I’m working on a Deepstream 5.0 python application which would count vehicle traffic flow and OCR license plates in realtime on Xavier device.
And looking for guidance and best practices in feature implementation.
As I understand on featuers:
- Vehicle detection can be done using TrafficCamNet
- Tracking using Deepstream built-in trackers
- License plate detection using ending from back-to-back detector from Deepstream 4.0 https://github.com/NVIDIA-AI-IOT/deepstream_reference_apps/tree/master/back-to-back-detectors
- On OCR I’m choosing between Teseract and OpenALPR
So my question is - what are the best/fastest-in-implementation way to implement feature #4 in Python application?
Options I know are:
- Import tesseract-ocr in Python code and process license plates cutouts in separate function
- Scrap Tesseract/OpenALPR for pretained models and use them as TensorRT engine in a Deepstream pipeline
- Make a gstreamer module (this is more like C++ coding)
I’d be glad to hear any feedback. Thanks!