Corto's profile - activity

I resolve this, i use 150 positive image and 200 negative image and it work's pretty well.

ok, i take 500 photo of image, for the tool i use Haartraining_Stuff. I think is the same! No?

i think i do like this, how many image do you think i take? he must have the same size or don't care? and in the image there is only the signal?

The stop signal is hexagonal and the other are circle. With stop sign, turn left and turn right work good, they give me a little problem but work, only with roundabout i have problem. I think the error is in the images used for training the classifier. How i can get a few hundred image? With createsamples it's possibile?

Hi all, I have create a road signal classifier using four signal (Stop, turn left, turn right and roundabout), i create the .vec file using one image for every road signal (one for stop, one for left ecc.) with opencv_createsamples, and with the file i training the classifier. I use the .xml file in one app for detect and track the signal with android but i have a problem, the classifier do 14 (at last) stage and never reach 20, and when i try to detect a photo of one (i have take the photo around) of this the classifier don't detect it. The question is: Is it better create a classifier with one image (With createsamples) or do a lot of a photo object? why the classifier does not work with real photos? Thanks for help!

It's Haar cascade. I mean pause the classification, just for a min, change image. I trained the classificator and i create an android app and it use the .xml file and with JavaCameraView i see the image and classificate it. I wanna pause it when it classificate one of this.

Yes! Your answer it's ok!

Hi all, I have a question, i have build a signal road classificator for the test phase i must pause it for change image and create a confusion matrix. How work my classificator? When it sees a signal tells me what kind of signal is drow a rectangle around it and go to increase a counter. Now i must pause it for change image, i try whit Thread.pause but it's realy bad, can someone help me? Thanks.

oh sorry, i read you message again. Thanks for help!

Ok thanks for help! I have another question, with opencv v 2.4.10 i create a new file .xml with opencv_traincascade but when i run opencv_performance give me this error

OpenCV Error: Unspecified error (The node does not represent a user object (unknown type?)) in cvRead, file C:\builds\2_4_PackSlave-win32-vc12-shared\opencv\modules\core\src\persistence.cpp, line 4991

I use the command, opencv\build\x86\vc12\bin\opencv_performance -data stop.xml -info positivesoutput.txt, i think the -info file is the error, but i don't understand.

Good morning all. I create a classifier following this guide http://docs.opencv.org/2.4/doc/user_g... and i have the file .xml. How can i do the evaluation model of the classificator? In opencv 2.4.10 there is opencv_performance but i use opencv 3.0 and the file performance is not present. Someone can help me?

Thanks, i've increase all the negative and positive element,

opencv_traincascade -data classifier/ -vec positive.vec -bg Stop/negative.txt -numPos 1700 -numNeg 3035 -numStages 20 -h 24 -w 24

But at the stages 9 it stop with Required leaf false alarm rate achieved. Branch training terminated.

I've create a classifier using Haartraining_Stuff, i have to create a road signal detection, i create a file info, negative.txt, positive.txt and .vec file. Then i use command traincascade write like this:

C:\OpenCV\opencv\build\x86\vc11\bin\opencv_traincascade.exe -data classifier\ -vec "C:\OpenCV\sample.vec" -bg "C:\OpenCV\negativeNew.txt" -numStages 2 -minHitRate 0.01 -maxFalseAllarmRate 0.5 -numPos 2 -numNeg 250 -w 20 -h 20 -mode ALL -precalcvalBuffSize 256 -precalcdxBufSize 256

But when i run it, give me this:

C:\OpenCV>C:\OpenCV\opencv\build\x86\vc11\bin\opencv_traincascade.exe -data classifier\ -vec "C:\OpenCV\sample.vec" -bg "C:\OpenCV\negativeNew.txt" -numStages 2 -minHitRate 0.01 -maxFalseAllarmRate 0.5 -numPos 2 -numNeg 250 -w 20 -h 20 -mode ALL -precalcvalBuffSize 256 -precalcdxBufSize 256 PARAMETERS: cascadeDirName: classifier\ vecFileName: C:\OpenCV\sample.vec bgFileName: C:\OpenCV\negativeNew.txt numPos: 2 numNeg: 250 numStages: 2 precalcValBufSize[Mb] : 1024 precalcIdxBufSize[Mb] : 1024 acceptanceRatioBreakValue : -1 stageType: BOOST featureType: HAAR sampleWidth: 20 sampleHeight: 20 boostType: GAB minHitRate: 0.01 maxFalseAlarmRate: 0.5 weightTrimRate: 0.95 maxDepth: 1 maxWeakCount: 100 mode: ALL

===== TRAINING 0-stage ===== < BEGIN POS count : consumed 2 : 2 NEG count : acceptanceRatio 250 : 1 Precalculation time: 0.594 +----+---------+---------+

| N | HR | FA |

+----+---------+---------+

| 1| 1| 0|

+----+---------+---------+ END> Training until now has taken 0 days 0 hours 0 minutes 1 seconds.

===== TRAINING 1-stage ===== BEGIN POS count : consumed 2 : 2 NEG count : acceptanceRatio 250 : 0.0423155

Required leaf false alarm rate achieved. Branch training terminated.

I think the problem is the low positive image no?

There is a command for use distorsion or something like this for create more file positive without take photo around? Thanks for help.