QuickPose provides developer-oriented cutting edge ML features of MediaPipe and BlazePose, with easy integration and production ready code, which dramatically improves the speed of implementation of pose estimation, skeleton tracking and fitness counting features into mobile applications.
See our Features below or checkout our full documentation on our website docs.quickpose.ai/docs/MobileSDK
| Range Of Motion Example | Leg Raises Counter Example |
|---|---|
 |  |
Get your free SDK key on https://dev.quickpose.ai, usage limits may apply. SDK Keys are linked to your bundle ID, please check Key before distributing to the Play Store.
QuickPose process a video frame and makes it easy for developers to perform complex AI features to the image, such as overlaying markings to the output image to highlight the user's pose.
+----------++-------------++-----------------+
| | | | | OverlayView |
| Camera |--------->| QuickPose |--------->| + |
| | | | | Results |
+----------++-------------++-----------------+| Feature | Example | Supported |
|---|---|---|
| Joint Positions |  | v0.1 |
Overlays Whole Body Upper Body Lower Body Shoulder Left Arm Right Arm Left Leg Right Leg |  | v0.1 |
Health - Range Of Motion Left Shoulder Right Shoulder Left Hip Right Hip Left Knee Right Knee Back Neck | | v0.1 |
Fitness - Exercise Detection & Counter Squat Sumo Squat Jumping Jack Push Up Plank Cobra Wings Left Leg Lunge Right Leg Lunge SitUps CobraWings Plank Leg Raises Glute Bridge Overhead Dumbbell Press vUps Lateral Raises Front Raises Hip Abduction Standing Left Hip Abduction Standing Right Side Lunges Left Side Lunges Right Biceps Curls |  | v0.3 |
| Feature | Example | Supported |
|---|---|---|
| Stacked Feature Styling |  Bike Side View Video by Tariq Ali | v0.1 |
| Conditional Styling |  | v0.1 |
- Android SDK 26
- You'll need minimum quickpose-core 0.17 and quickpose-mp 0.6
In your app's build.gradle, copy the quickpose dependencies
dependencies {
// recommended for starting quickpose
implementation ("androidx.lifecycle:lifecycle-runtime-ktx:2.6.1'")
// CameraX core library
val camerax_version = ("1.4.1")
implementation("androidx.camera:camera-core:$camerax_version")
implementation("androidx.camera:camera-camera2:$camerax_version")
implementation("androidx.camera:camera-lifecycle:$camerax_version")
implementation("androidx.camera:camera-view:$camerax_version")
implementation("com.google.flogger:flogger:latest.release")
implementation("com.google.flogger:flogger-system-backend:latest.release")
implementation("com.google.guava:guava:27.0.1-android")
implementation("com.google.protobuf:protobuf-javalite:3.19.1")
implementation("com.microsoft.onnxruntime:onnxruntime-android:latest.release")
implementation("ai.quickpose:quickpose-mp:0.4")
implementation("ai.quickpose:quickpose-core:0.18")
}
See code examples below or download our Sample Apps.
Step 1: Download/Clone Repo
Step 2: Open Basic Demo
Step 3: Build to your device
Step 4: Run
Step 5: Explore the features and returned results
quickPose.start(
arrayOf(
Feature.Overlay(group =Landmarks.Group.Arm(Side.LEFT))
),
onFrame = { status, overlay, features, feedback, landmarks ->println("$status, $features")
}
) To enable proguard/r8 minifying, add these to your proguard rules:
-keep public interface com.google.mediapipe.framework.* {
public *;
}
-keep public class com.google.mediapipe.framework.Packet {
public static *** create(***);
public long getNativeHandle();
public void release();
}
-keep public class com.google.mediapipe.framework.PacketCreator {
*** releaseWithSyncToken(...);
}
-keep public class com.google.mediapipe.framework.MediaPipeException {
<init>(int, byte[]);
}
-keep class com.google.mediapipe.framework.ProtoUtil$SerializedMessage { *; }
-keep public class * extends com.google.protobuf.GeneratedMessageLite { *; }
-keepclassmembers class com.google.common.flogger.** { *; }
-keep class ai.onnxruntime.** { *; }
-keep class ai.quickpose.core.Status$* { *; }
Checkout our full documentation at https://docs.quickpose.ai/docs/MobileSDK