Tracking and Train SVM detector with HOG features online

Support vector machine with Histogram of oriented gradient trained near online, and tracker. 

support vector machine with HOG tracker

Build the SVM detector based on HOG feature is relatively simple process. When is not necessary to be robust and detector is focused only on one object. You can build this by combine several OPENCV available tutorials and source codes distributed in Opencv samples. There is maybe one think what is not natural and cannot be taken from example and tutorials. Train set in online training is only 20 positive images warp over positive windows and 30 random negative samples.

What do you think  ? 

Tutorial on SVM with HOG, tracker soon

This is just and example. Tutorial will be available later.. Code is little bit complex.


  1. Hey,
    Can you share the code , I'm trying to use SVM with HOG to track and recognize people in a surveillance system. The method you followed could be a great head start for my project!

  2. Another advantage we can get from the way that it will be you and your family will's identity helping your companion all through the online canine preparing. dog training prices

  3. I'll audit this blog as An and it exhibits how much effort has been put into this.


Post a Comment