1
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 1 year has passed since last update.

【3D Object Detection】CenterPoint

Last updated at Posted at 2023-10-21

概要

  • Anchor-baseの物体検出を行うと3次元上だと回転方向(yaw angle)の影響を受けやすい。そこでCenter-baseのモデルを提案
    image.png

  • Backbone -> 3Dのpoint cloudをBEV(=Map View)に変換出来る物であれば何でも問題なさそう。

  • 1st stage Head -> それぞれのBEV Gridにclass毎のCenterの確率と、center offset(delta_x,delta_y)、高さ(h)、サイズ(width,length,hight)、yaw angle(sin,cos)を推定する。

  • 2nd stage Head -> 1st stageの結果の差分を推定する。やらなくても良い。

  • Assinment -> Ground TruthのBounding Box Centerが一致するBEV Gridの推定結果をLossにAssignする。
    image.png

参考文献

Center-based 3D Object Detection and Tracking

1
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
1
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?