Gst-nvdewarper Documentation Request

[josh4]

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 5.1
• TensorRT Version 7.2.2.3
• NVIDIA GPU Driver Version (valid for GPU only) 460.39
• Issue Type( questions, new requirements, bugs) questions

Could NVIDIA please provide some additional documentation on both the projection algorithms and configurable parameters in the dewarping plugin? I am able to achieve the desired output on my own cameras through trial and error but it’s important I understand how it all works. From reading through the forums, there are quite a few of us who are confused by the current documentation. Any additional documentation would be greatly appreciated by myself and many others! Thank you!

I have already looked at the following documentation:

• DeepStream Plugins 5.0
• Gst-nvdewarper — DeepStream 6.1.1 Release documentation
• deepstream_360_d_smart_parking_application/DeepStream_Analytics_Applications.pdf at master · NVIDIA-AI-IOT/deepstream_360_d_smart_parking_application · GitHub
• https://developer.nvidia.com/blog/calibration-translate-video-data/

I have already successfully run the following dewarping examples:

• GitHub - NVIDIA-AI-IOT/deepstream_360_d_smart_parking_application: Describes the full end to end smart parking application that is available with DeepStream 5.0
• dewarper example (C/C++ Sample Apps Source Details — DeepStream 6.1.1 Release documentation)

I have already looked at the the following forum posts:

• Regarding dewarper sample to dewarp 360d cams
• DS4.0 - understanding the dewarp example

[Fiona.Chen]

We will consider it, the document may take some time.

[josh4]

Thanks, that would be much appreciated!

[Fiona.Chen]

We have provided new dewarper sample code and document in GitHub - NVIDIA-AI-IOT/Deepstream-Dewarper-App: This project demonstrate how to infer and track from a 360 videos by using the dewarper plugin.