0
$\begingroup$

I am detecting the object from the live camera through feature detection with svm , and it read every frame from camera while predicting which affect its speed , i just want that it should select the frame which contain the object and ignore other frames which have no object like empty street or standing car's , it should only detect the moving object

For example , If the object came into camera in 6th frame , it contain into the camera till many frames until it goes out from camera's range , so it should not recount the same object and ignore that frames.

Explanation :

I am detecting the vehicle from video , i want to ignore the empty frames , but how to ignore them ? i only want to check the frames which contain object like vehicle , but if the vehicle is passing from video it take approximately lets assume 5 sec , than it mean same object take 10 frames , so the program count it as 10 vehicles , one from each frame , i want to count it as 1 , because its the one (SAME) vehicle which use 10 frames

My video is already in Background subtraction form , i used SURF/BOW with SVM

I explore two techniques :

1- Entropy ( Frame subtraction ) 2- Keyframe extraction

$\endgroup$
  • $\begingroup$ Can i use key frame extraction technique on it ? $\endgroup$ – ARG Aug 31 '13 at 9:43
0
$\begingroup$

I'm seeing two issues here:

  1. Frames with no activity: You can check the gradient between successive frames and only do object detection when the gradient information passes a certain threshold.

  2. Counting the same object: The vehicle location information can be useful for this task. If the gradient change occurs in the location of a detected object in the previous frame then it is the same vehicle. If necessary, you can also use object color and object size parameters to account for varying speeds.

$\endgroup$
  • $\begingroup$ for frame with no activity : you want to say that , if i have black background and human or vehicle is in white pixels so i only go for white pixels , if they are in a specific amount otherwise ignore the frame ? am i understand right ? $\endgroup$ – ARG Aug 31 '13 at 9:09
  • $\begingroup$ What about the use of entrophy ? $\endgroup$ – ARG Aug 31 '13 at 20:35
  • $\begingroup$ The Graident is the directional derivative with respect to time. You can simply try subtracting two successive frames to detect if a significant activity exists in the new frame. $\endgroup$ – Hasan Sep 1 '13 at 5:23
0
$\begingroup$

You should use "objectness" measures or object proposals. There are many works on that such as [1] and [2].

$\endgroup$
0
$\begingroup$
  1. Do background subtraction to retain only objects in motion.
  2. Threshold it to convert into binary image.
  3. Do morphological operations to separate them into blobs.
  4. Implement blob tracking to to make sure it's the new subject or the subject that already exists.If new subject, increment count by 2.
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.