Multivariate Probabilistic Monocular 3D Object Detection

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 54
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorShi, Xuepengko
dc.contributor.authorChen, Zhixiangko
dc.contributor.authorKim, Tae-Kyunko
dc.identifier.citationIEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp.4270 - 4279-
dc.description.abstractIn autonomous driving, monocular 3D object detection is an important but challenging task. Towards accurate monocular 3D object detection, some recent methods recover the distance of objects from the physical height and visual height of objects. Such decomposition framework can introduce explicit constraints on the distance prediction, thus improving its accuracy and robustness. However, the inaccurate physical height and visual height prediction still may exacerbate the inaccuracy of the distance prediction. In this paper, we improve the framework by multivariate probabilistic modeling. We explicitly model the joint probability distribution of the physical height and visual height. This is achieved by learning a full covariance matrix of the physical height and visual height during training, with the guide of a multivariate likelihood. Such explicit joint probability distribution modeling not only leads to robust distance prediction when both the predicted physical height and visual height are inaccurate, but also brings learned covariance matrices with expected behaviors. The experimental results on the challenging Waymo Open and KITTI datasets show the effectiveness of our framework1.-
dc.publisherCVF and IEEE Computer Society-
dc.titleMultivariate Probabilistic Monocular 3D Object Detection-
dc.citation.publicationnameIEEE/CVF Winter Conference on Applications of Computer Vision (WACV)-
dc.identifier.conferencelocationWaikoloa, Hawaii-
dc.contributor.localauthorKim, Tae-Kyun-
dc.contributor.nonIdAuthorShi, Xuepeng-
dc.contributor.nonIdAuthorChen, Zhixiang-
Appears in Collection
CS-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.


  • mendeley


rss_1.0 rss_2.0 atom_1.0