FreespaceDetector with a batch of input images

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’m triyng to use the FreespaceDetector in our setup with 2 calibrated cameras.

The underliyng openRoadNet is initialized with a batchSize equal to DW_OPENROADNET_BATCH_SIZE_2.

The freespace module is initialized using the dwFreespaceDetector_initializeFromOpenRoadNet_new function by passing a dwFreespaceDetectorInitParams structure where the cam_new parameter contains the two handles to the cameras.
Then I use the dwFreespaceDetector_setCameraExtrinsics_new function to set the cam2rig transformations for the 2 cameras (in order to retrieve the free area in the vehicle reference frame).

The code stop when calling the dwFreespaceDetector_detectBoundary function with the error:
DW_INVALID_ARGUMENT: Freespace detector: number of frames must be equal to model batch size

How can I pass a batch of two images to the FreespaceDetector?

Thank you in advance!

Hi, @m.giardino

We will check internally and get back to you here. Thanks.

Dear @m.giardino,
dwFreespaceDetector_detectBoundary API support only batch size 1.