DeepAI AI Chat
Log In Sign Up

Street-Map Based Validation of Semantic Segmentation in Autonomous Driving

by   Laura von Rueden, et al.

Artificial intelligence for autonomous driving must meet strict requirements on safety and robustness, which motivates the thorough validation of learned models. However, current validation approaches mostly require ground truth data and are thus both cost-intensive and limited in their applicability. We propose to overcome these limitations by a model agnostic validation using a-priori knowledge from street maps. In particular, we show how to validate semantic segmentation masks and demonstrate the potential of our approach using OpenStreetMap. We introduce validation metrics that indicate false positive or negative road segments. Besides the validation approach, we present a method to correct the vehicle's GPS position so that a more accurate localization can be used for the street-map based validation. Lastly, we present quantitative results on the Cityscapes dataset indicating that our validation approach can indeed uncover errors in semantic segmentation masks.


page 1

page 2

page 4

page 5

page 8


Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation

Data-driven sensor interpretation in autonomous driving can lead to high...

Towards automatic extraction and validation of on-street parking spaces using park-out events data

This article proposes two different approaches to automatically create a...

The Ethical Dilemma when (not) Setting up Cost-based Decision Rules in Semantic Segmentation

Neural networks for semantic segmentation can be seen as statistical mod...

Affordance Learning In Direct Perception for Autonomous Driving

Recent development in autonomous driving involves high-level computer vi...

Exploring OpenStreetMap Availability for Driving Environment Understanding

With the great achievement of artificial intelligence, vehicle technolog...

Label Efficient Visual Abstractions for Autonomous Driving

It is well known that semantic segmentation can be used as an effective ...

Single Level Feature-to-Feature Forecasting with Deformable Convolutions

Future anticipation is of vital importance in autonomous driving and oth...