FDAN: Fuzzy deep attention networks for driver behavior recognition

Abstract

Driver behavior is an essential factor affecting traffic safety, and driver behavior monitoring systems (DMSs) are widely exploited in intelligent transportation systems to reduce the risk of traffic accidents. However, understanding driver behavior is challenging because of the uncertainty of real driving scenarios. Most of the existing methods use deterministic models, which suffer from data uncertainty, for recognizing driver behaviors. In this paper, the fuzzy deep attention network (FDAN) method is proposed to improve driver behavior recognition. FDAN integrates fuzzy logic and an attention mechanism into deep neural networks, which enhances the representation ability of the model and reduces the uncertainty of the data. The attention mechanism with a lightweight squeeze-and-excitation block is embedded in the deep learning model for adaptively refining features. A DMS is designed, and the distracted driver dataset from the real scene is built. Experimental results confirm the proposed method performs better than the existing methods.