A Real-Time Fatigue Driving Recognition Method Incorporating Contextual Features and Two Fusion Leve

Abstract

Though experimental results have shown a strong correlation between contextual features and the driver’s fatigue state, contextual features have been applied only offline to evaluate a driver’s fatigue state. This paper identifies three of the most effective contextual features, i.e., continuous driving time, sleep duration time, and current time, to facilitate the real-time (online) recognition of fatigue state. By applying gray relational analysis, the three contextual features, together with the most effective facial and vehicle behavior features, are introduced in a two level fusion structure to improve fatigue driving recognition. In the first level of fusion, labeled the feature-level fusion, three separate multiclass support vector machine (MCSVM) classifiers are used for the three feature sources, i.e., contextual features, driver’s facial features, and vehicle behavior features, to fuse information. These three MCSVM classifiers output probabilities as inputs for the three real-time dynamic basic probability assignments (BPAs) at the second level of fusion, labeled decision-level fusion. These BPAs, and the fusion result of the previous time step, are fused in the decision-level fusion based on the Dempster–Shafer evidence theory. This includes modifying the BPAs to accommodate the decision conflict among the different feature sources. Field experiments show that the proposed recognition method can outperform the single-fatigue feature method and the single-source fusion-based method.

Existing System

User-Specific Classification, Support Vector Machine, Dynamic Bayesian Network.

Proposed System

Based on the need to recognize fatigue driving of drivers reliably and robustly, this study proposes a novel fatigue driving recognition method incorporating contextual features with multi-feature identification and two-level fusion. It has the following characteristics. First, contextual features related to fatigue driving are shown to improve fatigue driving recognition. Second, the proposed GRA-based fatigue feature selection method can efficiently identify the most effective fatigue features, which can enhance the efficiency and reliability of the recognition model. Third, a two-level fusion model consisting of feature-level fusion and decision-level fusion is developed. In the feature-level fusion, the most effective fatigue features are fused based on the proposed MCSVM classifier, which enables a dynamic assignment of BPA for each fatigue feature source. In the decision-level fusion based on the D-SET, the evidence conflict among multiple pieces of evidence is resolved during evidence combination and the reliability of the recognition model is enhanced by modifying the BPA and combining the fatigue state identified at the previous time step.

Architecture

Flowchart of Fatigue Driving Recognition