search

stephanecharette / DarkPlate

License plate parsing using Darknet and YOLO
MIT License
59 stars 11 forks source link

Awesome work #2

Closed rsingh2083 closed 3 years ago

rsingh2083 commented 3 years ago

Hi Stephane,

This is really good, just one issue. How can I reduce the input video size to make it run smoothly. Right now its running the input video in full 1080p mode, hence slow. Is there any way to pass the video in lower resolution to the inference model so as to make it realtime ?

stephanecharette commented 3 years ago

OpenCV has several ways to do this. The best of course is to modify the camera parameters to take video in the resolution and FPS you need. Take a look at cv::CAP_PROP_FRAME_WIDTH, cv::CAP_PROP_FRAME_HEIGHT, and cv::CAP_PROP_FPS, with the API cv::VideoCapture::set().

Otherwise, if you're not using cv::VideoCapture then use the normal OpenCV methods to resize your frames.

rsingh2083 commented 3 years ago

Ok Stephan