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

Suphanut Jamonnak, Ye Zhao, Xinyi Huang, Md Amiruzzaman

External link (DOI)
View presentation:2021-10-28T15:00:00ZGMT-0600Change your timezone on the schedule page
2021-10-28T15:00:00Z
Exemplar figure, described by caption below
Vision-based deep learning 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. We develop a geo-context aware visualization system for the study of Autonomous Driving Model predictions together with large-scale ADM video data. The visual study is seamlessly integrated with the geographical environment by combining deep learning model performance with geospatial visualization techniques. The system provides a new visual exploration platform for DL model designers in autonomous driving.
Fast forward

Direct link to video on YouTube: https://youtu.be/Y8bN-6G3Vko

Abstract

Vision-based deep learning (DL) methods have achieved success 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 geo-spatial 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.