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 2.37, ONNX Runtime 1.23.0 Download
ONNX w8a16 Universal QAIRT 2.37, ONNX Runtime 1.23.0 Download
ONNX w8a8 Universal QAIRT 2.37, ONNX Runtime 1.23.0 Download
QNN_DLC float Universal QAIRT 2.42 Download
QNN_DLC w8a16 Universal QAIRT 2.42 Download
QNN_DLC w8a8 Universal QAIRT 2.42 Download
TFLITE float Universal QAIRT 2.42, TFLite 2.17.0 Download
TFLITE w8a8 Universal QAIRT 2.42, 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 5.545 ms 17 - 17 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Gen 3 Mobile 4.267 ms 18 - 156 MB NPU
Person-Foot-Detection ONNX float Qualcomm® QCS8550 (Proxy) 5.911 ms 11 - 15 MB NPU
Person-Foot-Detection ONNX float Qualcomm® QCS9075 7.983 ms 16 - 19 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Elite For Galaxy Mobile 3.675 ms 0 - 106 MB NPU
Person-Foot-Detection ONNX float Snapdragon® 8 Elite Gen 5 Mobile 2.66 ms 0 - 112 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® X Elite 4.793 ms 10 - 10 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.229 ms 1 - 145 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS6490 532.305 ms 92 - 97 MB CPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS8550 (Proxy) 4.725 ms 9 - 12 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCS9075 5.225 ms 10 - 13 MB NPU
Person-Foot-Detection ONNX w8a16 Qualcomm® QCM6690 280.915 ms 94 - 102 MB CPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.908 ms 0 - 125 MB NPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 256.463 ms 98 - 106 MB CPU
Person-Foot-Detection ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.749 ms 0 - 124 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® X Elite 1.608 ms 8 - 8 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 1.107 ms 0 - 133 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS6490 75.94 ms 50 - 58 MB CPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS8550 (Proxy) 1.724 ms 0 - 87 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCS9075 2.042 ms 0 - 3 MB NPU
Person-Foot-Detection ONNX w8a8 Qualcomm® QCM6690 74.495 ms 50 - 59 MB CPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.957 ms 0 - 110 MB NPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 57.087 ms 50 - 61 MB CPU
Person-Foot-Detection ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.776 ms 0 - 117 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® X Elite 4.921 ms 4 - 4 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Gen 3 Mobile 3.207 ms 0 - 184 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8275 (Proxy) 22.469 ms 0 - 152 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8550 (Proxy) 4.529 ms 4 - 5 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA8775P 7.227 ms 0 - 157 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS9075 8.384 ms 4 - 14 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® QCS8450 (Proxy) 10.618 ms 3 - 195 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA7255P 22.469 ms 0 - 152 MB NPU
Person-Foot-Detection QNN_DLC float Qualcomm® SA8295P 7.846 ms 0 - 158 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.578 ms 4 - 160 MB NPU
Person-Foot-Detection QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 2.429 ms 1 - 201 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® X Elite 3.644 ms 2 - 2 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.315 ms 2 - 187 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS6490 12.958 ms 1 - 7 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 8.317 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 3.255 ms 2 - 4 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA8775P 3.938 ms 2 - 161 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS9075 4.179 ms 2 - 7 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCM6690 36.08 ms 2 - 157 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 5.834 ms 2 - 188 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA7255P 8.317 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Qualcomm® SA8295P 5.409 ms 2 - 156 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 1.983 ms 0 - 162 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.787 ms 2 - 158 MB NPU
Person-Foot-Detection QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.864 ms 2 - 168 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® X Elite 1.379 ms 1 - 1 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.786 ms 1 - 55 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS6490 5.525 ms 3 - 6 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 3.546 ms 1 - 39 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 1.165 ms 1 - 2 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA8775P 1.54 ms 1 - 41 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS9075 1.339 ms 0 - 4 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCM6690 14.901 ms 1 - 150 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 1.452 ms 1 - 56 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA7255P 3.546 ms 1 - 39 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Qualcomm® SA8295P 2.224 ms 0 - 36 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.644 ms 0 - 150 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.817 ms 0 - 151 MB NPU
Person-Foot-Detection QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.51 ms 1 - 155 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Gen 3 Mobile 3.214 ms 0 - 185 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8275 (Proxy) 22.496 ms 5 - 157 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8550 (Proxy) 4.488 ms 0 - 2 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA8775P 7.131 ms 5 - 161 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS9075 7.534 ms 4 - 19 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® QCS8450 (Proxy) 7.862 ms 5 - 193 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA7255P 22.496 ms 5 - 157 MB NPU
Person-Foot-Detection TFLITE float Qualcomm® SA8295P 8.772 ms 5 - 162 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.706 ms 0 - 153 MB NPU
Person-Foot-Detection TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 2.27 ms 0 - 161 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.779 ms 0 - 53 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS6490 5.506 ms 0 - 7 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 3.601 ms 1 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.133 ms 0 - 2 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA8775P 1.601 ms 0 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS9075 1.359 ms 0 - 7 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCM6690 14.833 ms 1 - 149 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.497 ms 0 - 52 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA7255P 3.601 ms 1 - 39 MB NPU
Person-Foot-Detection TFLITE w8a8 Qualcomm® SA8295P 2.246 ms 0 - 35 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.661 ms 0 - 155 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.839 ms 0 - 149 MB NPU
Person-Foot-Detection TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.518 ms 0 - 155 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