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
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. | Latency 1 | Micro 2 | Model size | Downloads |
|---|---|---|---|---|---|---|---|---|
|
PoseNet MobileNet V1 |
17 body points |
324x324x3 | 16 | 1 | N/A | Yes | 1.6 MB | |
|
PoseNet MobileNet V1 |
17 body points |
353x481x3 | 16 | 1 | 5.8 ms | Yes* | 1.5 MB | |
|
PoseNet MobileNet V1 |
17 body points |
481x641x3 | 16 | 1 | 10.3 ms | Yes* | 1.7 MB | |
|
PoseNet MobileNet V1 |
17 body points |
721x1281x3 | 16 | 1 | 32.4 ms | Yes* | 2.5 MB | |
|
MoveNet.SinglePose.Lightning |
17 body points |
192x192x3 | 4 | 2 | 7.1 ms | No | 3.1 MB | |
|
MoveNet.SinglePose.Thunder |
17 body points |
256x256x3 | 4 | 2 | 13.8 ms | No | 7.5 MB | |
|
PoseNet ResNet-50 |
17 body points |
288x416x3 | 16 | 1 | N/A | No | 24.4 MB | |
|
PoseNet ResNet-50 |
17 body points |
480x640x3 | 16 | 1 | N/A | No | 26.4 MB | |
|
PoseNet ResNet-50 |
17 body points |
496x768x3 | 32 | 1 | N/A | No | 26.8 MB | |
|
PoseNet ResNet-50 |
17 body points |
624x864x3 | 32 | 1 | N/A | No | 28.4 MB | |
|
PoseNet ResNet-50 |
17 body points |
672x928x3 | 16 | 1 | N/A | No | 35.0 MB | |
|
PoseNet ResNet-50 |
17 body points |
736x960x3 | 32 | 1 | N/A | No | 38.5 MB |
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.
2 Indicates compatibility with the Dev Board Micro. Some models are not compatible because they require a CPU-bound op that is not supported by TensorFlow Lite for Microcontrollers or they require more memory than available on the board. (All models are compatible with all other Coral boards.)
* Although Dev Board Micro supports all the PoseNet MobileNet V1 models, beware that the on-board camera is 324x324 px, so you should use only the 324x324x3 model, unless you connect a larger-resolution camera.
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
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
videocam
Person segmentation with video
Although this example is usually used for semantic segmentation on the human body (using BodyPix), it also provides pose estimation data.
Languages: Python