Object detection

Object detection

• 1.
  Object-Detection Somesh Vyas
• 2.
  Content OpenCV an Introduction Haar-training Flow-chart Algorithmpart-1 Algorithm part-2 Implementation Code Reference References
• 3.
  OpenCV an Introduction OpenCVis an open source C++ library for image processing and computer vision, originally developed by Intel and now supported by Willow Garage. It is free for both commercial and non-commercial use. It is a library of many inbuilt functions mainly aimed at real time image processing. Now it has several hundreds of image processing and computer vision algorithms which make developing advanced computer vision applications easy and efficient.
• 4.
  Haar-training The OpenCV librarygives us a greatly interesting demo for a object detection. Furthermore, it provides us programs (or functions) which they used to train classifiers for their object detection system (called HaarTraining). Thus, we can create our own object classifiers using the functions.
• 5.
  Flow-chart Gather image setof object e.g. fish Capture stream from camera Gather negative image set without object of interest While capture yes Create vector files of positive image set Query frame by frame Create dat file of negative one’s Convert each frame to grayscale haar training of positive and negative image sets to generate xml file Apply histogram equalization on image
• 6.
  Load haar cascade file Storeobjects to a variable faces while using detectMultiScale method While faces yes Draw Rectangle on object
• 7.
  Algorithm part-1 Collect imageset of particular object e.g. fish Crop these images for better haarCascade file Collect negative image set which doesn’t contain object Use openCV createsamples utility to generate positive .vec file for generating variations in image set Create collection file format .dat file of negative images using this command $ find [image dir] -name '*.[image ext]' > [description file] Using openCV haartraining utility we will generate xml file which is called cascade classifier file to detect object.
• 8.
  Algorithm part-2 Use OpenCVfor performing real time detection in video Use cvCaptureFromCAM to capture from camera Use cvQueryFrame to quering frame by frame for processing images to get ROI(Reason of Interest). Convert image to grayscale image using COLOR_BGR2GRAY of Imgproc class Use Histogram Equalization method for more accuracy.
• 9.
  Algorithm part-2 Using cascadeClassifierclass of OpenCV load haar cascade xml file generated in part 1 of algorithm Use detectMultiScale method of cascadeClassifier class to detect objects and store them in variable. Iterate the variable so we can get all ROI Use rectangle function to generate rectangle on ROI
• 10.
  Implementation Install windows 7 Installvisual studio Install crygwin Using crygwin generate sample training data positive sample data as well as negative data. Perform haartraining on sample data to generate haar cascade xml file. Install OpenCV
• 11.
  Set all environmentvariables according to opencv path Configure Visual studio project to get OpenCV libraries Use C++ or python for implementing algorithm
• 12.
  Code reference Code referencecould be found at http://pastebin.com/Vw00NgCt This is visual studio code for detecting object By changing haar cascade file with haar cascade fish file we can detect particular class of fish
• 13.
  References http://note.sonots.com/SciSoftware/haartraining.html http://docs.opencv.org/doc/tutorials/objdetect/cascade_clas sifier/cascade_classifier.html http://docs.opencv.org/doc/tutorials/imgproc/histograms/his togram_equalization/histogram_equalization.html https://opencv-pythontutroals.readthedocs.org/en/latest/py_tutorials/py_objdetec t/py_face_detection/py_face_detection.html http://opencv-srf.blogspot.in/2013/05/installing-configuringopencv-with-vs.html