> Jason stared at his image in the griddle's stainless steel surface. The image of a large, freckled man wearing a black t-shirt and green plaid boxers. It was like he'd stumbled upon an abandoned photo shoot, or a bizarre prop out of an old TV series. A figment of his imagination from a nightmare he'd had once where he was alone in a house, free to do anything. Aah. That was it. He'd been sitting in the dark eating his microwaved pizza, watching some sort of porno, and thinking about strange little things he'd seen when he was growing up. When he was younger, things were simply that much stranger. Everything he'd seen, for that matter. It was weird how that worked. He'd stare into space, the fog of drugs would clear, and some unseen object would immediately become a mirage. The pattern was always the same, though. He would fixate on some tiny detail, and a few seconds later that detail would become a goddamn spectacle. Even the stranger things in his life took on that shape. The porno had images in it that meant nothing, in their own way. And he was always left to ponder what sort of symbolism might be hidden beneath
> but it seems like training actually uses radar data to help calibrate vision
They seem to use radar solely to automatically label data for training.
In the given example though where according to the vision system smog interrupted the persistence of the label for the leading car, I wonder if the use of radar data to persist the label is strictly necessary.
A car disappeared then reappeared in the data, why not just tween the bounding box over time and assume the car had always been there, like, if it looked the same when it reappears or something. An extra sensor just for labelling data seems silly.
https://edition.cnn.com/2021/08/02/politics/dc-metropolitan-...