Custom Pose Estimation | Fritz AI

Custom Pose Estimation

Create augmented and virtual reality apps using Custom Pose Estimation to track the 2D position of keypoints on any object. Use Custom Pose Estimation to build experiences where physical objects interact with virtual ones.
 

Custom Pose Estimation

Quickly move from an idea to a production-ready Pose Estimation model with Fritz AI Studio.
import Fritz

let poseModel = FritzVisionHumanPoseModelFast()

let image = FritzVisionImage(buffer: sampleBuffer)

guard let result = try? poseModel.predict(image) else { return }
image.draw(poses: result.poses())
Custom Pose Estimation

The Swift code sample here illustrates how simple it can be to use Pose Estimation in your app. Use the links below to access additional information about Fritz AI Studio and documentation that will help you get started.

Discover Studio

Features

Detect Custom Keypoints

2D Coordinates of predicted keypoints are provided for each skeleton detected.

Runs On-Device

All predictions / model inferences are made completely on-device.

No internet connection is required to interpret images or video.

No internet dependency means super-fast performance.

Model Variants

Fast: Optimized for speed, best for processing video streams in real-time or on older devices.

Accurate: Optimized for higher accuracy where prediction quality is more important than speed.

Small: Optimized for size, keep your application bundle size low and conserve bandwidth.

Cross-Platform SDKs

Supported mobile platforms:

  • Android Pose Estimation
  • iOS Pose Estimation
Live Video Performance

Runs on live video with a fast frame rate.

Exact FPS performance varies depending on device, but it is possible to run this feature on live video on modern mobile devices.

Technical Specifications

Architecture

Uses a MobileNet backbone

Model Size

~2 MB

FLOPS

1,600 M

Input

353x257-pixel image

Output

2D Coordinates of each keypoint detected

Number of keypoints detected

The confidence associated with each detection

Formats

Core ML, TensorFlow, TensorFlow Mobile, TensorFlow Lite, Keras

Benchmarks

25 FPS on iPhone X

7 FPS on Pixel 2