*rkernel
      pixelf= image_buf_prod.sum();
      if pixelf < 0:
        oimage[i,j]=0
      else:
        if pixelf > 255:
          oimage[i,j] = 255
        else:
          # convert float value as uint8
          oimage[i,j] = np.uint8(pixelf)
  #print oimage   

OpenCV Source Code Documentation

Matrix.cpp - has all data structure matrix related operators and functions
convert.cpp -- has all the conversion functions such as split,merge

Image Processing 1- OpenCV, C++ - Color to Greyscale Conversion

Soln 1:

#include "stdafx.h"
#include <opencv2/highgui/highgui.hpp>
#include <iostream>
#include <opencv/cv.h>

using namespace cv;
using namespace std;

int main()
{
    //Read Color Image
    Mat im_rgb = imread("C:/Users/kvemishe/Documents/Vision/images/kitten.jpg");

    //waitKey is important for image display; 0 means wait forever
    imshow("Kitten",im_rgb);
    waitKey(0);

    //Convert Color to GrayScale
    Mat img_grey;
    cvtColor(im_rgb,img_grey,CV_BGR2GRAY);

    //Write Greyscale to file location
    imwrite("C:/Users/kvemishe/Documents/Vision/images/kittengrey.jpg",img_grey);
}

Image Processing in Python

1. Example 1
http://antianti.org/?p=440

2. Print np array with precision
np.set_printoptions(precision=4)

3. Convert float array to integer array
where calcImg is the input image
output = calcImg.astype(np.uint8)

Setting up Python

http://www.et.byu.edu/~nas52/blog/?p=126

http://antianti.org/?p=440

Vision and Image Processing Books

1. Morphological Image Analysis: Principles and Applications (Pierre Soille)

(Available in the library)

2. Image Processing Handbook (J.C.Russ)

3. Handbook of Pattern Recognition and Computer Vision (C.H.Chen)

4. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
http://www.amazon.com/Vision-Computational-Investigation-Representation-Information/dp/0262514621

Interesting Blogs on Image Processing

So, I started my journey on learning image processing....

I started looking for interesting posts on image processing

1) Steve on Image Processing
http://blogs.mathworks.com/steve/