Query regarding Depth perception

[user54392]

Please provide the following info (tick the boxes after creating this topic):
Software Version
DRIVE OS 6.0.6
[*] DRIVE OS 6.0.5
DRIVE OS 6.0.4 (rev. 1)
DRIVE OS 6.0.4 SDK
other

Target Operating System
Linux
QNX
other

Hardware Platform
[*] DRIVE AGX Orin Developer Kit (940-63710-0010-300)
DRIVE AGX Orin Developer Kit (940-63710-0010-200)
DRIVE AGX Orin Developer Kit (940-63710-0010-100)
DRIVE AGX Orin Developer Kit (940-63710-0010-D00)
DRIVE AGX Orin Developer Kit (940-63710-0010-C00)
DRIVE AGX Orin Developer Kit (not sure its number)
other

SDK Manager Version
1.9.3.10904
[*] other

Host Machine Version
[*] native Ubuntu Linux 20.04 Host installed with SDK Manager
native Ubuntu Linux 20.04 Host installed with DRIVE OS Docker Containers
native Ubuntu Linux 18.04 Host installed with DRIVE OS Docker Containers
other

I need to create a vehicle-based monocular depth perception system that uses inputs from just one camera. Please outline the measures I must take to implement this solution. Please advise if we need to create the model ourselves or if NVIDIA Drive offers built-in, pre-trained models for this solution.

[SivaRamaKrishnaNV]

Dear @user54392,
DNNs are not part of DRIVE OS + Driveworks release. However, we have DW DNN framework, that allows you integrate any model into DW framework. You need to prepare your model and use TensorRT_Optimization tool to get DW compatible TRT model.