GiGa.91's profile - activity

NIR Cam and OpenCV Hello to all. I want to ask for advice to you. I am looking for a cam compatible with opencv I would

Hello to all. I would like your help. I have two cams and I would like to calculate the matrices H and R. I have calculated the intrinsic parameters of both cams.

I do not know how to continue..Can i use openPNP? or whats?

You're right. You know how to help me? Can you give some advice on how to get a good result?

ok. My goal is to look a target with a cam. The target is this: https://www.dropbox.com/s/s64vekyb5g3...

I would like to calculate the x / y position of the hole. example: https://www.dropbox.com/s/d5vvt0d9gwd...

As you can see the second photo has the target slightly moved. How can I get a good result?

ps: It may happen that the images have different brightness, example: https://www.dropbox.com/s/ncl0wl07e1m...

Sorry for my bad English. What did you not understand? I try to explain this again

I explain: I do a series of photos to a target. If the photographs are the same, they have not fired. If I find a difference in the photographs then I suppose they fired. To find where they shot I searched for circumferences. When I have to find the next hole I do not use the original photograph anymore but the one where the first hole is. I wanted to find the difference between the two pictures to do this

I can use this form to know if the pictures are similar but after I have to extract the differences. Can i do it directly with adsdiff?

Hello to everyone, I wanted to ask you advice. My goal is to create an algorithm that succeeds with a good percentage, to see if two pictures are similar. I have a master photo and all the photos i want to compare with this to see if they are "the same". I wanted to divide the algorithm in 3 points.

1)Load photo to compare and adjust brightness, contrast, histogram 2)I adjust the perspective by calculating matrix h with the original photo 3)I make the difference between the master picture and this (absdiff)

My problem is: how do I get a similar picture to that master in brightness and contrast

My problem is just one step ""estimate first the geometric transformation between the IR and normal cameras" The two cams see the screen of a video projector. A cam see what is projected on the screen from the video projector. The second cam ( that works with ir) not see the projected image. They look the same way but they do not see the same thing. I could use the video projector as a reference but I do not get the accuracy

Hello to all, I'm here to ask for advice. I have two cams that resume the same thing. A cam has a filter that only passes light ir. The other cam is a normal cam that does not pass the light ir. I use this last cam (normal cam) to detect four balls (The four balls are projected onto a wall). These four balls are the vertices of a rectangle. When I find these four points I calculate the matrix H and apply findHomography() to fix the perspective. I would like to calculate this matrix H also for the IR cam but it cant see these 4 balls. How can I calculate matrix H for this new cam? I know the distance to which the two cams are placed Can anybody give me some advice?

Hello to everyone, I'm here to ask for advice to you. i'm noob in opencv. I wanted to make an algorithm that it must find this image (https://www.dropbox.com/s/o78v4c1pqdm...) and calculate the position of the balls in real time.

I wrote an algorithm that uses the threshold binary + findcountor function and it works. The problem is that it only works if there is enough light. I would like it to work under all conditions.

The questionfor you is: in your opinion, is it best to try to use a function that automatically adjusts the brightness and contrast or change algorithm and use for example "detect + SURF" or some other algorithm that I do not know?

The ultimate goal is to know the 4 points for to use "findHomography and warpPerspective"

thank you very much for helping. I solved by adding all the libraries ending with *d.lib in debug mode e *.lib in release mode

Ok but i run the program in debug mode. I took all the libraries to the linker and I added only: opencv_world320d.lib and opencv_xfeatures2d320d.lib. it's right ?

Now i compiled opencv 3.2 with cmake and visualstudio 2017. i use opencv 3.2 (opencv-build\install\x64\vc15)

Hi, I use opencv 3.2 and visual studio 2017. I wanted to try this example:

#include <iostream>
#include "opencv2/core.hpp"
#include "opencv2/features2d.hpp"
#include "opencv2/xfeatures2d.hpp"
#include "opencv2/highgui.hpp"

using namespace cv;
using namespace cv::xfeatures2d;


/** @function main */
int main()
{
    Mat img_1 = imread("a.jpg", IMREAD_GRAYSCALE);

    //-- Step 1: Detect the keypoints using SURF Detector
    int minHessian = 400;

    Ptr<SURF> detector = SURF::create(minHessian);

    std::vector<KeyPoint> keypoints_1, keypoints_2;

    detector->detect(img_1, keypoints_1);

    //-- Draw keypoints
    Mat img_keypoints_1;

    drawKeypoints(img_1, keypoints_1, img_keypoints_1, Scalar::all(-1), DrawMatchesFlags::DEFAULT);

    //-- Show detected (drawn) keypoints
    imshow("Keypoints 1", img_1);

    waitKey(0);

    return 0;
}

when I run the program, it gives me an error. Does anyone know how to help me? the error is:

Eccezione generata in corrispondenza di 0x000007FEE3CD6FC8 (ucrtbase.dll) in Test.exe: 0xC0000005: violazione di accesso durante la lettura del percorso 0x0000000243D22E48.. Si è verificata l'eccezione

I have solved. I've installed all Windows updates. I do not know how I got stuffed but I did :)

ok i write the id hardware: 1) USB Camera -> VID 0C45 PID 6340 2) USB2.0 HD UVC WebCam -> VID 04F2 PID B354

I have already tried both. The result is the same. Gray screen

I haven't antivirus installed. No, I do not think I have installed MPHC. Do I have to install it? i use https://github.com/opencv/opencv/rele...

i have 2 camera. A cam is inside the laptop. The second cam is a simple cam usb. I have tried them with AMCap and they work. they are 640x480

Hello to all. I'm noob whit opencv. I'm trying to use Windows 7, Opencv 3.2 and Visual Studio. I test example whit VideoCapture and .avi and it is ok. When i test VideoCapture whit cam usb it is not work. Can someone help me? the code is:

#include "opencv2/opencv.hpp"
#include "opencv2/core/core.hpp"
#include "opencv2/highgui/highgui.hpp"

using namespace cv;
int main(int, char**)
{
    VideoCapture cap(0); // open the default camera
    if (!cap.isOpened())  // check if we succeeded
        return -1;

    Mat edges;
    namedWindow("edges", 1);
    while(true)
    {
        Mat frame;
        cap >> frame; // get a new frame from camera
        waitKey(100);   
    }
    cap.release();
    return 0;
}

If I try this code the program opens the room but I see nothing (gray window)

***** VIDEOINPUT LIBRARY - 0.1995 - TFW07 *****

SETUP: Setting up device 0
SETUP: USB2.0 PC CAMERA
SETUP: Couldn't find preview pin using SmartTee
SETUP: Default Format is set to 640x480
SETUP: trying specified format RGB24 @ 640x480
SETUP: trying format RGB24 @ 640x480
SETUP: trying format RGB32 @ 640x480
SETUP: trying format RGB555 @ 640x480
SETUP: trying format RGB565 @ 640x480
SETUP: trying format YUY2 @ 640x480
SETUP: Capture callback set
SETUP: Device is setup and ready to capture.

Event: Code: 0x0d Params: 0, 0
Event: Code: 0x0e Params: 0, 0
Event: Code: 0x03 Params: -2147024891, 0