This is Person Identification Test App using Intel OpenVINO Person Re-Identification Model.
- Person Detection
- Person Re-Identification
Person re-identifiction - Tracking - (YouTube Link)
Person re-identifiction - Tracking - (YouTube Link)
- Python 3.9.13
- Windows 11 22H2
- OpenVINO Toolkit 2022.1 ~ 2022.3
[MODELS]
# Don't add a trailing slash
model_path = model/intel
model_det = person-detection-retail-0013
model_reid = person-reidentification-retail-0031
You can download models which you like.
See OpenVINO User Guide: Model Downloader
pip install -r requirements.txt
python app.py -h
usage: app.py [-h] -i INPUT [-d {CPU,GPU,FPGA,MYRIAD}]
[-d_reid {CPU,GPU,FPGA,MYRIAD}] [--v4l] [-g GRID] [-v]
optional arguments:
-h, --help show this help message and exit
-i INPUT, --input INPUT
Path to video file or image. 'cam' for capturing video
stream from camera
-d {CPU,GPU,FPGA,MYRIAD}, --device {CPU,GPU,FPGA,MYRIAD}
Specify the target device for Person Detection to
infer on; CPU, GPU, FPGA or MYRIAD is acceptable.
-d_reid {CPU,GPU,FPGA,MYRIAD}, --device_reidentification {CPU,GPU,FPGA,MYRIAD}
Specify the target device for person re-identificaiton
to infer on; CPU, GPU, FPGA or MYRIAD is acceptable.
--v4l cv2.VideoCapture with cv2.CAP_V4L
-g GRID, --grid GRID Specify how many grid to divide frame. This is used to
define boundary area when the tracker counts person. 0
~ 2 means not counting person. (range: 3 < max_grid)
-v, --verbose set logging level Debug
example1. camera streaming without person counter
python app.py -i cam
example2 Specify video file with person counter
python app.py -i video\TownCentreXVID.mp4
Access the url bellow on your browser
http://127.0.0.1:5000/
The log (app.log) is output to the current directory.