Convolutional Neural Network-Based In-Vehicle Occupant Detection and Classification Method using Second Strategic Highway Research Program Cabin Images

Abstract

This paper describes an approach for automatic detection and localization of drivers and passengers in automobiles using in-cabin images. We used a convolutional neural network (CNN) framework and conducted experiments based on the Faster R-CNN and Cascade R-CNN detectors. Training and evaluation were performed using the Second Strategic Highway Research Program (SHRP 2) naturalistic dataset. In SHRP 2, the cabin images have been blurred to maintain privacy. After detecting occupants inside the vehicle, the system classifies each occupant as driver, front-seat passenger, or back-seat passenger. For one SHRP 2 test set, the system detected occupants with an accuracy of 94.5%. Those occupants were correctly classified as front-seat passenger with an accuracy of 97.3%, as driver with 99.5% accuracy, and as back-seat passenger with 94.3% accuracy. The system performed slightly better for daytime images than for nighttime images. Unlike previous work, this method is capable of presence classification and location prediction of occupants. By fine-tuning the object detection model, there is also significant improvement in detection accuracy as compared with pretrained models. The study also provides a fully annotated dataset of in-cabin images. This work is expected to facilitate research involving interactions between drivers and passengers, particularly related to driver attention and safety.