CN104715235A - Train driver state recognizing and alarming method - Google Patents
Train driver state recognizing and alarming method Download PDFInfo
- Publication number
- CN104715235A CN104715235A CN201510067500.1A CN201510067500A CN104715235A CN 104715235 A CN104715235 A CN 104715235A CN 201510067500 A CN201510067500 A CN 201510067500A CN 104715235 A CN104715235 A CN 104715235A
- Authority
- CN
- China
- Prior art keywords
- mouth
- data
- driver
- eye
- limbs
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
A train driver state recognizing and alarming method is characterized by comprising the steps of electric start, system autodiagnosis, image inputting and preprocessing, facial area detecting, eye area detecting, binaryzation operation and connected domain operation, data interchanging and end. According to image inputting and preprocessing, serial port data information is reset, the data collected by a camera is received and preprocessed, the preprocessed image automatically generates relevant data, and the relevant data serve as the basis of a recognition algorithm; the binaryzation operation and the connected domain operation are performed on an eye area and a mouth area, and on the basis of the binaryzation operation, the judgment analysis on eyes, mouth shapes and limbs is achieved by adopting the human eye, mouth shape and limb recognition algorithm and using the Gaussian distribution; the system is provided with serial port communication data, a vehicle-mounted ATP and an LKJ2000 to achieve data interchanging. A serial port comprises a vehicle-mounted ATP interface, an LKJ2000 interface and a debug serial port body. Compared with the prior art, the driver state can be automatically analyzed and recognized, the mental pressure and the labor intensity of a driver are reduced, the driver can have more energy to drive a train, the driving safety can be further guaranteed, and the transport efficiency is improved.
Description
Technical field
The present invention relates to a kind of railway signal technology field, particularly a kind of train operator's state recognition alarm method.
Background technology
Railway, as the main artery of national economy, national important infrastructure and the popular vehicles, has vital role in China's economic social development.Come into operation for increasing EMU and subway train, specification train operator driving behavior, raising traffic safety and conevying efficiency are seemed most important, at present, in field of track traffic, that mainly adopt for train operating safety is train operation monitoring and recording device LKJ2000 and onboard system ATP.These equipment are mainly reflected in train operation unprotected sex supervision and protection, can not accomplish the prevention to driver's unprotected sex and diagnosis.
Summary of the invention
The object of invention is to provide and a kind ofly identifies the potential danger of driver in driving conditions and judge early warning, makes train before the generation of secured premise and minimizing accident, under topic, to improve train operator's state recognition alarm method of conevying efficiency.
The present invention is achieved in that and it is characterized in that:
(1), power on beginning;
(2), system autodiagnosis, to hardware interface circuit and software module diagnosis, comprise system process normal condition;
(3), image input and pre-service, system initialization, initialization recognizer and hardware-related data, reset serial data information, receive camera to collect data and also carry out pre-service, automatically generate related data and as the foundation of recognizer through pretreated image;
(4), face area detect, because driver's face location is roughly fixing, therefore first fix face area position, reduce computing time;
(5), ocular detects;
(6), fix the operation of threshold region binaryzation, and carry out connected domain operation, on the basis of binaryzation operation, adopt human eye, the shape of the mouth as one speaks and limbs recognizer, complete the discriminatory analysis to human eye, the shape of the mouth as one speaks and limbs;
(7), eye and mouth feature detect, and on the basis that face area detects, completes the detection to eye, the shape of the mouth as one speaks and limbs region, adopts the method for template matches to complete detection to face and mouth area;
(8), with other system carrying out data interaction, when not detecting that driver has abnormal conditions to occur, carrying out data interaction with other system; When detecting that driver's state has abnormal conditions to occur, exported by audio alert prompting, and make a record and video monitoring preservation, enter step images input and pre-service.
The device of train operator's state recognition alarm method comprises video camera, A/D converter (TVP5146), processor (TMS320DM3730), storer and external interface module, and video camera is connected with A/D converter, and A/D converter is connected with processor; Inputting video data is delivered to A/D converter and is completed and change the A/D of incoming video signal by video camera, then the identification to human eye, the shape of the mouth as one speaks and limbs state is completed through processor identification module, the dsp chip of external interface module completes the logic control controlling alarm light and stereo set, the dsp chip of external interface module completes and stores with the information interaction of train monitoring system and video data, provides USB interface to download to complete video.
The present invention is used for carrying out identification to the facial state in train operator's driving operation and limbs form and judges, especially in real time output is monitored to eye state and shape of the mouth as one speaks state, there is provided and analyze and report to the police and carry out data interaction with other system, jointly complete the constraint of driver's manipulative behavior lack of standardization, compared with prior art, automatically can carry out analysis to driver's state to identify, decrease stress and the labour intensity of driver, driver is made to have more energy to drive train, further guarantee traffic safety, improves conevying efficiency.
Accompanying drawing explanation
Below in conjunction with accompanying drawing, the present invention will be further described:
Fig. 1 is the process flow diagram of train operator's state recognition alarm method;
Fig. 2 is the structural representation of train operator's state recognition warning device.
Embodiment
As shown in Figure 1, this train operator's state recognition alarm method is: power on beginning; System autodiagnosis, comprises hardware interface circuit and software module diagnosis, system process normal condition; Image input and pre-service, system initialization, initialization recognizer and hardware-related data; Reset serial data information; Receive camera collect data and carry out pre-service; Automatically related data is generated and as the foundation of recognizer through pretreated image; Face area detects, and because driver's face location is roughly fixing, therefore first fixes face area position, reduces computing time; Ocular detects; On the basis that face area detects, complete the detection to eye, the shape of the mouth as one speaks and limbs region, adopt the method for template matches to complete detection to face and mouth area; To ocular and the operation of mouth area binaryzation, and carry out connected domain operation.On the basis of binaryzation operation, adopt human eye, the shape of the mouth as one speaks and limbs recognizer, utilize Gaussian distribution to complete discriminatory analysis to eye, the shape of the mouth as one speaks and limbs.When not detecting that driver has abnormal conditions to occur, entering and resetting serial data information; When detecting that driver's state has abnormal conditions to occur, exported by audio alert prompting, and make a record and video monitoring preservation; This Operation system setting serial port communication data, vehicle-mounted ATP and LKJ2000 carry out data interaction; Terminate.Described serial ports comprises vehicle-mounted ATP interface, LKJ2000 interface, debug serial port.
As shown in Figure 2, the device of train operator's state recognition alarm method comprises video camera, A/D converter (TVP5146), processor (TMS320DM3730), storer and external interface module, video camera is connected with A/D converter, and A/D converter is connected with processor; Inputting video data is delivered to A/D converter and is completed and change the A/D of incoming video signal by video camera, then the identification to human eye, the shape of the mouth as one speaks and limbs state is completed through processor identification module, the dsp chip of external interface module completes the logic control controlling alarm light and stereo set, the dsp chip of external interface module completes and stores with the information interaction of train monitoring system and video data, provides USB interface to download to complete video.
Camera identifies face, the shape of the mouth as one speaks and limbs state, is mainly divided into four steps, comprises face detection, eye and oral area location, eye, oral area and the identification of limbs state and the detection of fatigue state.Infrared pick-up head gathers cab video information, adopt the interface incoming video signal of NBC, the vision signal collected is carried out A/D conversion by analog-to-digital conversion chip, eye is completed by dsp processor, oral area and limbs state recognition, if detect that in official hour human eye is in closure state or detects that in official hour the closure time of human eye is greater than setting threshold value always, and the performance of oral area limbs feature is abnormal, then start sound equipment and the light warning of this device, and relevant information is passed to train monitoring system, as taked associative operation not yet within the warning stipulated time, then send train emergency mobile forces stop signal.
Due to the obvious characteristic of people when fatigue, to comprise of short duration doze, frequent blinking, limb activity abnormal etc., so be standard and oral area and limbs state to the differentiation of tired driver degree according to the ratio that the time of eyes closed state accounts for a certain special time.
Claims (2)
1. train operator's state recognition alarm method, is characterized in that:
(1), power on beginning;
(2), system autodiagnosis, to hardware interface circuit and software module diagnosis, comprise system process normal condition;
(3), image input and pre-service, system initialization, initialization recognizer and hardware-related data, reset serial data information, receive camera to collect data and also carry out pre-service, automatically generate related data and as the foundation of recognizer through pretreated image;
(4), face area detect, because driver's face location is roughly fixing, therefore first fix face area position, reduce computing time;
(5), ocular detects;
(6), the operation of fixing threshold region binaryzation, and carry out connected domain operation, on the basis of binaryzation operation, adopt human eye, the shape of the mouth as one speaks and limbs recognizer, utilize Gaussian distribution to complete discriminatory analysis to eye, the shape of the mouth as one speaks and limbs;
(7), eye and mouth feature detect, and on the basis that face area detects, completes the detection to eye, the shape of the mouth as one speaks and limbs region, adopts the method for template matches to complete detection to face and mouth area;
(8), with other system carrying out data interaction, when not detecting that driver has abnormal conditions to occur, carrying out data interaction with other system; When detecting that driver's state has abnormal conditions to occur, exported by audio alert prompting, and make a record and video monitoring preservation, enter step images input and pre-service.
2. train operator's state recognition alarm method according to claim 1, it is characterized in that: device used comprises video camera, A/D converter (TVP5146), processor (TMS320DM3730), storer and external interface module, video camera is connected with A/D converter, A/D converter is connected with processor, inputting video data is delivered to A/D converter and is completed and change the A/D of incoming video signal by video camera, then complete human eye through processor identification module, the identification of the shape of the mouth as one speaks and limbs state, the dsp chip of external interface module completes the logic control controlling alarm light and stereo set, the dsp chip of external interface module completes and stores with the information interaction of train monitoring system and video data, USB interface is provided.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510067500.1A CN104715235A (en) | 2015-02-10 | 2015-02-10 | Train driver state recognizing and alarming method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510067500.1A CN104715235A (en) | 2015-02-10 | 2015-02-10 | Train driver state recognizing and alarming method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104715235A true CN104715235A (en) | 2015-06-17 |
Family
ID=53414546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510067500.1A Pending CN104715235A (en) | 2015-02-10 | 2015-02-10 | Train driver state recognizing and alarming method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104715235A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295600A (en) * | 2016-08-18 | 2017-01-04 | 宁波傲视智绘光电科技有限公司 | Driver status real-time detection method and device |
| CN107729870A (en) * | 2017-01-24 | 2018-02-23 | 问众智能信息科技（北京）有限公司 | The method and apparatus of in-car safety monitoring based on computer vision |
| CN108297895A (en) * | 2018-02-02 | 2018-07-20 | 孟静 | Rail transit safety prompt system |
| CN108569315A (en) * | 2017-03-13 | 2018-09-25 | 卡斯柯信号有限公司 | A kind of tramcar driver management system |
| CN111582167A (en) * | 2020-05-08 | 2020-08-25 | 上海振华重工(集团)股份有限公司 | Container crane driver operation safety identification method, system and computing equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120089321A1 (en) * | 2010-10-11 | 2012-04-12 | Hyundai Motor Company | System and method for alarming front impact danger coupled with driver viewing direction and vehicle using the same |
| CN103400471A (en) * | 2013-08-12 | 2013-11-20 | 电子科技大学 | Detecting system and detecting method for fatigue driving of driver |
| CN104240446A (en) * | 2014-09-26 | 2014-12-24 | 长春工业大学 | Fatigue driving warning system on basis of human face recognition |
-
2015
- 2015-02-10 CN CN201510067500.1A patent/CN104715235A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120089321A1 (en) * | 2010-10-11 | 2012-04-12 | Hyundai Motor Company | System and method for alarming front impact danger coupled with driver viewing direction and vehicle using the same |
| CN103400471A (en) * | 2013-08-12 | 2013-11-20 | 电子科技大学 | Detecting system and detecting method for fatigue driving of driver |
| CN104240446A (en) * | 2014-09-26 | 2014-12-24 | 长春工业大学 | Fatigue driving warning system on basis of human face recognition |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106295600A (en) * | 2016-08-18 | 2017-01-04 | 宁波傲视智绘光电科技有限公司 | Driver status real-time detection method and device |
| CN107729870A (en) * | 2017-01-24 | 2018-02-23 | 问众智能信息科技（北京）有限公司 | The method and apparatus of in-car safety monitoring based on computer vision |
| CN108569315A (en) * | 2017-03-13 | 2018-09-25 | 卡斯柯信号有限公司 | A kind of tramcar driver management system |
| CN108297895A (en) * | 2018-02-02 | 2018-07-20 | 孟静 | Rail transit safety prompt system |
| CN111582167A (en) * | 2020-05-08 | 2020-08-25 | 上海振华重工(集团)股份有限公司 | Container crane driver operation safety identification method, system and computing equipment |
| CN111582167B (en) * | 2020-05-08 | 2024-03-01 | 上海振华重工(集团)股份有限公司 | Container crane driver operation safety identification method, system and computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104715235A (en) | Train driver state recognizing and alarming method | |
| CN104408878B (en) | Vehicle fleet fatigue driving early warning monitoring system and method | |
| CN101470951B (en) | Vehicle security drive monitoring system | |
| CN101593425B (en) | Machine vision based fatigue driving monitoring method and system | |
| CN102263937B (en) | Driver's driving behavior monitoring device and monitoring method based on video detection | |
| CN202130312U (en) | Driver fatigue driving monitoring device | |
| CN104240446A (en) | Fatigue driving warning system on basis of human face recognition | |
| CN101599207A (en) | A kind of fatigue driving detection device and automobile | |
| CN103824420A (en) | Fatigue driving identification system based on heart rate variability non-contact measuring | |
| WO2021023064A1 (en) | Safe driving monitoring system and method for train | |
| CN102426757A (en) | Safety driving monitoring system based on mode identification and method thereof | |
| CN109367479A (en) | A kind of fatigue driving monitoring method and device | |
| CN103315754B (en) | A kind of fatigue detection method and device | |
| CN103268686A (en) | Anti-theft system based on face recognition | |
| CN102930693A (en) | Early warning system and method for safe driving | |
| CN108154101A (en) | The fatigue driving detecting system and method for a kind of multi-parameter fusion | |
| CN104068868A (en) | Method and device for monitoring driver fatigue on basis of machine vision | |
| CN103198618A (en) | Mobile phone capable of preventing fatigue driving and warning method | |
| CN109094458A (en) | The control method of safe driving of vehicle and control device for safe driving of vehicle | |
| CN108937923A (en) | A kind of real-time driving fatigue monitoring system based on EEG signals, electro-ocular signal and electromyography signal | |
| CN106408877A (en) | Rail traffic driver fatigue state monitoring method | |
| CN112754095A (en) | Intelligent safety helmet based on multiple physiological signal monitoring and control method thereof | |
| CN103824421B (en) | Active safety fatigue driving detection caution system | |
| CN203025911U (en) | Fatigue driving detection and identification system based on human face recognition | |
| CN109308467A (en) | Traffic accident prior-warning device and method for early warning based on machine learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150617 |