Skip to content

Latest commit

 

History

History
73 lines (60 loc) · 2.46 KB

README_EN.md

File metadata and controls

73 lines (60 loc) · 2.46 KB

[Japanese/English]

Person-Detection-using-RaspberryPi-CPU

This repository is person detection model and demo script assuming CPU operation of Raspberry Pi 4.

Demo.mp4

Using PINTO's TensorflowLite-bin, it works in about 45-60ms when 4 threads are running. * About 75ms in 1 thread.
It works on laptops, but if you need precision, we recommend an object discovery model other than this repository.
Also, when using a laptop PC, "model.onnx" is often faster. *Approximately 10ms on Core i7-8750H

Requirement

opencv-python 4.5.3.56 or later
tensorflow 2.8.0 or later *Recommended to use TensorflowLite-bin
onnxruntime 1.9.0 or later *Only when using model.onnx

Demo

Here's how to run the demo.

python demo.py
  • --device
    Specifying the camera device number
    Default：0
  • --movie
    Specify video file *When specified, priority is given to the camera device
    Default：unspecified
  • --width
    Width at the time of camera capture
    Default：640
  • --height
    Height at the time of camera capture
    Default：360
  • --model
    Storage path of the model to load
    Default：model/model.tflite
  • --score_th
    Detection threshold
    Default：0.4
  • --nms_th
    NMS threshold
    Default：0.5
  • --num_threads
    Number of threads used *Valid only when using TensorFlow-Lite
    Default：None

Demo(ROS2)

This is a demo for ROS2.

Terminal 1

ros2 run v4l2_camera v4l2_camera_node

Terminal 2

python3 ./demo_ros2.py

Application Example

Reference

Author

Kazuhito Takahashi(https://twitter.com/KzhtTkhs)

License

Person-Detection-using-RaspberryPi-CPU is under Apache 2.0 License.

License(Movie)

The sample video uses "London, England, Regent Street" from the NHK Creative Library.