Sight line-based driver attention detection method

Abstract

The invention discloses a sight line-based driver attention detection method. The sight-based driver attention detection method comprises the five steps of human face 2D key point detection, 3D face feature extraction, sunglasses detection, sight line estimation and attention region detection. The sight line is the best mode for expressing the attention state of a driver. However, when the driverwears the sunglasses, the sight line estimation cannot be carried out. In this way, whether the driver wears the sunglasses or not is detected through a computer vision correlation algorithm. When thedriver wears the sunglasses, the head direction of the driver is adopted to replace the direction of the sight line as the attention direction. According to the invention, the attention state of thedriver is detected through an automatic monitoring system, so that the occurrence of traffic accidents due to distracted driving can be effectively reduced. The good robustness is achieved for different illumination conditions and driver characteristics. Meanwhile, the method is good in real-time performance, and the warning can be timely sent out at the dangerous moment.

Description

technical field [0001] The invention belongs to the technical field of computer vision, in particular to a line-of-sight-based driver's attention detection method, which is applied to the driver's attention detection scene. Background technique [0002] At present, distracted driving is the main factor leading to traffic accidents. According to research conducted by the National Highway Traffic Safety Administration (NHTSA) and VTTI, 70% of traffic accidents involve driver distraction. Driver distracted driving is behavior that diverts a driver's attention from driving to any other activity. For example, common behaviors such as texting, talking on the phone, eating, and operating GPS can all lead to distracted driving. Studies have shown that driving while performing other tasks (texting, calling, etc.) will increase the driver's cognitive load, and this phenomenon is becoming more frequent, which leads to an increasing frequency of distracted driving . When the driver'...

AI Technical Summary

Problems solved by technology

However, the cost of promoting this system on commercial vehicles is very high and the dependence on the necessary hardware is very high. Additional hardware facilities need to be installed on the vehicle, which greatly restricts the portability of the system.

Therefore, such systems are difficult to install and use on ordinary cars

Images