Pose estimation

A pose estimation model can identify the position of several points on the human body, for multiple people in the image.

With the Coral Edge TPU™, you can run a pose estimation model directly on your device, using real-time video, at over 100 frames per second. You can even run a second model concurrently on one Edge TPU, while maintaining a high frame rate.

This page provides several trained models that are compiled for the Edge TPU, and some example code to run them.

Trained models link

These models are trained and compiled for the Edge TPU.

Notice: These are not production-quality models; they are for demonstration purposes only.
Model name Detections/Dataset Input size Output stride TF ver. Latency1 Model size Downloads

PoseNet MobileNet V1

17 body points

353x481x3 16 1 5.8 ms 1.5 MB

Edge TPU model, CPU model

PoseNet MobileNet V1

17 body points

481x641x3 16 1 10.3 ms 1.7 MB

Edge TPU model, CPU model

PoseNet MobileNet V1

17 body points

721x1281x3 16 1 32.4 ms 2.5 MB

Edge TPU model, CPU model

MoveNet.SinglePose.Lightning
New

17 body points

192x192x3 4 2 7.1 ms 3.1 MB

Edge TPU model, CPU model

MoveNet.SinglePose.Thunder
New

17 body points

256x256x3 4 2 13.8 ms 7.5 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body points

288x416x3 16 1 N/A 24.4 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body points

480x640x3 16 1 N/A 26.4 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body points

496x768x3 32 1 N/A 26.8 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body points

624x864x3 32 1 N/A 28.4 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body points

672x928x3 16 1 N/A 35.0 MB

Edge TPU model, CPU model

PoseNet ResNet-50

17 body points

736x960x3 32 1 N/A 38.5 MB

Edge TPU model, CPU model

1 Latency is the time to perform one inference, as measured with a Coral USB Accelerator on a desktop CPU. Latency varies between systems and is primarily intended for comparison between models. For more comparisons, see the Performance Benchmarks.

Note: BodyPix is another model that performs pose estimation, but it also provides semantic segmentation output for 24 body parts, so you can find it with the semantic segmentation models.

Example code link

MoveNet pose estimation

This example shows how to use the high-performance MoveNet model to detect human poses from images, and can be used with the high-speed "lighting" model or high-accuracy "thunder" model.

Languages: Python

videocam

PoseNet pose estimation with video

Multiple examples showing how to use the PoseNet model to detect human poses from images and video, such as locating the position of someone’s elbow, shoulder or foot.

Languages: Python