Vehicle face recognition method based on deep learning

A technology of face recognition and deep learning, applied in the field of in-vehicle face recognition based on deep learning, can solve problems such as lack of too much research, lack of judging methods for whether the driver is driving illegally, etc., and achieve the effect of reducing the possibility

Active Publication Date: 2018-08-24
TIANJIN UNIV
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, although my country's vehicle-mounted cameras have developed to a certain extent, they are mainly concentrated in the fields of vehicle speed testing, target tracking, pedestrian detec

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
  • Vehicle face recognition method based on deep learning
  • Vehicle face recognition method based on deep learning
  • Vehicle face recognition method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The vehicle-mounted face recognition method based on deep learning of the present invention will be described in detail below in conjunction with the embodiments and accompanying drawings.

[0032] Such as figure 1 As shown, the vehicle-mounted face recognition method based on deep learning of the present invention comprises the following steps:

[0033] 1) Acquire images and build a driver data set, including:

[0034] Use python-based network picture acquisition scripts to acquire different driver images through the Internet, make labels on the images, label the image content in detail, and then summarize them as a driver data set. The image content includes: the driver’s normal driving, Looking down at the phone, looking around, chatting and driving tired.

[0035] 2) Build a model, including:

[0036] (1) In order to better distinguish the driver's behavior, the present invention extracts visual features and semantic features. Through the convolutional neural ne...

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 present invention provides a vehicle face recognition method based on deep learning. The method comprises the steps of: obtaining an image, and constructing a driver data set; constructing a model: extracting visual features and semantic features, and forming a feature processing model; training the feature processing model; optimizing an experiment result according to a test result, and transmitting the optimized feature processing model to a total control terminal; and installing a warning lamp and a camera on a vehicle, and uploading a driver's operation condition to the total control terminal in real time, wherein the total control terminal determines whether the drive breaks driving rules or not according to the optimized feature processing model, when the drive breaks driving rules, the total control terminal emits signals to excite the warning lamp to prompt the driver to perform legal driving. Through real-time analysis of face change, the vehicle face recognition method extracts face features to detect whether there is violation operation or not and perform analysis and comparison with a data set, once behaviors of violating laws and rules are discovered, such as fatigue driving and call answering, watching of a mobile phone, alarm can be automatically emitted to timely stop the drivers' illegal behaviors so as to reduce the possibility of generation of traffic accidents.

Description

technical field [0001] The invention relates to a face recognition method. In particular, it relates to a deep learning-based vehicle face recognition method. Background technique [0002] With the rapid development of information acquisition and information processing technology, computer vision, that is, how to use computer technology to efficiently and accurately obtain relevant information from environmental images or videos, and then analyze, judge and make decisions about things and phenomena in the objective world , has become a very important research topic. With the rapid development of deep learning, computer vision has developed rapidly in recent years, and deep convolutional neural networks have played a very important role in the research and development of computer vision. [0003] With the rapid development of computer vision, the development momentum of face recognition technology is good, and the application of face recognition is becoming more and more ex...

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
IPC IPC(8): G06K9/00
CPCG06V40/168G06V20/597Y02T10/40
Inventor 冀中贺二路庞彦伟
Owner TIANJIN UNIV
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