# Use of First and Third Person Views for Deep Intersection Classification

## TL;DR

This paper presents a unified deep learning framework that combines first and third person views for improved intersection classification using monocular vision, outperforming previous methods with minimal measurements.

## Contribution

The paper introduces a novel combined FPV-TPV deep learning approach for intersection classification, integrating two data perspectives for enhanced accuracy.

## Key findings

- The FPV-TPV scheme outperforms previous methods.
- Minimal FPV/TPV measurements are sufficient for accurate classification.
- Unified framework improves robustness over individual approaches.

## Abstract

We explore the problem of intersection classification using monocular on-board passive vision, with the goal of classifying traffic scenes with respect to road topology. We divide the existing approaches into two broad categories according to the type of input data: (a) first person vision (FPV) approaches, which use an egocentric view sequence as the intersection is passed; and (b) third person vision (TPV) approaches, which use a single view immediately before entering the intersection. The FPV and TPV approaches each have advantages and disadvantages. Therefore, we aim to combine them into a unified deep learning framework. Experimental results show that the proposed FPV-TPV scheme outperforms previous methods and only requires minimal FPV/TPV measurements.