detect a irregular shape with opencv/ c++

up vote
0
down vote

favorite

I want to recognize the shape/mark shown in picture 1 highlighted shape (green border)

The scanned object resembles a bridge.
Unfortunately, I don't know how to detect the particular shape.

Picture 2 shows the original RGB picture. 2.Original Image

I edit it with the edge detection "cv::Canny" and the contouring "cv::findContours" (3.Edge detection results).

From this point on I don't know what to do.

I use opencv 3.4.2 and libfreenect2 in c++.
I use the kinect v2 for the recording.

The code section calls the image (3.) and edits it using "findContours". However, only the outer rectangle is displayed. But I would like to display the whole form as in picture (1). Unfortunately I don't have any ideas how to do this.

I would be very happy about help. Feel free to send some code examples.
Thank you

vector< vector<Point> > contours;

   

vector<Vec4i> hierarchy;





src.copyTo( dst, detected_edges);

imshow( window_name, dst );

imwrite ("Canny.png", dst);



image=imread ("Canny.png");

Mat converted (image.rows, image.cols, CV_8UC1);

Mat dat (image.rows, image.cols, CV_8UC1, Scalar ::all(0));

cvtColor(image, converted, COLOR_BGR2GRAY,1);

dilate(converted, converted, Mat(), Point(-1.5,-1.5));

threshold (converted, converted,25, 255, THRESH_BINARY);

    //findContours (converted, contours, CV_RETR_LIST, CV_CHAIN_APPROX_NONE );

findContours (converted, contours,hierarchy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);

    // Mat drawing =Mat::zeros (converted.size(), CV_8UC3);

    for (int i=0; i<contours.size(); i++)

    {

    double a= contourArea (contours[i], false);

    if(a>largest_area)

    	{

    	largest_area=a;

    	largest_contour_index=i;

    bounding_rect=boundingRect (contours[i]);

    	}	

    }

Scalar color (255,255,255);

drawContours (dat, contours, largest_contour_index, color, CV_FILLED,8,hierarchy);

rectangle (image, bounding_rect , Scalar (0,255,0),1,8,0);

imshow("dat", image);

imshow ("largestContour", dat);

imwrite("largestContour.png", image);

imwrite("dat.png", dat);

edited Nov 11 at 10:37

asked Nov 10 at 16:47

Jule

Please, take a moment to proof-read your question and edit it to make it legible (e.g. fix the broken markup, fix your capitalization, use paragraphs, etc.) Furthermore, please provide a proper Minimal, Complete, and Verifiable example (e.g. in the current code sample, what is src_gray, detected_edges, lowThreshold, ratio, kernel_size... ) | Just out of curiosity, why is that code's indentation all over the place? Attention to detail and ability to be consistent are key for a good software engineer.
– Dan Mašek
Nov 10 at 23:12

add a comment |

up vote
0
down vote

favorite

I want to recognize the shape/mark shown in picture 1 highlighted shape (green border)

The scanned object resembles a bridge.
Unfortunately, I don't know how to detect the particular shape.

Picture 2 shows the original RGB picture. 2.Original Image

I edit it with the edge detection "cv::Canny" and the contouring "cv::findContours" (3.Edge detection results).

From this point on I don't know what to do.

I use opencv 3.4.2 and libfreenect2 in c++.
I use the kinect v2 for the recording.

I would be very happy about help. Feel free to send some code examples.
Thank you

vector< vector<Point> > contours;

   

vector<Vec4i> hierarchy;





src.copyTo( dst, detected_edges);

imshow( window_name, dst );

imwrite ("Canny.png", dst);



image=imread ("Canny.png");

Mat converted (image.rows, image.cols, CV_8UC1);

Mat dat (image.rows, image.cols, CV_8UC1, Scalar ::all(0));

cvtColor(image, converted, COLOR_BGR2GRAY,1);

dilate(converted, converted, Mat(), Point(-1.5,-1.5));

threshold (converted, converted,25, 255, THRESH_BINARY);

    //findContours (converted, contours, CV_RETR_LIST, CV_CHAIN_APPROX_NONE );

findContours (converted, contours,hierarchy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);

    // Mat drawing =Mat::zeros (converted.size(), CV_8UC3);

    for (int i=0; i<contours.size(); i++)

    {

    double a= contourArea (contours[i], false);

    if(a>largest_area)

    	{

    	largest_area=a;

    	largest_contour_index=i;

    bounding_rect=boundingRect (contours[i]);

    	}	

    }

Scalar color (255,255,255);

drawContours (dat, contours, largest_contour_index, color, CV_FILLED,8,hierarchy);

rectangle (image, bounding_rect , Scalar (0,255,0),1,8,0);

imshow("dat", image);

imshow ("largestContour", dat);

imwrite("largestContour.png", image);

imwrite("dat.png", dat);

edited Nov 11 at 10:37

asked Nov 10 at 16:47

Jule

Please, take a moment to proof-read your question and edit it to make it legible (e.g. fix the broken markup, fix your capitalization, use paragraphs, etc.) Furthermore, please provide a proper Minimal, Complete, and Verifiable example (e.g. in the current code sample, what is src_gray, detected_edges, lowThreshold, ratio, kernel_size... ) | Just out of curiosity, why is that code's indentation all over the place? Attention to detail and ability to be consistent are key for a good software engineer.
– Dan Mašek
Nov 10 at 23:12

add a comment |

up vote
0
down vote

favorite

I want to recognize the shape/mark shown in picture 1 highlighted shape (green border)

The scanned object resembles a bridge.
Unfortunately, I don't know how to detect the particular shape.

Picture 2 shows the original RGB picture. 2.Original Image

I edit it with the edge detection "cv::Canny" and the contouring "cv::findContours" (3.Edge detection results).

From this point on I don't know what to do.

I use opencv 3.4.2 and libfreenect2 in c++.
I use the kinect v2 for the recording.

I would be very happy about help. Feel free to send some code examples.
Thank you

vector< vector<Point> > contours;

   

vector<Vec4i> hierarchy;





src.copyTo( dst, detected_edges);

imshow( window_name, dst );

imwrite ("Canny.png", dst);



image=imread ("Canny.png");

Mat converted (image.rows, image.cols, CV_8UC1);

Mat dat (image.rows, image.cols, CV_8UC1, Scalar ::all(0));

cvtColor(image, converted, COLOR_BGR2GRAY,1);

dilate(converted, converted, Mat(), Point(-1.5,-1.5));

threshold (converted, converted,25, 255, THRESH_BINARY);

    //findContours (converted, contours, CV_RETR_LIST, CV_CHAIN_APPROX_NONE );

findContours (converted, contours,hierarchy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);

    // Mat drawing =Mat::zeros (converted.size(), CV_8UC3);

    for (int i=0; i<contours.size(); i++)

    {

    double a= contourArea (contours[i], false);

    if(a>largest_area)

    	{

    	largest_area=a;

    	largest_contour_index=i;

    bounding_rect=boundingRect (contours[i]);

    	}	

    }

Scalar color (255,255,255);

drawContours (dat, contours, largest_contour_index, color, CV_FILLED,8,hierarchy);

rectangle (image, bounding_rect , Scalar (0,255,0),1,8,0);

imshow("dat", image);

imshow ("largestContour", dat);

imwrite("largestContour.png", image);

imwrite("dat.png", dat);

edited Nov 11 at 10:37

asked Nov 10 at 16:47

Jule

I want to recognize the shape/mark shown in picture 1 highlighted shape (green border)

The scanned object resembles a bridge.
Unfortunately, I don't know how to detect the particular shape.

Picture 2 shows the original RGB picture. 2.Original Image

I edit it with the edge detection "cv::Canny" and the contouring "cv::findContours" (3.Edge detection results).

From this point on I don't know what to do.

I use opencv 3.4.2 and libfreenect2 in c++.
I use the kinect v2 for the recording.

I would be very happy about help. Feel free to send some code examples.
Thank you

vector< vector<Point> > contours;

   

vector<Vec4i> hierarchy;





src.copyTo( dst, detected_edges);

imshow( window_name, dst );

imwrite ("Canny.png", dst);



image=imread ("Canny.png");

Mat converted (image.rows, image.cols, CV_8UC1);

Mat dat (image.rows, image.cols, CV_8UC1, Scalar ::all(0));

cvtColor(image, converted, COLOR_BGR2GRAY,1);

dilate(converted, converted, Mat(), Point(-1.5,-1.5));

threshold (converted, converted,25, 255, THRESH_BINARY);

    //findContours (converted, contours, CV_RETR_LIST, CV_CHAIN_APPROX_NONE );

findContours (converted, contours,hierarchy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);

    // Mat drawing =Mat::zeros (converted.size(), CV_8UC3);

    for (int i=0; i<contours.size(); i++)

    {

    double a= contourArea (contours[i], false);

    if(a>largest_area)

    	{

    	largest_area=a;

    	largest_contour_index=i;

    bounding_rect=boundingRect (contours[i]);

    	}	

    }

Scalar color (255,255,255);

drawContours (dat, contours, largest_contour_index, color, CV_FILLED,8,hierarchy);

rectangle (image, bounding_rect , Scalar (0,255,0),1,8,0);

imshow("dat", image);

imshow ("largestContour", dat);

imwrite("largestContour.png", image);

imwrite("dat.png", dat);

vector< vector<Point> > contours;

   

vector<Vec4i> hierarchy;





src.copyTo( dst, detected_edges);

imshow( window_name, dst );

imwrite ("Canny.png", dst);



image=imread ("Canny.png");

Mat converted (image.rows, image.cols, CV_8UC1);

Mat dat (image.rows, image.cols, CV_8UC1, Scalar ::all(0));

cvtColor(image, converted, COLOR_BGR2GRAY,1);

dilate(converted, converted, Mat(), Point(-1.5,-1.5));

threshold (converted, converted,25, 255, THRESH_BINARY);

    //findContours (converted, contours, CV_RETR_LIST, CV_CHAIN_APPROX_NONE );

findContours (converted, contours,hierarchy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);

    // Mat drawing =Mat::zeros (converted.size(), CV_8UC3);

    for (int i=0; i<contours.size(); i++)

    {

    double a= contourArea (contours[i], false);

    if(a>largest_area)

    	{

    	largest_area=a;

    	largest_contour_index=i;

    bounding_rect=boundingRect (contours[i]);

    	}	

    }

Scalar color (255,255,255);

drawContours (dat, contours, largest_contour_index, color, CV_FILLED,8,hierarchy);

rectangle (image, bounding_rect , Scalar (0,255,0),1,8,0);

imshow("dat", image);

imshow ("largestContour", dat);

imwrite("largestContour.png", image);

imwrite("dat.png", dat);

vector< vector<Point> > contours;

   

vector<Vec4i> hierarchy;





src.copyTo( dst, detected_edges);

imshow( window_name, dst );

imwrite ("Canny.png", dst);



image=imread ("Canny.png");

Mat converted (image.rows, image.cols, CV_8UC1);

Mat dat (image.rows, image.cols, CV_8UC1, Scalar ::all(0));

cvtColor(image, converted, COLOR_BGR2GRAY,1);

dilate(converted, converted, Mat(), Point(-1.5,-1.5));

threshold (converted, converted,25, 255, THRESH_BINARY);

    //findContours (converted, contours, CV_RETR_LIST, CV_CHAIN_APPROX_NONE );

findContours (converted, contours,hierarchy, RETR_CCOMP, CHAIN_APPROX_SIMPLE);

    // Mat drawing =Mat::zeros (converted.size(), CV_8UC3);

    for (int i=0; i<contours.size(); i++)

    {

    double a= contourArea (contours[i], false);

    if(a>largest_area)

    	{

    	largest_area=a;

    	largest_contour_index=i;

    bounding_rect=boundingRect (contours[i]);

    	}	

    }

Scalar color (255,255,255);

drawContours (dat, contours, largest_contour_index, color, CV_FILLED,8,hierarchy);

rectangle (image, bounding_rect , Scalar (0,255,0),1,8,0);

imshow("dat", image);

imshow ("largestContour", dat);

imwrite("largestContour.png", image);

imwrite("dat.png", dat);

c++ opencv object-detection shapes kinect-v2

edited Nov 11 at 10:37

asked Nov 10 at 16:47

Jule

edited Nov 11 at 10:37

asked Nov 10 at 16:47

Jule

edited Nov 11 at 10:37

asked Nov 10 at 16:47

Jule

asked Nov 10 at 16:47

Jule

asked Nov 10 at 16:47

Jule

Please, take a moment to proof-read your question and edit it to make it legible (e.g. fix the broken markup, fix your capitalization, use paragraphs, etc.) Furthermore, please provide a proper Minimal, Complete, and Verifiable example (e.g. in the current code sample, what is src_gray, detected_edges, lowThreshold, ratio, kernel_size... ) | Just out of curiosity, why is that code's indentation all over the place? Attention to detail and ability to be consistent are key for a good software engineer.
– Dan Mašek
Nov 10 at 23:12

add a comment |

Please, take a moment to proof-read your question and edit it to make it legible (e.g. fix the broken markup, fix your capitalization, use paragraphs, etc.) Furthermore, please provide a proper Minimal, Complete, and Verifiable example (e.g. in the current code sample, what is src_gray, detected_edges, lowThreshold, ratio, kernel_size... ) | Just out of curiosity, why is that code's indentation all over the place? Attention to detail and ability to be consistent are key for a good software engineer.
– Dan Mašek
Nov 10 at 23:12

Please, take a moment to proof-read your question and edit it to make it legible (e.g. fix the broken markup, fix your capitalization, use paragraphs, etc.) Furthermore, please provide a proper Minimal, Complete, and Verifiable example (e.g. in the current code sample, what is src_gray, detected_edges, lowThreshold, ratio, kernel_size... ) | Just out of curiosity, why is that code's indentation all over the place? Attention to detail and ability to be consistent are key for a good software engineer.
– Dan Mašek
Nov 10 at 23:12

add a comment |

active

oldest

votes

Your Answer

StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});

}
});

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53241165%2fdetect-a-irregular-shape-with-opencv-c%23new-answer', 'question_page');
}
);

Post as a guest

Name

Required, but never shown

active

oldest

votes

draft saved

draft discarded

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Name

Required, but never shown

Name

Required, but never shown

This page is only for reference, If you need detailed information, please check here

搜尋此網誌

Nrthugu