VWise: A novel benchmark for evaluating scene classification for vehicular applications

TL;DR

VWise is a new Latin American-focused benchmark dataset for scene and road-type classification in vehicular applications, addressing geographical bias in existing datasets.

Contribution

It introduces VWise, a comprehensive dataset with over 520 annotated videos from Latin America, and provides baseline evaluations of state-of-the-art models.

Findings

Achieved over 84% accuracy with baseline models

Collected diverse urban and rural Latin American scenes

Highlights the need for region-specific datasets in vehicular AI

Abstract

Current datasets for vehicular applications are mostly collected in North America or Europe. Models trained or evaluated on these datasets might suffer from geographical bias when deployed in other regions. Specifically, for scene classification, a highway in a Latin American country differs drastically from an Autobahn, for example, both in design and maintenance levels. We propose VWise, a novel benchmark for road-type classification and scene classification tasks, in addition to tasks focused on external contexts related to vehicular applications in LatAm. We collected over 520 video clips covering diverse urban and rural environments across Latin American countries, annotated with six classes of road types. We also evaluated several state-of-the-art classification models in baseline experiments, obtaining over 84% accuracy. With this dataset, we aim to enhance research on vehicular tasks in Latin America.