Detecting Driver Drowsiness as an Anomaly Using LSTM Autoencoders
This work addresses driver safety by detecting drowsiness as an anomaly, but it is incremental as it builds on existing methods with a hybrid approach.
The paper tackles driver drowsiness detection by framing it as an anomaly detection problem using an LSTM autoencoder with ResNet-34 for feature extraction, achieving a detection rate of 0.8740 AUC and showing improvements in specific scenarios.
In this paper, an LSTM autoencoder-based architecture is utilized for drowsiness detection with ResNet-34 as feature extractor. The problem is considered as anomaly detection for a single subject; therefore, only the normal driving representations are learned and it is expected that drowsiness representations, yielding higher reconstruction losses, are to be distinguished according to the knowledge of the network. In our study, the confidence levels of normal and anomaly clips are investigated through the methodology of label assignment such that training performance of LSTM autoencoder and interpretation of anomalies encountered during testing are analyzed under varying confidence rates. Our method is experimented on NTHU-DDD and benchmarked with a state-of-the-art anomaly detection method for driver drowsiness. Results show that the proposed model achieves detection rate of 0.8740 area under curve (AUC) and is able to provide significant improvements on certain scenarios.