I am trying to use the LaneGraph with Lane net as input. However when the dwLanedetections from
LaneNet are received the array which should contain the worldpoints (dwLaneMarking.worldpoints) always
filled with zeroes. This causes the lane graph to fail.
We have tried to use an instance of a calibrated camera with a rig file to backproject from pixelspace to world space. We used the following code as found in this thread (https://devtalk.nvidia.com/default/topic/1043877/driveworks/how-to-transform-points-from-image-space-to-world-space-/post/5302776/#5302776) until step 10.
Our question is how do we transform this ray into a worldpoint?