Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) GTX 1080Ti
• DeepStream Version 6.2
Before using the gst-nvinfer plugin for inference, I wanted to use OpenCV to perform image preprocessing on multiple video streams, such as adjusting the brightness of each frame. Do we have any examples for reference? Thanks！
Yes. You can refer to our demo: opt\nvidia\deepstream\deepstream\sources\apps\sample_apps\deepstream-preprocess-test.
nvdspreprocess
Thanks for your reply. I looked at the code. Is this done by modifying the CustomTensorPreparation function in gst-plugins\gst-nvdspreprocess\nvdspreprocess_lib\ nvdspreprocess_lib.cpp? In this function, I want to call an OpenCV function to preprocess a batch of data.
There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks
Yes. Or you can directly extract this part as a separate part like deepstream-pose-classification. You can also use the NvbufTransform to preprocess the data.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.