RSG-Net: Towards Rich Sematic Relationship Prediction for Intelligent Vehicle in Complex Environments

TL;DR

This paper introduces RSG-Net, a graph convolutional network that predicts semantic relationships among objects in complex driving environments, enhancing scene understanding for autonomous vehicles.

Contribution

The paper presents RSG-Net, a novel graph convolutional network for predicting semantic relationships, enabling richer scene understanding in autonomous driving scenarios.

Findings

Efficient prediction of semantic relationships among objects.

RSG-Net outperforms baseline models on the Road Scene Graph dataset.

Enhanced environment understanding for self-driving vehicles.

Abstract

Behavioral and semantic relationships play a vital role on intelligent self-driving vehicles and ADAS systems. Different from other research focused on trajectory, position, and bounding boxes, relationship data provides a human understandable description of the object's behavior, and it could describe an object's past and future status in an amazingly brief way. Therefore it is a fundamental method for tasks such as risk detection, environment understanding, and decision making. In this paper, we propose RSG-Net (Road Scene Graph Net): a graph convolutional network designed to predict potential semantic relationships from object proposals, and produces a graph-structured result, called "Road Scene Graph". The experimental results indicate that this network, trained on Road Scene Graph dataset, could efficiently predict potential semantic relationships among objects around the ego-vehicle.