A device for detecting a driver's safe driving state

Abstract

The invention relates to a device for detecting safety driving states of a driver. The device comprises line-of-sight capturing equipment, more than one vehicle-mounted forward scene camera and a computer, wherein the line-of-sight capturing equipment is used for detecting the current line-of-sight direction of the driver in real time; the vehicle-mounted forward scene cameras are used for collecting a scene image signal in a forward road when a vehicle travels; the computer is used for processing the collected current scene image signal according to a visual attention calculation model, obtaining the expected attention distribution of the driver under the current road scene, integrating and analyzing the real-time detected current line-of-sight direction of the driver and the calculated expected attention distribution of the driver, and judging if the driver is in the normal driving state and if the driver can timely make a proper response to the sudden road traffic accidents. The device has the advantages that the principle is simple, the implementation is easy, the real driving state of the driver can be directly reflected, the driving safety is improved, and the like.

Description

technical field [0001] The invention mainly relates to the field of vehicle active safety design, in particular to a device for detecting a driver's safe driving state. Background technique [0002] With the development of the automobile industry, automobiles have increasingly become an important part of social production and daily life; at the same time, automobile safety issues have gradually become the focus of attention. According to statistics, about 75% of road traffic accidents are caused by human error, that is, due to the driver's personal factors. Specifically, it includes the driver's inaccurate estimation of the vehicle's operating environment, the driver's reaction lag, and so on. Therefore, detecting whether the driver's driving state is safe through technical means can effectively improve the safety of road traffic. [0003] At present, the detection technology for the driver's safe driving state can be divided into three categories: the first category is ba...

AI Technical Summary

Problems solved by technology

To sum up, this kind of method infers the driver's safe driving state through the driver's fatigue state, and there are three problems in the following aspects: First, it is an indirect detection method itself, and the effect is not reliable

The third is to infer whether the driver's driving state is safe from the fatigue state, and the timeliness is difficult to guarantee

The disadvantage of this type of method is that it can only be judged when a dangerous traffic event is about to take place, and it is difficult to provide a clear and objective method for distinguishing between normal traffic events and abnormal traffic events, such as normal traffic events. overtaking behavior and abnormal lane deviation behavior

Although this type of method can directly judge whether the driver can respond to sudden stimulation, this type of method also has the following disadvantages: the one is that it is easy to disperse the driver's attention in doing so itself.

The second is that the specific mode of stimulation itself has produced additional stimulation to the driver's psychological activities, increasing the driver's burden

The existing detection technology of the driver's safe driving state is difficult to detect the second type of unsafe driving state

Images