MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation

06/14/2019
by   Lorenzo Bertoni, et al.
3

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.

READ FULL TEXT

page 1

page 7

page 8

research
08/25/2020

MonStereo: When Monocular and Stereo Meet at the Tail of 3D Human Localization

Monocular and stereo vision are cost-effective solutions for 3D human lo...
research
09/01/2020

Perceiving Humans: from Monocular 3D Localization to Social Distancing

Perceiving humans in the context of Intelligent Transportation Systems (...
research
09/16/2021

Assessments of model-form uncertainty using Gaussian stochastic weight averaging for fluid-flow regression

We use Gaussian stochastic weight averaging (SWAG) to assess the model-f...
research
08/03/2020

Recognition and 3D Localization of Pedestrian Actions from Monocular Video

Understanding and predicting pedestrian behavior is an important and cha...
research
08/04/2023

Likelihood-ratio-based confidence intervals for neural networks

This paper introduces a first implementation of a novel likelihood-ratio...
research
06/10/2019

Confidence intervals for class prevalences under prior probability shift

Point estimation of class prevalences in the presence of data set shift ...
research
01/31/2017

Deep Multitask Architecture for Integrated 2D and 3D Human Sensing

We propose a deep multitask architecture for fully automatic 2d and 3d h...

Please sign up or login with your details

Forgot password? Click here to reset