There are a ton of videos available of vehicles (for ex : https://www.youtube.com/watch?v=vSLqtBs2RbA), but i believe you are searching labeled video datasets
mortal coyote
There are a ton of videos available of vehicles (for ex : https://www.youtube.com/watch?v=vSLqtBs2RbA), but i believe you are searching labeled video datasets
One solution can be to train model on some vehicle detection dataset (images) than use that for inference, by treating videos as image/frame collection
