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® X Elite 4.905 ms 17 - 17 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 3.29 ms 0 - 189 MB NPU
Person-Foot-Detection ONNX float Qualcomm® QCS8550 (Proxy) 4.595 ms 2 - 12 MB NPU
Person-Foot-Detection ONNX float Qualcomm® QCS9075 7.551 ms 19 - 22 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.818 ms 0 - 151 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.347 ms 0 - 160 MB NPU
Person-Foot-Detection ONNX float Snapdragon® X2 Elite 2.566 ms 18 - 18 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® X Elite 4.284 ms 10 - 10 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 2.755 ms 0 - 197 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS6490 523.879 ms 92 - 96 MB CPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS8550 (Proxy) 3.931 ms 9 - 117 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS9075 5.008 ms 9 - 12 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCM6690 286.396 ms 116 - 124 MB CPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.361 ms 0 - 167 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 258.056 ms 74 - 83 MB CPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.618 ms 0 - 172 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® X2 Elite 2.633 ms 7 - 7 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® X Elite 1.607 ms 8 - 8 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.959 ms 0 - 66 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS6490 76.04 ms 51 - 58 MB CPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS8550 (Proxy) 1.396 ms 0 - 5 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS9075 1.809 ms 0 - 3 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCM6690 75.574 ms 49 - 58 MB CPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.789 ms 0 - 49 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 58.51 ms 55 - 64 MB CPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.675 ms 0 - 160 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® X2 Elite 0.754 ms 5 - 5 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® X Elite 4.874 ms 4 - 4 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.214 ms 0 - 184 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8275 (Proxy) 22.5 ms 1 - 153 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8550 (Proxy) 4.447 ms 4 - 5 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA8775P 7.212 ms 1 - 157 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS9075 8.377 ms 4 - 14 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8450 (Proxy) 10.656 ms 2 - 192 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA7255P 22.5 ms 1 - 153 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA8295P 7.833 ms 0 - 158 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.515 ms 4 - 165 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.403 ms 4 - 167 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® X2 Elite 3.134 ms 4 - 4 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® X Elite 3.636 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 13.009 ms 1 - 7 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 8.104 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 3.228 ms 2 - 3 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA8775P 3.797 ms 2 - 162 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS9075 4.429 ms 1 - 7 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCM6690 32.852 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 5.549 ms 2 - 186 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA7255P 8.104 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA8295P 5.16 ms 2 - 157 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 1.989 ms 0 - 163 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.774 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.966 ms 2 - 166 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® X2 Elite 2.659 ms 2 - 2 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® X Elite 1.401 ms 1 - 1 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.785 ms 1 - 54 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS6490 5.184 ms 1 - 5 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 3.549 ms 1 - 38 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 1.164 ms 1 - 2 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA8775P 5.717 ms 1 - 39 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS9075 1.351 ms 3 - 6 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCM6690 14.913 ms 1 - 151 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 1.486 ms 1 - 56 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA7255P 3.549 ms 1 - 38 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA8295P 2.213 ms 1 - 37 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.646 ms 0 - 150 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.786 ms 1 - 152 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.519 ms 1 - 155 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® X2 Elite 0.798 ms 1 - 1 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 3.002 ms 0 - 179 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8275 (Proxy) 22.065 ms 5 - 157 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8550 (Proxy) 4.367 ms 1 - 2 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA8775P 6.974 ms 5 - 160 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS9075 7.549 ms 4 - 19 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8450 (Proxy) 7.926 ms 5 - 194 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA7255P 22.065 ms 5 - 157 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA8295P 8.657 ms 5 - 163 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.739 ms 0 - 160 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.277 ms 0 - 159 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.788 ms 0 - 54 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS6490 5.417 ms 1 - 8 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 3.572 ms 1 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.17 ms 0 - 2 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA8775P 1.592 ms 0 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS9075 1.369 ms 0 - 7 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCM6690 14.971 ms 1 - 153 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.463 ms 0 - 53 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA7255P 3.572 ms 1 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA8295P 2.253 ms 0 - 35 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.649 ms 0 - 149 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.807 ms 0 - 150 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.514 ms 0 - 154 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