Fatigue Driving Evaluation Method Based on Artificial Neural Network and Evidence Theory

Abstract

The invention discloses a fatigue driving evaluation method based on an artificial neural network and evidence theory, comprising the following steps: step 1, collecting fatigue characteristic data samples; step 2, constructing an artificial neural network, and using the sample data to determine artificial neural network parameters; step 3, Real-time calculation of fatigue feature parameters; Step 4, feature-level fusion based on artificial neural network; Step 5, decision-level fusion based on D‑S evidence theory; Step 6, driving state identification based on decision rules. The present invention overcomes the limitations of the fatigue driving evaluation method based on a single category feature or a single information source feature, reduces its false detection rate and missed detection rate, improves the reliability and accuracy of fatigue driving evaluation, and is suitable for high accuracy and robustness. Strong real-time evaluation of driving fatigue occasions.

Description

technical field [0001] The invention relates to a fatigue driving evaluation method based on artificial neural network and evidence theory, and belongs to the technical field of driver fatigue driving evaluation. Background technique [0002] Fatigue driving detection and evaluation has become a research hotspot in the field of automotive active safety. The non-contact fatigue driving detection method based on physical sensors has attracted extensive attention in theoretical research and application fields in recent years. However, most of the existing fatigue driving evaluation methods only focus on a single fatigue characteristic of a certain aspect of the driver, such as frequent blinking and yawning, abnormal head rotation, or abnormal driving status of the vehicle. With the development of information fusion technology, although many evaluation methods have begun to consider the fusion of multiple fatigue features, most of them only fuse a few fatigue features of the dri...

AI Technical Summary

Problems solved by technology

However, most of the existing fatigue driving evaluation methods only focus on a single fatigue characteristic of a driver, such as frequent blinking and yawning, abnormal head rotation, or abnormal driving conditions, etc.

With the development of information fusion technology, although many evaluation methods have begun to consider the fusion of multiple fatigue features, most of them only integrate a few fatigue features of the driver's face, and for vehicle behavior features that indirectly reflect whether the driver is tired, such as The abnormal deviation of the vehicle due to fatigue driving, the abnormal steering wheel rotation and the abnormal change of vehicle speed are ignored, which leads to the unsatisfactory evaluation effect of these current methods, which may easily lead to misjudgments and missed evaluations.

At the same time, fatigue driving is a very complex physiological phenomenon. There are many causes, complex symptoms, and difficulties in detection and evaluation. These have brought great challenges to traditional fatigue driving evaluation methods.

Images