Track Pedestrians

asked 2013-06-27 10:42:06 -0600

UserOpenCV
402 ●6 ●12 ●22

updated 2016-08-21 13:31:13 -0600

6772 ●3 ●48 ●79 https://github.com/stu...

I am using OpenCV sample code “peopledetect.cpp” to detect and track pedestrians. The code uses HoG for feature extraction and SVM for classification. Please find the reference paper used here.

The camera is mounted on the wall at a height of 10 feet and 45 down. There is no restriction on the pedestrian movement within the frame. I want to track the detected pedestrians’ movement within the frame. The issue I am facing is pedestrians are detected only in the middle region of the frame as most of the features are not visible as soon as the pedestrian enters the frame region.

I want to track each person’s movement in the entire frame region. How to do it? Is tracking required?

Can anyone give any reference to blogs/codes?

edit retag flag offensive close merge delete

add a comment

4

answered 2013-06-27 21:39:46 -0600

Mathieu Barnachon

4678 ●18 ●53 http://www.math-barnac...

If your pedestrians are quite different from pedestrians used to train the SVM, you may have to train your own SVM with your data. To do so, record many sequences with your camera, manually extract bounding box around pedetrian in each part of your image (they are positif samples), extract bounding box around non pedestrian (they are negative samples). Compute HOG on your samples and train your SVM. OpenCV has all the classes to help you during this process.