search

fundamentalvision / BEVFormer

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
https://arxiv.org/abs/2203.17270
Apache License 2.0
3.4k stars 550 forks source link

Velocity estimation #183

Open ms-kumar opened 1 year ago

ms-kumar commented 1 year ago

HI, @all I have a general doubt regarding velocity, How velocity is used in 3d object detection?

htian01 commented 1 year ago

For Motion prediction and then for planning. See UniAD to have a general sense of the entire system.

ms-kumar commented 1 year ago

@htian01 yes u r right, but in bevformer velocity is calculate as (vx, vy), is this the ego vehicle velocity? and it is like added one features in model?