Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data

TL;DR

This paper introduces a geo-context aware visualization system that integrates deep learning model performance with geospatial data, enabling detailed analysis of autonomous driving models across city-wide and street-level environments.

Contribution

It presents a novel visualization platform that combines geospatial visualization with autonomous driving model analysis, facilitating comprehensive model evaluation and comparison.

Findings

System effectively visualizes model performance with geospatial context.

Enables comparison of multiple DL models at different geographic scales.

Domain experts find the system useful for autonomous driving research.

Abstract

Vision-based deep learning (DL) methods have made great progress in learning autonomous driving models from large-scale crowd-sourced video datasets. They are trained to predict instantaneous driving behaviors from video data captured by on-vehicle cameras. In this paper, we develop a geo-context aware visualization system for the study of Autonomous Driving Model (ADM) predictions together with large-scale ADM video data. The visual study is seamlessly integrated with the geographical environment by combining DL model performance with geospatial visualization techniques. Model performance measures can be studied together with a set of geospatial attributes over map views. Users can also discover and compare prediction behaviors of multiple DL models in both city-wide and street-level analysis, together with road images and video contents. Therefore, the system provides a new visual exploration platform for DL model designers in autonomous driving. Use cases and domain expert evaluation show the utility and effectiveness of the visualization system.