Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.

Data of human pose estimation demo

Lc00
Beginner
430 Views

Hi, when getting the raw output message there has three parameters. Eg ( a, b, c)

Lc00_0-1647089315052.png

If the a and b is the coordinate of x and y and how about the c? What the data after symbol " | " represent?

Thank you.

 

0 Kudos
1 Solution
Hairul_Intel
Moderator
348 Views

Hi Lc00,

Thank you for reaching out to us.

 

I've ran Human Pose Estimation Python Demo with the following command:

python human_pose_estimation_demo.py -m intel\human-pose-estimation-0005\FP16\human-pose-estimation-0005.xml -at ae -i vid0.mp4 -r

 

Here is the result for my demo:

demo_result.png

 

When we use '-r' flag, the demo will print the raw detection results which are the values for 'poses' and 'scores' as shown in the code from line 160 of human_pose_estimation_demo.py

line 160.png

 

As I am running the demo using '-at ae' flag, we can confirm the 'poses' and 'scores' values from the human_pose_estimation_demo.py and hpe_associative_embedding.py script as shown below:

 

From line 102 of human_pose_estimation_demo.py:

line 102.png

From line 127 of hpe_associative_embedding.py :

line 127.png

From line 334 of hpe_associative_embedding.py :

line 334.png

 

Based on the code snippet shared above, the three parameters of the ( a, b, c ) are the X coordinate, Y coordinate and followed by the key point confidence score. Meanwhile, the result after "|" symbol is the mean score of the total key point confidence score.

 

For sharing purposes, the raw detection result outputs 17 ( x, y, score ) values as I am using human-pose-estimation-0005 model. These represents 17 key points of the joints (ears, eyes, nose, shoulders, elbows, wrists, hips, knees, and ankles).

 

 

Regards,

Hairul

 

View solution in original post

4 Replies
Hairul_Intel
Moderator
349 Views

Hi Lc00,

Thank you for reaching out to us.

 

I've ran Human Pose Estimation Python Demo with the following command:

python human_pose_estimation_demo.py -m intel\human-pose-estimation-0005\FP16\human-pose-estimation-0005.xml -at ae -i vid0.mp4 -r

 

Here is the result for my demo:

demo_result.png

 

When we use '-r' flag, the demo will print the raw detection results which are the values for 'poses' and 'scores' as shown in the code from line 160 of human_pose_estimation_demo.py

line 160.png

 

As I am running the demo using '-at ae' flag, we can confirm the 'poses' and 'scores' values from the human_pose_estimation_demo.py and hpe_associative_embedding.py script as shown below:

 

From line 102 of human_pose_estimation_demo.py:

line 102.png

From line 127 of hpe_associative_embedding.py :

line 127.png

From line 334 of hpe_associative_embedding.py :

line 334.png

 

Based on the code snippet shared above, the three parameters of the ( a, b, c ) are the X coordinate, Y coordinate and followed by the key point confidence score. Meanwhile, the result after "|" symbol is the mean score of the total key point confidence score.

 

For sharing purposes, the raw detection result outputs 17 ( x, y, score ) values as I am using human-pose-estimation-0005 model. These represents 17 key points of the joints (ears, eyes, nose, shoulders, elbows, wrists, hips, knees, and ankles).

 

 

Regards,

Hairul

 

Lc00
Beginner
334 Views

Thank you for the information. Can I know where to find the hpe_associative_embedding.py?

 

Hairul_Intel
Moderator
293 Views

Hi Lc00,

The hpe_associative_embedding.py file can be found in the following directory:

 

C:\Program Files (x86)\Intel\openvino_2021\deployment_tools\open_model_zoo\demos\common\python\models

 

 

Regards,

Hairul


Hairul_Intel
Moderator
231 Views

Hi Lc00,

This thread will no longer be monitored since this issue has been resolved. If you need any additional information from Intel, please submit a new question.

 

 

Regards,

Hairul


Reply