I am going to write yolov4 real-time object detection, and I have to do it for car then vehicle plate number, but it does not have to find plate number if there is no car, first car then number on car, is that possible? Is it okay to use the darknet framework?
Is it okay to use the darknet framework?
You can use Darknet for finding the car and number plate.
I have to do it for car then vehicle plate number
If you are only looking to find plate numbers, finding the car also will be redundant. Unless you expect bikes or something else with number plates.
To get the characters on the number plate you will have to feed your detections from YOLO into an OCR. Have a look at this article for a more detailed description: "OpenCV: Automatic License/Number Plate Recognition (ANPR) with Python".
It summes up the process like this:
- Step #1: Detect and localize a license plate in an input image/frame
- Step #2: Extract the characters from the license plate
- Step #3: Apply some form of Optical Character Recognition (OCR) to recognize the extracted characters
it does not have to find plate number if there is no car
It never will if it's trained on images with cars, with number plates.