I've always wondered... if Lidar + Cameras is always making the right decision, you should theoretically be able to take the output of the Lidar + Cameras model and use it as training data for a Camera only model.
I've always wondered... if Lidar + Cameras is always making the right decision, you should theoretically be able to take the output of the Lidar + Cameras model and use it as training data for a Camera only model.
That's exactly what Tesla is doing with their validation vehicles, the ones with Lidar towers on top. They establish the "ground truth" from Lidar and use that to train and/or test the vision model. Presumably more "test", since they've most often been seen in Robotaxi service expansion areas shortly before fleet deployment.
Is that exactly true though? Can you give a reference for that?
I don't have a specific source, no. I think it was mentioned in one of their presentation a few years back, that they use various techniques for "ground truth" for vision training, among those was time series (depth change over time should be continuous etc) and iirc also "external" sources for depth data, like LiDAR. And their validation cars equipped with LiDAR towers are definitely being seen everywhere they are rolling out their Robotaxi services.
are definitely being seen everywhere they are rolling out their Robotaxi services
So...nowhere?
> you should theoretically be able to take the output of the Lidar + Cameras model and use it as training data for a Camera only model.
Why should you be able to do that exactly? Human vision is frequently tricked by it's lack of depth data.
"Exactly" is impossible: there are multiple Lidar samples that would map to the same camera sample. But what training would do is build a model that could infer the most likely Lidar representation from a camera representation. There would still be cases where the most likely Lidar for a camera input isn't a useful/good representation of reality, e.g. a scene with very high dynamic range.
No, I don't think that will be successful. Consider a day where the temperature and humidity is just right to make tail pipe exhaust form dense fog clouds. That will be opaque or nearly so to a camera, transparent to a radar, and I would assume something in between to a lidar. Multi-modal sensor fusion is always going to be more reliable at classifying some kinds of challenging scene segments. It doesn't take long to imagine many other scenarios where fusing the returns of multiple sensors is going to greatly increase classification accuracy.
Sure, but those models would never have online access to information only provided in lidar data…
No, but if you run a shadow or offline camera-only model in parallel with a camera + LIDAR model, you can (1) measure how much worse the camera-only model is so you can decide when (if ever) it's safe enough to stop installing LIDAR, and (2) look at the specific inputs for which the models diverge and focus on improving the camera-only model in those situations.