Hugging Face's logo

qualcomm
/
Person-Foot-Detection

Object Detection
PyTorch
real_time
bu_iot
android
Model card Files
xet
 Community

Person-Foot-Detection: Optimized for Qualcomm Devices

Real-time multiple person detection with accurate feet localization optimized for mobile and edge.

This is based on the implementation of Person-Foot-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 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
QNN_DLC float Universal QAIRT 2.43 Download
QNN_DLC w8a16 Universal QAIRT 2.43 Download
QNN_DLC w8a8 Universal QAIRT 2.43 Download
TFLITE float Universal QAIRT 2.43, TFLite 2.17.0 Download
TFLITE w8a8 Universal QAIRT 2.43, TFLite 2.17.0 Download

For more device-specific assets and performance metrics, visit Person-Foot-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 Person-Foot-Detection on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

  • Inference latency: RealTime
  • Input resolution: 640x480
  • Number of output classes: 2
  • Number of parameters: 2.53M
  • Model size (float): 9.69 MB
  • Model size (w8a8): 2.62 MB
  • Model size (w8a16): 2.90 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Person-Foot-Detection ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.34 ms 1 - 161 MB NPU
Person-Foot-Detection ONNX float Snapdragon® X2 Elite 2.559 ms 19 - 19 MB NPU
Person-Foot-Detection ONNX float Snapdragon® X Elite 4.949 ms 17 - 17 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 3.27 ms 3 - 191 MB NPU
Person-Foot-Detection ONNX float Qualcomm® QCS8550 (Proxy) 4.575 ms 17 - 21 MB NPU
Person-Foot-Detection ONNX float Qualcomm® QCS9075 7.535 ms 16 - 19 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.815 ms 0 - 151 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.425 ms 0 - 172 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® X2 Elite 2.662 ms 7 - 7 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® X Elite 4.264 ms 10 - 10 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 2.757 ms 0 - 194 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS6490 527.625 ms 93 - 97 MB CPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS8550 (Proxy) 3.937 ms 0 - 5 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS9075 4.994 ms 9 - 12 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCM6690 284.277 ms 94 - 102 MB CPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.366 ms 0 - 168 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 276.468 ms 100 - 109 MB CPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.674 ms 0 - 160 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® X2 Elite 0.751 ms 5 - 5 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® X Elite 1.618 ms 8 - 8 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.953 ms 0 - 66 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS6490 76.476 ms 50 - 57 MB CPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS8550 (Proxy) 1.398 ms 0 - 24 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS9075 1.76 ms 0 - 3 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCM6690 75.419 ms 49 - 58 MB CPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.791 ms 0 - 49 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 58.437 ms 57 - 67 MB CPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.385 ms 4 - 166 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® X2 Elite 3.136 ms 4 - 4 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® X Elite 4.847 ms 4 - 4 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.216 ms 4 - 188 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8275 (Proxy) 22.51 ms 0 - 152 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8550 (Proxy) 4.454 ms 4 - 74 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA8775P 7.206 ms 0 - 156 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS9075 8.412 ms 4 - 13 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8450 (Proxy) 10.641 ms 3 - 195 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA7255P 22.51 ms 0 - 152 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA8295P 7.797 ms 0 - 158 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.524 ms 0 - 156 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.941 ms 2 - 167 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® X2 Elite 2.636 ms 2 - 2 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® X Elite 3.628 ms 2 - 2 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.191 ms 2 - 187 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS6490 12.911 ms 1 - 6 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 8.102 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 3.234 ms 2 - 3 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA8775P 3.814 ms 2 - 162 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS9075 4.402 ms 1 - 7 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCM6690 36.664 ms 2 - 160 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 5.594 ms 2 - 188 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA7255P 8.102 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA8295P 5.193 ms 2 - 157 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.032 ms 2 - 163 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.815 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.514 ms 1 - 154 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® X2 Elite 0.782 ms 1 - 1 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® X Elite 1.378 ms 1 - 1 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.787 ms 1 - 54 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS6490 5.77 ms 3 - 7 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 3.519 ms 1 - 39 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 1.162 ms 1 - 2 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA8775P 1.565 ms 1 - 41 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS9075 1.36 ms 3 - 7 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCM6690 14.765 ms 1 - 150 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 1.432 ms 1 - 56 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA7255P 3.519 ms 1 - 39 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA8295P 2.221 ms 0 - 35 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.645 ms 1 - 156 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.786 ms 1 - 152 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.249 ms 0 - 160 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 2.984 ms 0 - 185 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8275 (Proxy) 22.084 ms 5 - 157 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8550 (Proxy) 4.25 ms 0 - 9 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA8775P 28.742 ms 5 - 157 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS9075 7.585 ms 4 - 19 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8450 (Proxy) 7.908 ms 4 - 192 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA7255P 22.084 ms 5 - 157 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA8295P 8.608 ms 5 - 163 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.698 ms 0 - 154 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.511 ms 0 - 153 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.788 ms 0 - 53 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS6490 5.159 ms 1 - 8 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 3.58 ms 1 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.147 ms 0 - 2 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA8775P 1.581 ms 0 - 40 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS9075 1.382 ms 0 - 7 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCM6690 14.752 ms 1 - 150 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.486 ms 0 - 53 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA7255P 3.58 ms 1 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA8295P 2.225 ms 0 - 35 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.655 ms 0 - 154 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.808 ms 0 - 150 MB NPU

License

  • The license for the original implementation of Person-Foot-Detection can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Object Detection
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support