MediaPipe-Hand-Detection: Optimized for Qualcomm Devices

The MediaPipe Hand Landmark Detector is a machine learning pipeline that predicts bounding boxes and pose skeletons of hands in an image.

This is based on the implementation of MediaPipe-Hand-Detection found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime	Precision	Chipset	SDK Versions	Download
ONNX	float	Universal	QAIRT 2.50, ONNX Runtime 1.30.0	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit MediaPipe-Hand-Detection on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

Custom weights (e.g., fine-tuned checkpoints)
Custom input shapes
Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for MediaPipe-Hand-Detection on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

Input resolution: 256x256
Model size (hand_detector) (float): 6.75 MB
Model size (hand_landmark_detector) (float): 7.70 MB
Number of parameters (hand_detector): 1.76M
Number of parameters (hand_landmark_detector): 2.01M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
hand_detector	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.427 ms	0 - 46 MB	NPU
hand_detector	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.49 ms	0 - 49 MB	NPU
hand_detector	ONNX	float	Snapdragon® X2 Elite	0.476 ms	2 - 2 MB	NPU
hand_detector	ONNX	float	Snapdragon® X Elite	0.842 ms	0 - 0 MB	NPU
hand_detector	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.59 ms	0 - 69 MB	NPU
hand_detector	ONNX	float	Snapdragon® 8 Gen 1 Mobile	1.39 ms	1 - 66 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	1.36 ms	1 - 5 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.835 ms	0 - 6 MB	NPU
hand_detector	ONNX	float	Qualcomm® QCS8450	1.39 ms	1 - 66 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	1.262 ms	1 - 4 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	0.842 ms	0 - 0 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.49 ms	0 - 49 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.384 ms	1 - 44 MB	NPU

License

The license for the original implementation of MediaPipe-Hand-Detection can be found here.

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.