Cost-based Feature Transfer for Vehicle Occupant Classification

TL;DR

This paper introduces a transfer learning framework for occupant detection and classification in vehicles using a single overhead camera, enhancing safety features like child locks and airbag control.

Contribution

It proposes a novel transfer learning approach that leverages data from all seats while controlling bias, improving occupant classification accuracy.

Findings

Effective transfer process demonstrated on a challenging dataset

Improved classification performance with weighted and unweighted classifiers

Framework applicable to all passenger seats using a single camera

Abstract

Knowledge of human presence and interaction in a vehicle is of growing interest to vehicle manufacturers for design and safety purposes. We present a framework to perform the tasks of occupant detection and occupant classification for automatic child locks and airbag suppression. It operates for all passenger seats, using a single overhead camera. A transfer learning technique is introduced to make full use of training data from all seats whilst still maintaining some control over the bias, necessary for a system designed to penalize certain misclassifications more than others. An evaluation is performed on a challenging dataset with both weighted and unweighted classifiers, demonstrating the effectiveness of the transfer process.