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

Pose Estimation Performance

idata
Employee
1,461 Views

Hi - we're looking at pose estimation (in the sense of skeleton tracking) on the Movidius - excited to see that there's a pre-trained model and example code, but I can't find any sense anywhere of how fast that runs. I realise that what it's attached to will have significant bearing, as will the size of the image it's processing, but does anyone have any finger-to-the-wind idea (or better still numbers from an actual rig) of how many frames per second we could get (even if it's seconds per frame!)?

 

Many thanks

 

Mike

0 Kudos
7 Replies
idata
Employee
1,060 Views

Really? Has nobody run this example on anything? I just want a sense of how fast or slow it is!

0 Kudos
idata
Employee
1,060 Views

Hi @mikepelton

 

Is there any particular example you are interested in? I can do a quick test and share the results with you.

 

Regards,

 

Jesus
0 Kudos
idata
Employee
1,060 Views

Hi @Jesus_at_Intel

 

I'm interesting in a pose estimation project using Movidius. I wanna ask you if you have done some work about pose estimation mission on Movidius. I‘m grateful if you share some useful models with me.

 

Best wishes,

 

Neil
0 Kudos
idata
Employee
1,060 Views

Hi @neilwu

 

I have not done any work with pose estimation with the Neural Compute SDK. However, I ran the example code with the pre-trained model included in the OpenVINO toolkit and I am getting about 2.8 FPS on the Intel Neural Compute Stick and about 4.5 FPS on the Intel Nerual Compute Stick 2. I am running the example code with a web cam feed.

 

./human_pose-Estimation_demo -i cam -m ~/intel/computer_vision_sdk/deployment_tools/intel_models/human-pose-estimation-0001/FP16/human-pose-estimation-0001.xml -d MYRIAD

 

Running the same example code on my Ubuntu virtual machine using the CPU resulted in about 8.8 FPS.

 

./human_pose-Estimation_demo -i cam -m ~/intel/computer_vision_sdk/deployment_tools/intel_models/human-pose-estimation-0001/FP32/human-pose-estimation-0001.xml -d CPU

 

Hope this helps!

 

Regards,

 

Jesus
0 Kudos
idata
Employee
1,060 Views

Hi @Jesus_at_Intel

 

Thanks for your advising! And I successfully ran the example human pose estimation code in the OpenVINO toolkit.

 

But I found a little questions on the running speed between NCS and NCS2.

 

With a local video file (means -i /PATH/TO/VIDEO/.mp4) , I am getting about 2.8 FPS on the Intel Neural Compute Stick and about 4.8 FPS on the Intel Nerual Compute Stick 2 just exactly like yours.

 

BUT, with a USB cam input (means -i cam), I am getting about 1.9 FPS on the Intel Neural Compute Stick and about 2.4 FPS on the Intel Nerual Compute Stick 2. You can see the running speed improvement is little. Can you tell me about it? Thanks a lot.

 

Regards,

 

Neil
0 Kudos
idata
Employee
1,060 Views

Hi @neilwu

 

Could you tell me which USB camera you are using? I'm wondering if the performance is different with a higher resolution camera. The camera I used in my test had a 720p resolution.

 

Update: I ran a quick test with a higher resolution (1080p) camera and saw similar FPS as my previous test. I am using OpenVINO toolkit R 5.0.1, ran tests on a Windows install of OpenVINO and an Ubuntu VM install.

 

Regards,

 

Jesus
0 Kudos
idata
Employee
1,060 Views

Hi @Jesus_at_Intel

 

As you say, I think the USB camera I used might be a lower resolution(a cheap camera). After I will use a higher resolution camera and test on it.

 

Thanks your reply!

 

Regards,

 

Neil
0 Kudos
Reply