Ask Your Question
8

What is the average training time needed for LBP object detector to reach a next stage?

asked 2013-03-21 05:29:20 -0500

updated 2013-04-04 04:30:48 -0500

I see many topics appearing about cascade training for object detection. However, what I do not seem to find are discussions about how fluently training should actually be.

I am training a LBP object detector using the boosted cascade of weak classifiers, done by using the train_cascade algorithm. The detector is used for detecting cars in aerial imagery.

I have used 200 positive examples and 1000 negative examples. I asked to train 35 stages, which the trainer is actually doing, but when I check how fast the algorithm is processing the negative samples, I see weird results.

At first stages processing goes very fast. At stage 19 however, processing goes about a sample each 5 - 10 minutes. Just wondering, since LBP has been reported as beïng trainable in matter of a day, where HAAR needs a week, how fast training goes with others.

Also, I have the idea that assigning more memory to the process, by increasing the precalcValBufSize and precalcIdxBufSize parameter to 2048 MB each, doesn't seem to influence the training more, than actually assigning 500 MB to each. Any suggestions there?


UPDATE

I have done multiple tests on this, still not being able to define a relation between LBP training time and the algorithm itself. Still open for suggestions!

edit retag flag offensive close merge delete

Comments

1

@sammy or @Vladislav Vinogradov : could you guys maybe point me in the direction of someone who is doing implementation work containing LBP feature training? I am asking you guys because you are experienced Q&A forum users. Looking at the voting, more people would like to know about this it seems :)

StevenPuttemans gravatar imageStevenPuttemans ( 2013-03-22 05:38:12 -0500 )edit

1 answer

Sort by » oldest newest most voted
8

answered 2013-06-04 02:47:23 -0500

Ok after some more months of researching, I think I can formulate an answer to my problem myself. Basically the reason why the negative processing goes slower with each stage is the following.

Simply said, it is something like this:

For each stage the training algorithm has to look for negatives, using the negative set that was passed, that are discriminant enough to still make a difference with all previous trained negative samples. In the beginning this is easy because no negatives have been trained yet. However, the further we go, the more negatives already get classified as negative by the training algorithm and thus the more effort the algorithm must do to find negatives that actually still get wrongly classified throughout the stages.

This also means that you should actually think about your negative training set. If you have 10 images that look exactly the same, then it is better to only supply it once to the algorithm, since the other negatives won't help improve your classifier anymore.

I do think this is a part of cascade classifiers that hasn't been researched enough, trying to define relations between the actual negatives and the training process. Many times people use the words 'the set has to be diverse enough' but thats kind of a blurry description nevertheless.

edit flag offensive delete link more

Comments

@StevenS, I need to train LBP classifier for vehicle detection from video streams and answer to the following question would be of great help for me.

1) How much time does it take to train a classifier using LBP for detecting cars?

2) What was the ratio of positive and negative images?

3) Which dataset did you use to train your LBP classifier?

4) How long does it take to train the classifier?

5) Were you able to make a comparison of HaarCascade Classifier and LBP?

6) Is it possible to share the classifier?

Tariq gravatar imageTariq ( 2014-06-02 03:53:37 -0500 )edit

@tesmai4 If you want maximal response then do make a new question referencing this. Now I am the only one seeing your remark.

StevenPuttemans gravatar imageStevenPuttemans ( 2014-06-02 04:00:22 -0500 )edit

This is the link for the question [http://answers.opencv.org/question/34476/lbp-for-vehicle-detection/]. Hope to get answer now.

Tariq gravatar imageTariq ( 2014-06-02 06:12:49 -0500 )edit
Login/Signup to Answer

Question Tools

3 followers

Stats

Asked: 2013-03-21 05:29:20 -0500

Seen: 2,899 times

Last updated: Jun 04 '13