Online Monitoring for Neural Network Based Monocular Pedestrian Pose Estimation

by   Arjun Gupta, et al.

Several autonomy pipelines now have core components that rely on deep learning approaches. While these approaches work well in nominal conditions, they tend to have unexpected and severe failure modes that create concerns when used in safety-critical applications, including self-driving cars. There are several works that aim to characterize the robustness of networks offline, but currently there is a lack of tools to monitor the correctness of network outputs online during operation. We investigate the problem of online output monitoring for neural networks that estimate 3D human shapes and poses from images. Our first contribution is to present and evaluate model-based and learning-based monitors for a human-pose-and-shape reconstruction network, and assess their ability to predict the output loss for a given test input. As a second contribution, we introduce an Adversarially-Trained Online Monitor ( ATOM ) that learns how to effectively predict losses from data. ATOM dominates model-based baselines and can detect bad outputs, leading to substantial improvements in human pose output quality. Our final contribution is an extensive experimental evaluation that shows that discarding outputs flagged as incorrect by ATOM improves the average error by 12.5 by 126.5


page 1

page 3

page 7


Learning to Refine Human Pose Estimation

Multi-person pose estimation in images and videos is an important yet ch...

Learning to Estimate 3D Human Pose from Point Cloud

3D pose estimation is a challenging problem in computer vision. Most of ...

PoseNet3D: Unsupervised 3D Human Shape and Pose Estimation

Recovering 3D human pose from 2D joints is a highly unconstrained proble...

Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation

A central challenge in human pose estimation, as well as in many other m...

PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation

Human pose and shape (HPS) estimation methods achieve remarkable results...

CoreUI: Interactive Core Training System with 3D Human Shape

We present an interactive core training system for core training using a...

Monitoring and Diagnosability of Perception Systems

Perception is a critical component of high-integrity applications of rob...

Please sign up or login with your details

Forgot password? Click here to reset