Combining DriveNet and LandMarkPerception on a single CPP file

Please provide the following info (check/uncheck the boxes after creating this topic):
Software Version
DRIVE OS Linux 5.2.6
DRIVE OS Linux 5.2.0
DRIVE OS Linux 5.2.0 and DriveWorks 3.5
NVIDIA DRIVE™ Software 10.0 (Linux)
NVIDIA DRIVE™ Software 9.0 (Linux)
other DRIVE OS version

Target Operating System

Hardware Platform
NVIDIA DRIVE™ AGX Xavier DevKit (E3550)
NVIDIA DRIVE™ AGX Pegasus DevKit (E3550)

SDK Manager Version

Host Machine Version
native Ubuntu 18.04


I would like to know or receive suggestions how to make an application that can access the same camera and send frame info to the DriveNet DNN and LandMarkPerception DNN in parallel. The goal is to determine vehicle and lane markings using one single camera and binary

Is there any guidance how to use the DriveWork API to accomplish this?

Thanks in advance

Dear @jpvans,
DW does not sample to show processing 2 DNNs. But to process in parallel, you need to use iGPU/dGPU in parallel. Each thread is responsible for to process a DNN on its own GPU(use cudaSetDevice to select iGPU or dGPU). Each threads can have copy of input frame and send to CUDA over seperate Imagestreamer and for DNN processing. Fina results can be combined for each frame and display it using GL.