MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation

We tackle the fundamentally ill-posed problem of 3D human localization from monocular RGB images. Driven by the limitation of neural networks outputting point estimates, we address the ambiguity in the task with a new neural network predicting confidence intervals through a loss function based on the Laplace distribution. Our architecture is a light-weight feed-forward neural network which predicts the 3D coordinates given 2D human pose. The design is particularly well suited for small training data and cross-dataset generalization. Our experiments show that (i) we outperform state-of-the art results on KITTI and nuScenes datasets, (ii) even outperform stereo for far-away pedestrians, and (iii) estimate meaningful confidence intervals. We further share insights on our model of uncertainty in case of limited observation and out-of-distribution samples.


Présenté à:
ArXiv
Année
Jun 07 2019
Mots-clefs:
Laboratoires:




 Notice créée le 2019-06-07, modifiée le 2019-06-15

Fichiers:
Télécharger le document
PDF

Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)