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 1.24.3 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.3 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 2.19.1 Download
TFLITE w8a8 Universal QAIRT 2.43, TFLite 2.19.1 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 2.337 ms 0 - 160 MB NPU
Person-Foot-Detection ONNX float Snapdragon® X2 Elite 2.554 ms 18 - 18 MB NPU
Person-Foot-Detection ONNX float Snapdragon® X Elite 4.858 ms 17 - 17 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 3.287 ms 3 - 186 MB NPU
Person-Foot-Detection ONNX float Qualcomm® QCS8550 (Proxy) 4.606 ms 14 - 18 MB NPU
Person-Foot-Detection ONNX float Qualcomm® QCS9075 7.59 ms 18 - 21 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.819 ms 0 - 156 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.419 ms 0 - 173 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® X2 Elite 2.632 ms 7 - 7 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® X Elite 4.255 ms 10 - 10 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 2.747 ms 0 - 195 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS6490 523.864 ms 92 - 97 MB CPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS8550 (Proxy) 3.938 ms 7 - 16 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS9075 5.004 ms 9 - 12 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCM6690 287.992 ms 95 - 103 MB CPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.357 ms 0 - 169 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 277.411 ms 94 - 102 MB CPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.676 ms 0 - 161 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® X2 Elite 0.753 ms 5 - 5 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® X Elite 1.604 ms 8 - 8 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.952 ms 0 - 66 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS6490 75.736 ms 50 - 57 MB CPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS8550 (Proxy) 1.389 ms 0 - 22 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS9075 1.773 ms 0 - 3 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCM6690 75.315 ms 51 - 60 MB CPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.791 ms 0 - 43 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 58.112 ms 51 - 61 MB CPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.395 ms 4 - 168 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® X2 Elite 3.072 ms 4 - 4 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® X Elite 4.894 ms 4 - 4 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.349 ms 1 - 184 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8275 (Proxy) 22.477 ms 1 - 152 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8550 (Proxy) 4.462 ms 4 - 89 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA8775P 7.221 ms 0 - 155 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS9075 8.379 ms 6 - 15 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8450 (Proxy) 10.647 ms 3 - 194 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA7255P 22.477 ms 1 - 152 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA8295P 7.826 ms 0 - 158 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.523 ms 0 - 156 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.955 ms 2 - 167 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® X2 Elite 2.676 ms 2 - 2 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® X Elite 3.634 ms 2 - 2 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.193 ms 2 - 186 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS6490 13.11 ms 1 - 6 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 8.132 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 3.272 ms 2 - 3 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA8775P 3.776 ms 2 - 162 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS9075 4.392 ms 0 - 6 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCM6690 35.259 ms 2 - 157 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 5.53 ms 2 - 186 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA7255P 8.132 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA8295P 5.205 ms 2 - 157 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.006 ms 0 - 162 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.77 ms 2 - 159 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.516 ms 0 - 154 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® X2 Elite 0.793 ms 1 - 1 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® X Elite 1.394 ms 1 - 1 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.782 ms 0 - 53 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS6490 5.173 ms 1 - 5 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 3.567 ms 1 - 38 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 1.165 ms 1 - 18 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA8775P 1.566 ms 0 - 41 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS9075 1.346 ms 3 - 7 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCM6690 14.76 ms 1 - 150 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 1.537 ms 1 - 56 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA7255P 3.567 ms 1 - 38 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA8295P 2.226 ms 0 - 36 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.643 ms 1 - 154 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.826 ms 1 - 151 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.255 ms 0 - 159 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 3.0 ms 0 - 183 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) 4.33 ms 5 - 14 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA8775P 6.976 ms 5 - 161 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS9075 7.56 ms 4 - 19 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8450 (Proxy) 7.912 ms 5 - 193 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA7255P 22.084 ms 5 - 157 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA8295P 8.633 ms 5 - 163 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.707 ms 0 - 154 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.513 ms 0 - 154 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 5.789 ms 1 - 8 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 3.577 ms 1 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.148 ms 0 - 2 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA8775P 1.599 ms 0 - 40 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS9075 1.369 ms 0 - 7 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCM6690 14.725 ms 1 - 150 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.485 ms 0 - 53 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA7255P 3.577 ms 1 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA8295P 2.228 ms 0 - 35 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.656 ms 0 - 150 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.8 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