Model Guided Road Intersection Classification

TL;DR

This paper presents a neural network-based method for classifying road intersections from RGB images, improving accuracy over existing approaches and utilizing a teacher/student training scheme to enhance results.

Contribution

It introduces a novel application of neural networks with a teacher/student training paradigm for intersection classification, validated on KITTI datasets.

Findings

Outperforms current state-of-the-art methods on KITTI datasets

Effective use of teacher/student training scheme

Optimal input configurations identified for best performance

Abstract

Understanding complex scenarios from in-vehicle cameras is essential for safely operating autonomous driving systems in densely populated areas. Among these, intersection areas are one of the most critical as they concentrate a considerable number of traffic accidents and fatalities. Detecting and understanding the scene configuration of these usually crowded areas is then of extreme importance for both autonomous vehicles and modern ADAS aimed at preventing road crashes and increasing the safety of vulnerable road users. This work investigates inter-section classification from RGB images using well-consolidate neural network approaches along with a method to enhance the results based on the teacher/student training paradigm. An extensive experimental activity aimed at identifying the best input configuration and evaluating different network parameters on both the well-known KITTI dataset and the new KITTI-360 sequences shows that our method outperforms current state-of-the-art approaches on a per-frame basis and prove the effectiveness of the proposed learning scheme.