Road Scene Graph: A Semantic Graph-Based Scene Representation Dataset for Intelligent Vehicles

TL;DR

This paper introduces the Road Scene Graph dataset and a scene graph representation for intelligent vehicles, enabling better organization and exploitation of semantic road scene data using graph neural networks.

Contribution

It proposes a novel road scene graph dataset and a topological graph representation that includes objects and their relationships, optimized for GCN processing.

Findings

Effective scene graph representation for road scenes

Successful application of GCNs on the dataset

Improved understanding of semantic relationships in road scenes

Abstract

Rich semantic information extraction plays a vital role on next-generation intelligent vehicles. Currently there is great amount of research focusing on fundamental applications such as 6D pose detection, road scene semantic segmentation, etc. And this provides us a great opportunity to think about how shall these data be organized and exploited. In this paper we propose road scene graph,a special scene-graph for intelligent vehicles. Different to classical data representation, this graph provides not only object proposals but also their pair-wise relationships. By organizing them in a topological graph, these data are explainable, fully-connected, and could be easily processed by GCNs (Graph Convolutional Networks). Here we apply scene graph on roads using our Road Scene Graph dataset, including the basic graph prediction model. This work also includes experimental evaluations using the proposed model.