Loam's profile - activity

I have trained LBP classifier for searching cars top view. And i do not know how to exlude redetection at the same places during searching.

I saved a resulting picture, as you see one car is found twice:

I use this function:

cascade.detectMultiScale( smallImg, cars,
    1.1, 3, 0
    //|CV_HAAR_FIND_BIGGEST_OBJECT
    //|CV_HAAR_DO_ROUGH_SEARCH
    |CV_HAAR_SCALE_IMAGE
    ,
    Size(30, 30),
    Size(700,700)
    );

@StevenPuttemans Thank you very much, i'l try what u said and will response later

1. You mean to rotate images in programm which uses classifier?
2. I have to create 2 classifiers for an up facing car and a down facing car or what?
3. And last. I still can't understand: i have to cut cars neatly rotating them to one direction or just use opencv_objdetect for example, which means i will have a file containing all images and ROI (in ROI will be a car with it's own orientation and pieces of ground).

Hi!

I'm working on creating LBP or HAAR classifier for detecting cars top view. I have created LBP classifier and when i checked it's work, it finds only vertically oriented cars and even not all of them:

1) Could this be due to the fact that in all samples I used images with a clear cut vertically disposed cars? I mean i rotated them myself vertically and cuted using Adobe Photoshop. For example:

And does this mean that i have to cut cars from images like this (with parts of ground):

OR it's just because i used too few pictures (150 positives -> opencv_createsamples -> 600 samples)?

OR because of both reasons?

2) opencv_createsamples.exe applies to much distortions that i do not need, especially Z angle. With wich parameters should i run this programm to not to make Z distortion? (probably: -maxzangle 0 (?))

Pls give me some advises ;)

P.S. sorry for my bad English

cvPutText(

  CvArr*        img, // Image

  const char*   text, // Text

  CvPoint       origin, // Left bottom corner from which text is drawed

  const CvFont* font, // font

  CvScalar      color // Color

);

for example:

cvPutText(image, "Hello World!", cvPoint(50, 50), &font, CV_RGB(0,255,255));

@StevenPuttemans Here is my samples.vec, which can be opened with createsamples.exe -vec samples.vec -w 40 -h 90 -show

@StevenPuttemans I'm working under Windows 8.1, and it actually really have took that long for 1 stage . I started this process yesterday at 15:00, more than 24 hours left, and it's still training second stage (stage 1) (almost finished).

Very intriguing!

$ traincascade.exe -data classifier1/ -vec samples.vec -bg negatives.txt -numPos 500 -numNeg 1134 -numStages 10 -precalcValBufSize 1024 -precalcIdxBufSize 1024 -featureType HAAR -w 40 -h 90 -minHitRate 0.995 -maxFalseAlarmRate 0.5 -mode ALL
PARAMETERS:
cascadeDirName: classifier1/
vecFileName: samples.vec
bgFileName: negatives.txt
numPos: 500
numNeg: 1134
numStages: 10
precalcValBufSize[Mb] : 1024
precalcIdxBufSize[Mb] : 1024
stageType: BOOST
featureType: HAAR
sampleWidth: 40
sampleHeight: 90
boostType: GAB
minHitRate: 0.995
maxFalseAlarmRate: 0.5
weightTrimRate: 0.95
maxDepth: 1
maxWeakCount: 100
mode: ALL

===== TRAINING 0-stage =====
<BEGIN
POS count : consumed   500 : 500
NEG count : acceptanceRatio    1134 : 1
Precalculation time: 37.424
+----+---------+---------+
|  N |    HR   |    FA   |
+----+---------+---------+
|   1|        1|        1|
+----+---------+---------+
|   2|        1|        1|
+----+---------+---------+
|   3|    0.996| 0.622575|
+----+---------+---------+
|   4|    0.996| 0.622575|
+----+---------+---------+
|   5|    0.996| 0.623457|
+----+---------+---------+
|   6|    0.998|  0.55291|
+----+---------+---------+
|   7|    0.998| 0.568783|
+----+---------+---------+
|   8|    0.996| 0.539683|
+----+---------+---------+
|   9|    0.996| 0.428571|
+----+---------+---------+
END>
Training until now has taken 0 days **14 hours 15 minutes 46 seconds**.

===== TRAINING 1-stage =====
<BEGIN
POS count : consumed   500 : 502
NEG count : acceptanceRatio    1134 : 0.584838
Precalculation time: 38.191
+----+---------+---------+
|  N |    HR   |    FA   |
+----+---------+---------+
|   1|        1|        1|
+----+---------+---------+
|   2|        1|        1|
+----+---------+---------+

14 hours just for 1 stage, is it normal?

This is what my task manager shows. It seems to me all cores are working, but only 20% of my CPU is under load:

Is it possible to make it work faster?

@StevenPuttemans I found it here: link text So, what do you advise me to use with this purpose?

@StevenPuttemans I used mergevec.exe to combine them with cmd options:

mergevec.exe "C:\OPENCV\bin\Debug\samples.txt" samples.vec

When i try to start classifier training after about 1 minute i got this:

opencv_traincascaded.exe -data classifier -vec samples.vec -bg negatives.txt -numStages 20 -minHitRate 0.999 -maxFalseAlarmRate 0.5 -numPos 600 -numNeg 900 -w 40 -h 90 -mode ALL -precalcValBufSize 1024 -precalcIdxBufSize 1024

This generates the following output

PARAMETERS:
cascadeDirName: classifier
vecFileName: samples.vec
bgFileName: negatives.txt
numPos: 600
numNeg: 900
numStages: 20
precalcValBufSize[Mb] : 1024
precalcIdxBufSize[Mb] : 1024
stageType: BOOST
featureType: HAAR
sampleWidth: 40
sampleHeight: 90
boostType: GAB
minHitRate: 0.999
maxFalseAlarmRate: 0.5
weightTrimRate: 0.95
maxDepth: 1
maxWeakCount: 100
mode: ALL

===== TRAINING 0-stage =====

<BEGIN
POS count : consumed   600 : 600
NEG count : acceptanceRatio    900 : 1
Precalculation time: 90.112
+----+---------+---------+
|  N |    HR   |    FA   |
+----+---------+---------+

OpenCV Error:

Assertion failed (dims <= 2 && data && (unsigned)i0 < (unsigned)size.p[0] && (unsigned)(i1 * DataType<_Tp>::channels) < (unsigned)(size.p[1] * channels()) && ((((sizeof(size_t)<<28)|0x8442211) >> ((DataType<_Tp>::depth) & ((1<< 3) - 1))*4) & 15) == elemSize1()) in cv::Mat::at, file C:\OPENCV\opencv-master\modules\core\include\opencv2/core/mat.inl.hpp, line 845

Interesting thing is that if I use this option:

-featureType LBP

then training works fine. I am trying to create a classifier for detecting cars top view. This training I started just for example, and if it will begun to work I will find more positive images to create good classifier. I used 73 positives and with help of createsamples.exe I created 600 samples (73 vec files) and merged them to create one samples.vec (4 Mb). All negative images I used are greyscale, I took them from base of negative images wich was used to create face recognizing classifier and sorted them out deleting any images with cars.

P. S. Sorry for my bad english :)