Skip to content

Latest commit

 

History

History
115 lines (79 loc) · 2.54 KB

README.md

File metadata and controls

115 lines (79 loc) · 2.54 KB
Raw

anpr-luxonis-python

ANPR using Luxonis camera

Requirements

  • depthai==2.22.0.0
  • opencv-python==4.8.0.76
  • depthai-pipeline-graph==0.0.5
  • depthai-sdk==1.13.1
  • openvino-dev==2023.1.0

developer tools

  • black
  • pylint
  • autoimport
  • isort

Setup

clone the repo

git clone [email protected]:slashdevops/anpr-luxonis-python.git

create a virtual environment and activate it

python3.9 -m venv venv

source venv/bin/activate
pip install --upgrade pip

install the dependencies

pip install -r requirements.txt

Download models

pip install openvino-dev
mkdir -p /Volumes/Projects/ANPR/project/openvino/{models,cache}
omz_downloader --all --cache_dir /Volumes/Projects/ANPR/project/openvino/cache --output_dir /Volumes/Projects/ANPR/project/openvino/models

Run

All detections

python3 main.py -nn ~/ai/custom_models/frozen_inference_graph_openvino_2021.4_6shave.blob -vid ~/Videos/1.mp4

License plate detections

python3 main.py -nn ~/ai/custom_models/frozen_inference_graph_openvino_2021.4_6shave.blob -vid ~/Videos/1.mp4

Car detections

python3 car_detect.py -vid ~/Videos/1.mp4

Pre-trained models

Luxonis zoo

Utils

Converters

OpenVINO to luxonis

Using converter.py script

python3 converter.py \
  -bin /home/christian/ai/openvino/intel/text-recognition-0014/FP16/text-recognition-0014.bin \
  -xml /home/christian/ai/openvino/intel/text-recognition-0014/FP16/text-recognition-0014.xml \
  -s 6

Using blobconverter tool

blobconverter \
  --openvino-bin "https://storage.openvinotoolkit.org/repositories/open_model_zoo/2021.4/models_bin/3/text-recognition-0014/FP16/text-recognition-0014.bin" \
  --openvino-xml "https://storage.openvinotoolkit.org/repositories/open_model_zoo/2021.4/models_bin/3/text-recognition-0014/FP16/text-recognition-0014.xml" \
  --shaves 6 \
  --no-cache
blobconverter \
  --zoo-name text-recognition-0014 \
  --shaves 6