pradeep_kb's profile - activity

Can anyone help me on this please..

class ImageProcessing       //user defined class 
{   
Public:
    void checkzone(CvTracks::const_iterator ot, double position1);
       .
       .
       .
     };

When I compile, compiler is throwing

1. error: 'CvTracks' has not been declared.
2. error: expected ',' or '...' before 'ot'

But when I declare this function outside the class, compiler is not throwing error.

Please help me to resolve this error.

@donald83180 How did you calculate the angle rotation?

Hello,

My program has to detect the rectangular object present in the water and measure its angle of orientation with respect to X-Axis. The idea behind this is, i have to move my vehicle in the direction of the object orientation, the object will be rectangular in shape. So if I get the angle of orientation of the object then I can send that angle to my vehicle and then rotate the vehicle with that angle and then move on.

@Vit @StevenPuttemans @sturkmen, I have done profiling for the program on raspberry pi 2 with raspbian OS. here are the details. Need your help to analyse it in depth.

This profiling i have done in my PC not on raspberry pi. On raspberry pi compiler is not generating gmon.out I am working on that. I have followed theset steps. But not working for raspbian OS.

@Vit @StevenPuttemans @sturkmen, I have done profiling for my program using gprof tool here is the details. I am new to this, not able to analyze properly. Thanks for the help.

@Vit, From the above result that I have posted I found morphology process is taking more time. I think background subtraction process will take less time then morphology process, What do you say? I am new to Opencv, this program was written by someone else. I have to optimize it now.

how about this

@Vit @StevenPuttemans I have gone through the profiling, I got to know we need a tool to check the which function is taking much time. But there are lot of tools available. Which is the best tool to use for Opencv, Raspberry pi, C++?

@Vit, this is manual profiling that I have done. All the results are in milliseconds.

Total time: 3.99949e+07ms  fps: 2.5e-05
END OF VIDEO
Times: 
1-Moving difference, grayscale conversion-------------->1.18404e+06
2-Image binarization----------------------------------->102496
3-Dilate and erode (Morphology)------------------------>1.35859e+07
4-Blob process(FilterByArea,UpdateTracks,RenderTracks)->983343
5-Car and person detection----------------------------->99999.6
6-Getting frames from video and frames skipped--------->1.63229e+06
(Adding 1 to 6) Total->1.75881e+07

@sturkmen @Vit Does Background subtraction helps to speedup the program?

@Vit, I did not do profiling, I don't know what it is. Could you please help me to know that

I have written program for detecting cars in the video. If two cars found simultaneously my program is counting for only one or some times it do not count. is there any way to solve this problem? Does background subtraction help to solve this problem?

@sturkmen I have even done re-sizing of image to 50% 75% and 25%.. did all possible thinngs to get good result.

I am detecting the cars present in the video and counting no. of cars entering in certain region. I am not processing every frame. I am have tested the program with 4, 6 & 8 frame skips. But still it is taking more time and not processing in required time. The video that have is of 5 hours and when I run the program it is taking 6.5 to 7 hours for skip 8 but it is not giving accurate results. The number of cars count is reducing.

@sturkmen I am detecting the cars present in the video and counting no. of cars entering in certain region. I am not processing every frame. I am have tested the program with 4, 6 & 8 frame skips. But still it is taking more time and not processing in required time. The video that have is of 5 hours and when I run the program it is taking 6.5 to 7 hours for skip 8 but it is not giving accurate results. The number of cars count is reducing.

I have written a program in which the program has to detect objects from the video. the actual duration of video is 5 hours but it is taking nearly 10 hours on raspberry pi 2. It is taking very long time, doesn't work in real time. Is there any technique to utilize all the 4 cores of raspberry pi to run the program? Are there any optimization techniques available for opencv to make my program run faster?

@pkblab , I am very new to opencv.. I didn't think about it still. Please advice me your best.

Hello,

I want to know the co-ordinates or angle with respect to y axis of the object detected. In my case we are detecting rectangular object placed in side the swimming pool or water. I should get the any of the object and I should make my robot to align and move in that direction. Please advice.

> #include <iostream>
> #include <opencv/cv.h>
> #include <opencv/highgui.h>
> 
> using namespace std;
> 
> char key;
> 
> int main() {
>   cvNamedWindow("Camera_Output",1);    
> //create a window     CvCapture* capture
> =cvCaptureFromCAM(0);                   // Capture using any camera, we can
> aslo use 0 as a parameter if we are
> using single camera.  if(capture ==
> NULL)         {           printf("cannot open
> camera#n");           return -1;      }
>   while(1){                            
> //creating any infinite loop for live
> streaming
>           IplImage* frame = cvQueryFrame(capture);                
> //capture image frames from camera
>       cvShowImage("Camera_Output",frame); 
> //show image frames on created window
>       key = cvWaitKey(10);                
> //Capture keyboard storke
>       if(char(key) == 27){
>                   break;      }   }       cvReleaseCapture(&capture);          
> //Release capture Image
>   cvDestroyWindow("camera_Output");    
> //Destroy Window
> 
>   return 0; }

please advice

I got the answer for my issue. The below changes are required specially for raspberry pi 2(armhf) which avoids the program to run infinite.

go to /home/pi/cvblob/cvBlob

In cvLabel.h file

const char movesE ... const char movesI ...

to

const signed char movesE ... const signed char movesI ...

and in cvBlob/cvcontour.cpp , line 84:

change

const char cvChainCodeMoves[8][2] = { { 0, -1},

to

const signed char cvChainCodeMoves[8][2] = { { 0, -1},

Hello Everyone,

I have written a program to count no of cars from the captured video. I have installed opencv and cvblob, raspbian wheezy OS on raspberry pi 2. The problem I am facing is "During run time the program hangs at cvLabel after certain no of iterations.

IplImage *labelImg =cvCreateImage(cvGetSize(greyImage), IPL_DEPTH_LABEL, 1);
unsigned int result = cvLabel(greyImage, labelImg,blobs);

But when I run the same program on Virtual Machine in my laptop it will run completely. What might be the reason for this..? Please advice

Thanks.

Hello Everyone,

I have written program for Car tracking. I am sending video Car.mp4 during run time.

g++ -I/usr/local/include CarMotion-HSV.cpp $(pkg-config opencv cvblob --cflags --libs)

./a.out -f Car.mp4

The problem here is it will open a window and remain stagnant showing only picture of video, it is not playing video in the window. However when I play it with omxplayer it will play (omxplayer -o hdmi Car.mp4). Same code I have tried in Ubuntu Mate in VM, its working. But not working in Raspberry pi 2, Raspbian Jesse OS.

Please help me out to know how to run video during run time.

Thanks in advance

@theodore Thank you

I am installing Opencv, CvBlob on Raspbian OS. there were list of build instruction which i was following and found this line.

Thanks in advance

I am getting error Cannot open output file a.out: Permission denied when i tried to run the sample program which are present in opencv-2.4.11 directory. the path of the directory is /home/pi/opencv-2.4.11/samples/.. the properties of the cpp file are -rw-r--r-- 1 root root starter_video.cpp.

i even tried to change the permission for directory /home/pi/opencv-2.4.11/samples/.. it didn't work. it throw "Changing permissions of 'samples' : Operation not permitted".

Please advice

@berak Thank you.. I compiled with linking the libraries.. errors got resolved.

@berak Could you please explain in detail. I am new to OpenCV