Affine transformation/warp on bbox

[bcao]

@twangbarang

t I guess NPP API is also capable of that. Any idea how?

RIght, you can refer https://docs.nvidia.com/cuda/npp/group__affine__transform.html

@twangbarang

Additionally I would probably need to not only change the rect_params fields in the probe callbacks but also some buffers I guess?

Yeah, in gstnvinfer.cpp , instead of calling NvBufSurfTransform inside convert_batch_and_push_to_input_thread, need to call affine transformation