Cost-based Feature Transfer for Vehicle Occupant Classification
This work addresses safety and design needs for vehicle manufacturers by improving occupant classification for features like automatic child locks and airbag suppression, though it appears incremental as it builds on existing transfer learning methods.
The paper tackles occupant detection and classification in vehicles using a single overhead camera, introducing a transfer learning technique to utilize training data from all seats while controlling bias for safety-critical misclassifications, and demonstrates its effectiveness on a challenging dataset with weighted and unweighted classifiers.
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.