How to Combine Motion and Appearence descriptor

asked 2013-11-05 07:58:45 -0600

Madhujith
16 ●3

I'm going to detect objects using a method proposed by Navneet Dalal, Bill Triggs, and Cordelia Schmid in 2006 (Human Detection Using Oriented Histograms of Flow and Appearance)

In that case they first calculate appearance descriptor using HOG algorithm and motion descriptor using Optical flow. Then they combined these two descriptors to get the final descriptor as I understand. But I couldn't find how they combined that.

So my question is how to combine appearance and motion descriptor to get the final descriptor. (I'm going to use leaner SVM for training)

answered 2013-11-05 10:01:52 -0600

r.a.
171 ●1 ●2 ●11

Hi,

This is the common scheme for such a case:

1.extract HOG feature; Extract Optical flow feature.

2.Normalize HOG vector;Normalize OF vector.

3.Concatenate HOG and OF vectors.

4.Normalize again the concatenated vector.

Some things to remember:

1.Try which is the best normalization method in your case L2 L1 ...

2.Try different vector length for each feature.

3.Try several Image flow techniques.

Good luck

edit flag offensive delete link

Comments

Thank you very much!. can I use hog.compute() method to calculate OF descriptor?

Madhujith ( 2013-11-05 11:58:34 -0600 )edit

Hi, 1.Yes you can.(I didn't do so but You should be able to) 2.It is probably not the best OF Feature,But it may be a good point to start from. 3.Check type (int ,float...) 4.Do Hog.compute for Mx My seperately. 5.Try different Block sizes , smaller than your HOG.

r.a. ( 2013-11-10 02:02:13 -0600 )edit

add a comment

How to Combine Motion and Appearence descriptor

1 answer

Comments

Links

Question Tools

Stats

Related questions

How to Combine Motion and Appearence descriptor edit

1 answer

Comments

Links

Question Tools

Stats

Related questions

How to Combine Motion and Appearence descriptor