SVM classifier based on HOG features for “object detection” in OpenCV

by

In order to detect arbitrary objects with using opencv HOG descriptors and SVM classifier, you need to first train the classifier. Playing with the parameters will not help here, sorry 🙁 .

In broad terms, you will need to complete the following steps:

Step 1) Prepare some training images of the objects you want to detect (positive samples). Also you will need to prepare some images with no objects of interest (negative samples).

Step 2) Detect HOG features of the training sample and use this features to train an SVM classifier (also provided in OpenCV).

Step 3) Use the coefficients of the trained SVM classifier in HOGDescriptor::setSVMDetector() method.

Only then, you can use the peopledetector.cpp sample code, to detect the objects you want to detect.

More Related Contents:

  1. using OpenCV and SVM with images
  2. OpenCV unable to set up SVM Parameters
  3. Training custom SVM to use with HOGDescriptor in OpenCV
  4. Setup OpenCV-2.3 for Visual Studio 2010
  5. Image Processing: Algorithm Improvement for ‘Coca-Cola Can’ Recognition
  6. Getting started with OpenCV 2.4 and MinGW on Windows 7
  7. What does OpenCV’s cvWaitKey( ) function do?
  8. OpenCV better detection of red color?
  9. OpenCV C++/Obj-C: Advanced square detection
  10. how to check whether two matrices are identical in OpenCV
  11. Nonfree module is missing in OpenCV 3.0
  12. openCV program compile error “libopencv_core.so.2.4: cannot open shared object file: No such file or directory” in ubuntu 12.04
  13. Copy an cv::Mat inside a ROI of another one
  14. Compiling a static executable with CMake
  15. Converting cv::Mat to IplImage*
  16. Fast color quantization in OpenCV
  17. Convert a single color with cvtColor
  18. Assertion failed (size.width>0 && size.height>0)
  19. How to get a color palette from an image using OpenCV [closed]
  20. Inverse fourier transformation in OpenCV
  21. scale and rotation Template matching
  22. cmake find_package specify path
  23. Writing robust (color and size invariant) circle detection with OpenCV (based on Hough transform or other features)
  24. load image with openCV Mat c++
  25. OpenCV warpperspective
  26. OpenCV: Find all non-zero coordinates of a binary Mat image
  27. OpenCV SURF function is not implemented
  28. how to remove straight lines or non-curvical lines in a canny image
  29. Using custom camera in OpenCV (via GStreamer)
  30. Differences of using “const cv::Mat &”, “cv::Mat &”, “cv::Mat” or “const cv::Mat” as function parameters?

Leave a Comment