Truck fatigue driving detection method based on image recognition and ADAS device

Abstract

The invention discloses a truck fatigue driving detection method based on image recognition and an ADAS device. The method comprises the following steps: S1, determining the state of a driver based on an image in a cab acquired by a cab monitoring camera, and determining a detection interval time T1 according to the state of the driver; and S2, for each detection interval time T1, executing steps of determining a driver fatigue value FA, wherein the steps of determining the driver fatigue value FA comprises: S21, in a preset detection period T2, obtaining a forward image by a vehicle-mounted forward camera at a set frequency f, S22, based on the forward image, determining a vehicle lateral displacement Di in each t, S23, determining a driver fatigue value FA based on the vehicle lateral displacement Di, and S24, determining a fatigue degree grade according to the driver fatigue value FA.

Description

technical field [0001] The invention relates to the technical field of vehicles, in particular to an image recognition-based fatigue driving detection method for trucks and an ADAS device. Background technique [0002] Fatigue driving is a common phenomenon in freight transportation and can easily lead to extremely serious traffic accidents. At present, regarding fatigue driving monitoring, as long as it is based on the recognition of the driver's physiological characteristics and driving behavior, such as through eye blink recognition, mouth opening and closing degree recognition, etc. On the one hand, this method may require the participation and cooperation of the driver. On the other hand, due to the individual differences of different drivers, it is easy to misjudge and be controlled by the driver, resulting in inaccurate monitoring results. [0003] To this end, various technical solutions have been proposed to improve the detection of fatigue driving. Chinese patent...

AI Technical Summary

Problems solved by technology

[0004] On the one hand, the above-mentioned existing technology needs to install a large number of dense roadside units 1 to realize the detection of fatigue driving, the cost is high and the construction period is long, and it is difficult to achieve a large coverage

On the other hand, it is difficult to obtain the lateral offset of the vehicle relative to the centerline of the lane by using a high-definition camera installed on the roadside unit

Especially for trucks with a high body height, it is difficult to achieve due to reasons such as body occlusion

In addition, it is difficult for the camera installed on the roadside unit to take into account the long detection distance and the large viewing angle. Therefore, it is difficult to use the camera of the roadside unit to detect the lateral offset of the vehicle at different road sections within a large range (for example, on a 500m road). position detection

Images