Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

Detectiong of multi-person using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

I am interesting of line #327

Line #327 and next processing gets us only single person's pose. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes, Sergey Netyagin

click to hide/show revision 2
None

updated 2018-04-09 09:58:25 -0500

berak gravatar image

Detectiong of multi-person Multi-person poses detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

I am interesting of line #327

Line #327 and next processing gets us only single person's pose. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes, Sergey Netyagin

click to hide/show revision 3
None

updated 2018-04-09 09:58:31 -0500

berak gravatar image

Multi-person poses detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

Line #327 and next processing gets us only single person's pose. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes, Sergey Netyagin

Multi-person poses detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

Line #327 and next processing gets us only single person's pose. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes, Sergey Netyagin

Multi-person poses detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

314 private void RecognizePose( Mat image, Mat output_image, List<point> points, float[] data ) {

315

316 for( int i = 0; i < BODY_PARTS_MPI.Count; i++ ) {

317

318 output_image.get( i, 0, data );

319

320 Mat heat_map = new Mat ( 1, data.Length, CvType.CV_32FC1 );

321

322 heat_map.put( 0, 0, data );

323

324 //Originally, we try to find all the local maximums. To simplify a sample

325 //we just find a global one. However only a single pose at the same time

326 //could be detected this way.

327 Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );

328

329 heat_map.Dispose();

330

331 double x = (image.cols() * (result.maxLoc.x % matrix_output_columns)) / matrix_output_columns;

332 double y = (image.rows() * (result.maxLoc.x / matrix_output_rows)) / matrix_output_rows;

333

334 if( result.maxVal > 0.1d ) points.Add( new Point( x, y ) );

335 else points.Add( null );

336 }

337 }

Line #327 and next processing gets us only single person's pose. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes, Sergey Netyagin

Multi-person poses detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

314

//314 private void RecognizePose( Mat image, Mat output_image, List<point> points, float[] data ) {

315

316 { //315 //316 for( int i = 0; i < BODY_PARTS_MPI.Count; i++ ) {

317

318 { //317 //318 output_image.get( i, 0, data );

319

320 ); //319 //320 Mat heat_map = new Mat ( 1, data.Length, CvType.CV_32FC1 );

321

322 ); //321 //322 heat_map.put( 0, 0, data );

323

324 ); //323
//324
//Originally, we try to find all the local maximums. To simplify a sample

325 sample //325 //we just find a global one. However only a single pose at the same time

326 time //326 //could be detected this way.

327 way. //327 Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );

328

329 heat_map.Dispose();

330

331 ); //328 //329 heat_map.Dispose(); //330 //331 double x = (image.cols() * (result.maxLoc.x % matrix_output_columns)) / matrix_output_columns;

332 matrix_output_columns; //332 double y = (image.rows() * (result.maxLoc.x / matrix_output_rows)) / matrix_output_rows;

333

334 matrix_output_rows; //333 //334 if( result.maxVal > 0.1d ) points.Add( new Point( x, y ) );

335 ); //335 else points.Add( null );

336 ); //336 } //337 }

337 }

Line #327 and next processing gets us only single person's pose. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes, Sergey Netyagin

click to hide/show revision 7
None

updated 2018-04-09 11:53:40 -0500

berak gravatar image

Multi-person poses detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

//314        private void RecognizePose( Mat image, Mat output_image, List<point> List<Point> points, float[] data ) {
//315
//316            for( int i = 0; i < BODY_PARTS_MPI.Count; i++ ) {
//317
//318                output_image.get( i, 0, data );
//319
//320                Mat heat_map = new Mat ( 1, data.Length, CvType.CV_32FC1 );
//321
//322                heat_map.put( 0, 0, data );
//323 
//324 //Originally, we try to find all the local maximums. To simplify a sample //325 //we just find a global one. However only a single pose at the same time //326 //could be detected this way. //327 Core.MinMaxLocResult result = Core.minMaxLoc( heat_map ); //328 //329 heat_map.Dispose(); //330 //331 double x = (image.cols() * (result.maxLoc.x % matrix_output_columns)) / matrix_output_columns; //332 double y = (image.rows() * (result.maxLoc.x / matrix_output_rows)) / matrix_output_rows; //333 //334 if( result.maxVal > 0.1d ) points.Add( new Point( x, y ) ); //335 else points.Add( null ); //336 } //337 }

}

Line #327 and next processing gets us only single person's pose. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes, Sergey Netyagin

Multi-person poses detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

//314        

CODE FRAGMENT:

private void RecognizePose( Mat image, Mat output_image, List<Point> List<point> points, float[] data ) { //315 //316 {

for( int i = 0; i < BODY_PARTS_MPI.Count; i++ ) {
//317
//318                 output_image.get( i, 0, data );
//319
//320                 Mat heat_map = new Mat ( 1, data.Length, CvType.CV_32FC1 );
//321
//322                 heat_map.put( 0, 0, data );
//323    
//324                 //Originally, we try to find all the local maximums. To simplify a sample
//325                //we just find a global one. However only a single pose at the same time
//326                //could be detected this way.
//327                Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );
//328
//329                 heat_map.Dispose();
//330
//331                 double x = (

        (image.cols() *  (result.maxLoc.x % matrix_output_columns)) / matrix_output_columns;
//332            
        matrix_output_columns
    );

    double y = (

        (image.rows() *  (result.maxLoc.x / matrix_output_rows)) / matrix_output_rows;
//333
//334            
        matrix_output_rows
    );

    if( result.maxVal > 0.1d ) points.Add( new Point( x, y ) );
//335                else points.Add( null );
//336            }
//337        }

}

Line #327 "Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );" and next processing gets us only single person's pose. pose. And comment for this line says the same. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes, Sergey Netyagin

Multi-person poses detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

CODE FRAGMENT:

private void RecognizePose( Mat image, Mat output_image, List<point> points, float[] data ) {

for( int i = 0; i < BODY_PARTS_MPI.Count; i++ ) {

    output_image.get( i, 0, data );

    Mat heat_map = new Mat ( 1, data.Length, CvType.CV_32FC1 );

    heat_map.put( 0, 0, data );

    //Originally, we try to find all the local maximums. To simplify a sample
    //we just find a global one. However only a single pose at the same time
    //could be detected this way.
    Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );

    heat_map.Dispose();

    double x = (

        (image.cols() * 
        (result.maxLoc.x % matrix_output_columns)) / 
        matrix_output_columns
    );

    double y = (

        (image.rows() * 
        (result.maxLoc.x / matrix_output_rows)) / 
        matrix_output_rows
    );

    if( result.maxVal > 0.1d ) points.Add( new Point( x, y ) );
    else points.Add( null );
}

}

Line "Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );" and next processing gets us only single person's pose. And comment for this line says the same. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes, wishes,

Sergey Netyagin

Multi-person poses detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

CODE FRAGMENT:

private void RecognizePose( Mat image, Mat output_image, List<point> points, float[] data ) {

for( int i = 0; i < BODY_PARTS_MPI.Count; i++ ) {

    output_image.get( i, 0, data );

    Mat heat_map = new Mat ( 1, data.Length, CvType.CV_32FC1 );

    heat_map.put( 0, 0, data );

    //Originally, we try to find all the local maximums. To simplify a sample
    //we just find a global one. However only a single pose at the same time
    //could be detected this way.
    Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );

    heat_map.Dispose();

    double x = (

        (image.cols() * 
        (result.maxLoc.x % matrix_output_columns)) / 
        matrix_output_columns
    );

    double y = (

        (image.rows() * 
        (result.maxLoc.x / matrix_output_rows)) / 
        matrix_output_rows
    );

    if( result.maxVal > 0.1d ) points.Add( new Point( x, y ) );
    else points.Add( null );
}

}

Line "Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );" and next processing gets us only single person's pose. And comment for this line says the same. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes,

Sergey Netyagin

Multi-person poses poses' detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

CODE FRAGMENT:

private void RecognizePose( Mat image, Mat output_image, List<point> points, float[] data ) {

for( int i = 0; i < BODY_PARTS_MPI.Count; i++ ) {

    output_image.get( i, 0, data );

    Mat heat_map = new Mat ( 1, data.Length, CvType.CV_32FC1 );

    heat_map.put( 0, 0, data );

    //Originally, we try to find all the local maximums. To simplify a sample
    //we just find a global one. However only a single pose at the same time
    //could be detected this way.
    Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );

    heat_map.Dispose();

    double x = (

        (image.cols() * 
        (result.maxLoc.x % matrix_output_columns)) / 
        matrix_output_columns
    );

    double y = (

        (image.rows() * 
        (result.maxLoc.x / matrix_output_rows)) / 
        matrix_output_rows
    );

    if( result.maxVal > 0.1d ) points.Add( new Point( x, y ) );
    else points.Add( null );
}

}

Line "Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );" and next processing gets us only single person's pose. And comment for this line says the same. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes,

Sergey Netyagin

Multi-person poses' detection using OpenCV + OpenPose

Hello, dear colleagiues!

I recently started studying computer vision. I'm very interested this direction. Now I'm studying the recognition of human poses, and I'm trying to remake some examples in C # to experiment further in Unity.

However, I can not find documentation or examples of how I could improve my code anywhere to find the poses of all people in the image. Could you tell me how I should change my code so that I can recognize the poses for all people in the image?

CODE FRAGMENT:

private void RecognizePose( Mat image, Mat output_image, List<point> points, float[] data ) {

for( int i = 0; i < BODY_PARTS_MPI.Count; i++ ) {

    output_image.get( i, 0, data );

    Mat heat_map = new Mat ( 1, data.Length, CvType.CV_32FC1 );

    heat_map.put( 0, 0, data );

    //Originally, we try to find all the local maximums. To simplify a sample
    //we just find a global one. However only a single pose at the same time
    //could be detected this way.
    Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );

    heat_map.Dispose();

    double x = (

        (image.cols() * 
        (result.maxLoc.x % matrix_output_columns)) / 
        matrix_output_columns
    );

    double y = (

        (image.rows() * 
        (result.maxLoc.x / matrix_output_rows)) / 
        matrix_output_rows
    );

    if( result.maxVal > 0.1d ) points.Add( new Point( x, y ) );
    else points.Add( null );
}

}

Line "Core.MinMaxLocResult result = Core.minMaxLoc( heat_map );" and next processing gets us only single person's pose. And comment for this line says the same. But how can I get the all local maximumns and detect all poses?

With best regards and best wishes,

wishes, Sergey Netyagin