Sight line-based driver attention detection method

A detection method and driver's technology, applied in the field of computer vision, can solve problems such as high cost, high hardware dependence, and difficult installation and use of the system, and achieve good robustness, good real-time performance, and simple configuration

Active Publication Date: 2018-03-20
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF13 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Sight line-based driver attention detection method
  • Sight line-based driver attention detection method
  • Sight line-based driver attention detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0034] In the present invention, a CCD camera and a near-infrared camera are used to acquire daytime and nighttime images respectively, facial appearance and shape information are used for training, and facial features are acquired; then rigid and non-rigid head movements are decoupled and driving Then, use the SIFT feature to train the SVM model to detect whether the driver wears sunglasses, if wearing sunglasses, use the head posture to represent the driver's attention direction, otherwise use the driver's line of sight direction as the driver's attention direction, The driver's gaze direction is solved by the inherent geometric relationship in the simplified 3D eyeball model; finally, the driver's attention state is determined by combining the driver's attention direction and the division position of the car. The method process of the presen...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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'...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06T17/00
CPCG06T17/00G06V40/165G06V40/171G06V20/597G06V10/462G06F18/2411
Inventor 程洪谢非甘路涛赵洋郝家胜
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap