The app partially reproduces deepstream_lpr_app in the Savant framework. The pipeline detects cars using the YoloV11 model and detects license plates using the NVidia LPD model. Cars and plates track using NVidia tracker the license plate is recognized using the NVidia OCR model. The results are displayed on the frames.

Preview:

Tested on platforms:

• Nvidia Turing, Ampere
• Nvidia Jetson Orin family

Demonstrated adapters:

• Video loop source adapter;
• Always-ON RTSP sink adapter.

git clone https://github.com/insight-platform/Savant.git
cd Savant
git lfs pull
./utils/check-environment-compatible

Note: Ubuntu 22.04 runtime configuration guide helps to configure the runtime to run Savant pipelines.

The demo uses models that are compiled into TensorRT engines the first time the demo is run. This takes time. Optionally, you can prepare the engines before running the demo by using the command:

# you are expected to be in Savant/ directory

./scripts/run_module.py --build-engines samples/license_plate_recognition/module.yml

# you are expected to be in Savant/ directory

# if x86
docker compose -f samples/license_plate_recognition/docker-compose.x86.yml up

# if Jetson
docker compose -f samples/license_plate_recognition/docker-compose.l4t.yml up

# open 'rtsp://127.0.0.1:554/stream/video' in your player
# or visit 'http://127.0.0.1:888/stream/video/' (LL-HLS)

# Ctrl+C to stop running the compose bundle

Download the video file to the data folder. For example:

# you are expected to be in Savant/ directory

mkdir -p data && curl -o data/lpr_test_1080p.mp4 \
   https://eu-central-1.linodeobjects.com/savant-data/demo/lpr_test_1080p.mp4

Now you are ready to run the performance benchmark with the following command:

./samples/license_plate_recognition/run_perf.sh

Note: Change the value of the DATA_LOCATION variable in the run_perf.sh script if you changed the video.