CN112489370A - Detection method and system for fatigue driving - Google Patents
Detection method and system for fatigue driving Download PDFInfo
- Publication number
- CN112489370A CN112489370A CN202011316378.4A CN202011316378A CN112489370A CN 112489370 A CN112489370 A CN 112489370A CN 202011316378 A CN202011316378 A CN 202011316378A CN 112489370 A CN112489370 A CN 112489370A
- Authority
- CN
- China
- Prior art keywords
- model
- abnormity judgment
- fatigue driving
- judgment result
- image data
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of traffic safety, in particular to a method and a system for detecting fatigue driving. The method comprises the steps of obtaining image data; processing the image data based on the first abnormity judgment model to obtain a first abnormity judgment result; if the first abnormity judgment result is abnormal, acquiring voice question-answer data; processing the voice question-answer data based on the second abnormity judgment model to obtain a second abnormity judgment result; giving a prompt based on the second abnormality determination result. According to the detection method for the fatigue driving, whether the fatigue driving exists is detected through a multidimensional and interactive method based on a model obtained through big data training, and a prompt is given, so that the driving safety is guaranteed, and the efficiency is high.
Description
Technical Field
The invention relates to the field of traffic safety, in particular to a method and a system for detecting fatigue driving.
Background
The traffic transportation industry in China develops rapidly, accompanying road traffic accidents also show an increasing trend, according to the data of traffic departments, the proportion of the traffic accidents caused by fatigue driving is large, the proportion of the traffic accidents caused by the fatigue driving is larger, the fatigue driving is already used as a main hidden danger of the traffic accidents, people pay attention to the traffic accidents, and a plurality of fatigue driving reminding tools are also provided for the fatigue driving, but the tools have extremely low timeliness and can play a poorer reminding effect.
Disclosure of Invention
The invention provides a method and a system for detecting fatigue driving.
Some embodiments of the invention are implemented as follows:
a method of detecting fatigue driving, comprising:
acquiring image data;
processing the image data based on a first abnormity judgment model to obtain a first abnormity judgment result;
if the first abnormity judgment result is abnormal, acquiring voice question-answer data;
processing the voice question-answer data based on a second abnormity judgment model to obtain a second abnormity judgment result;
giving a prompt based on the second abnormality determination result.
In one embodiment of the invention:
the image data includes driver eye image information.
In one embodiment of the invention:
the first abnormality judgment model is a GNN model.
In one embodiment of the invention:
the second anomaly determination model includes a BERT model.
In one embodiment of the invention:
the features of the voice question-answer data at least comprise voice features and semantic features.
Some embodiments of the present invention further provide a fatigue driving detection system, including:
the image acquisition module is used for acquiring image data;
the first processing module is used for processing the image data based on a first abnormity judgment model to obtain a first abnormity judgment result;
the voice acquisition module is used for acquiring voice question and answer data if the first abnormity judgment result is abnormal;
the second processing module is used for processing the voice question-answer data based on a second abnormity judgment model to obtain a second abnormity judgment result;
and the prompting module is used for giving a prompt based on the second abnormity judgment result.
Some embodiments of the present invention also provide an apparatus for detecting fatigue driving, the apparatus comprising at least one storage medium and at least one processor; the at least one storage medium is configured to store computer instructions; the at least one processor is configured to execute the computer instructions to implement the above-mentioned fatigue driving detection method.
The technical scheme of the invention at least has the following beneficial effects:
according to the detection method for the fatigue driving, whether the fatigue driving exists is detected through a multidimensional and interactive method based on a model obtained through big data training, and a prompt is given, so that the driving safety is guaranteed, and the efficiency is high.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is an exemplary flowchart of a method for detecting fatigue driving according to some embodiments of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.
Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
In some embodiments, detection methods are employed, e.g., based on pulse signals, driving behavior, pupil condition, voice signals, etc., which are primarily based on univariate detection, with insufficient accuracy; in addition, most of the existing detection methods are objective detection and do not interact, and the brought consequence is that once the system detects and judges that the driver is in a fatigue state, the driver can not normally control the vehicle, and the judgment of the driver loses practical significance.
In view of the defect, some embodiments of the present application provide a method and a system for detecting fatigue driving, which detect whether fatigue driving exists through a multidimensional and interactive method.
Referring to fig. 1, there is shown an exemplary flow chart of a method for detecting fatigue driving, comprising the steps of:
step 110, acquiring image data; alternatively, this step may be performed by the image acquisition module.
In some embodiments, the image data may be a picture of the driver, and the driver image may be acquired by providing a camera or a camera in the vehicle when actually performed.
Further, in order to reduce interference in the image and improve the judgment accuracy, the image data comprises the eye image information of the driver. Whether the driver is tired or not is judged according to the condition of eyes, including one or more of eyelids, eyeballs and pupils.
In some embodiments, the first abnormality determination model may be a deep learning model that is made possible by pre-training to determine whether there is fatigue driving through an eye image. Specifically, the eye features can be extracted by acquiring historical face data; and training the deep learning model by using fatigue as a label to obtain a trained model.
Further, the first abnormality determination model is a GNN model. The GNN is a graph neural network, which has better processing effect on the image, and a Graph Convolution Network (GCN) in the graph neural network can be preferably selected. In other specific embodiments, the first abnormality determination model may also be a classifier or the like.
In some embodiments, the first abnormality determination includes safe or possible presence of fatigue driving. When safe, the procedure may be terminated, while when fatigue driving may be present, the subsequent steps are performed.
In some embodiments, the first abnormality determination result is that there is an abnormality, which may be understood as an abnormality of the driver, and therefore further determination of alignment is required. The condition of the driver is further acquired in an interactive mode through a voice question-answer mode. That is, voice question and answer data is acquired in this step.
In some embodiments, the first abnormality determination model may be a Natural Language Processing (NLP) model, such as a transformer, seq2seq, or the like, and determines whether the driver has fatigue driving through semantic analysis of the response content. Further, the second abnormality determination model may include a BERT model.
In some embodiments, the speech characteristics in the speech question-answering data may be determined simultaneously, the speech characteristics may substantially determine the mental condition of the driver, specifically, the speech characteristics may be analyzed by using another deep learning model, and the speech characteristics model and the semantic analysis model may be trained jointly, that is, two model loss functions are added or weighted and added and then trained.
In some embodiments, the second abnormality determination result may include safety or presence of fatigue driving. When safe, the procedure may be terminated, while when fatigue driving may be present, the subsequent steps are performed.
In some embodiments, when the first abnormality judgment model and the second abnormality judgment model both judge that the driver has fatigue driving, the driver is reminded, and the reminding mode may include, but is not limited to, voice reminding, light flashing reminding, and the like. In some embodiments, the determination may also be uploaded or sent to a transportation department for traceability or penalization.
Some embodiments of the present application further provide a fatigue driving detection system, which includes an image acquisition module, a first processing module, a voice acquisition module, a second processing module, and a prompt module.
And the image acquisition module is used for acquiring image data.
And the first processing module is used for processing the image data based on the first abnormity judgment model to obtain a first abnormity judgment result.
And the voice acquisition module is used for acquiring voice question and answer data if the first abnormity judgment result is abnormal.
And the second processing module is used for processing the voice question-answer data based on the second abnormity judgment model to obtain a second abnormity judgment result.
And the prompting module is used for giving a prompt based on the second abnormity judgment result.
In some embodiments of the present application, the image data includes driver eye image information.
In some embodiments of the present application, the first anomaly determination model is a GNN model.
In some embodiments of the present application, the second anomaly determination model comprises a BERT model.
According to the detection method for the fatigue driving, whether the fatigue driving exists is detected through a multidimensional and interactive method based on a model obtained through big data training, and a prompt is given, so that the driving safety is guaranteed, and the efficiency is high.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.
Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present description may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereof. Accordingly, aspects of this description may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present description may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
Claims (10)
1. A method for detecting fatigue driving, comprising:
acquiring image data;
processing the image data based on a first abnormity judgment model to obtain a first abnormity judgment result;
if the first abnormity judgment result is abnormal, acquiring voice question-answer data;
processing the voice question-answer data based on a second abnormity judgment model to obtain a second abnormity judgment result;
giving a prompt based on the second abnormality determination result.
2. The method of claim 1, wherein:
the image data includes driver eye image information.
3. The method of claim 1, wherein:
the first abnormality judgment model is a GNN model.
4. The method of claim 1, wherein:
the second anomaly determination model includes a BERT model.
5. The method of claim 1, wherein:
the features of the voice question-answer data at least comprise voice features and semantic features.
6. A fatigue driving detection system, comprising:
the image acquisition module is used for acquiring image data;
the first processing module is used for processing the image data based on a first abnormity judgment model to obtain a first abnormity judgment result;
the voice acquisition module is used for acquiring voice question and answer data if the first abnormity judgment result is abnormal;
the second processing module is used for processing the voice question-answer data based on a second abnormity judgment model to obtain a second abnormity judgment result;
and the prompting module is used for giving a prompt based on the second abnormity judgment result.
7. The system of claim 6, wherein:
the image data includes driver eye image information.
8. The system of claim 6, wherein:
the first abnormality judgment model is a GNN model.
9. The system of claim 6, wherein:
the second anomaly determination model includes a BERT model.
10. A detection apparatus for fatigue driving, the apparatus comprising at least one storage medium and at least one processor; the at least one storage medium is configured to store computer instructions; the at least one processor is configured to execute the computer instructions to implement the method of detecting fatigue driving of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011316378.4A CN112489370A (en) | 2020-11-20 | 2020-11-20 | Detection method and system for fatigue driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011316378.4A CN112489370A (en) | 2020-11-20 | 2020-11-20 | Detection method and system for fatigue driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112489370A true CN112489370A (en) | 2021-03-12 |
Family
ID=74932824
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011316378.4A Pending CN112489370A (en) | 2020-11-20 | 2020-11-20 | Detection method and system for fatigue driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489370A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2772958A1 (en) * | 1997-12-24 | 1999-06-25 | Sgs Thomson Microelectronics | SECURITY SYSTEM, ESPECIALLY FOR A MOTOR VEHICLE |
| CN103198618A (en) * | 2013-04-13 | 2013-07-10 | 杭州立体世界科技有限公司 | Mobile phone capable of preventing fatigue driving and warning method |
| CN103824421A (en) * | 2014-03-26 | 2014-05-28 | 上海长安汽车工程技术有限公司 | System and method for detecting fatigue driving and alarming to ensure active safety |
| CA2864974A1 (en) * | 2014-12-08 | 2016-06-08 | Mahmud Khan | Child & pet safeguard |
| CN109795319A (en) * | 2019-01-15 | 2019-05-24 | 威马智慧出行科技（上海）有限公司 | Detection and the methods, devices and systems for intervening driver tired driving |
-
2020
- 2020-11-20 CN CN202011316378.4A patent/CN112489370A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2772958A1 (en) * | 1997-12-24 | 1999-06-25 | Sgs Thomson Microelectronics | SECURITY SYSTEM, ESPECIALLY FOR A MOTOR VEHICLE |
| CN103198618A (en) * | 2013-04-13 | 2013-07-10 | 杭州立体世界科技有限公司 | Mobile phone capable of preventing fatigue driving and warning method |
| CN103824421A (en) * | 2014-03-26 | 2014-05-28 | 上海长安汽车工程技术有限公司 | System and method for detecting fatigue driving and alarming to ensure active safety |
| CA2864974A1 (en) * | 2014-12-08 | 2016-06-08 | Mahmud Khan | Child & pet safeguard |
| CN109795319A (en) * | 2019-01-15 | 2019-05-24 | 威马智慧出行科技（上海）有限公司 | Detection and the methods, devices and systems for intervening driver tired driving |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Castro et al. | Cognitive workload measurement and modeling under divided attention. | |
| Gage et al. | Writing performance of students with emotional and/or behavioral disabilities | |
| US8416988B2 (en) | Systems and methods for analyzing facial expressions, identifying intent and transforming images through review of facial expressions | |
| Pinkwart et al. | Toward legal argument instruction with graph grammars and collaborative filtering techniques | |
| CN110143202A (en) | A kind of dangerous driving identification and method for early warning and system | |
| CN114219224B (en) | Teaching quality detection method and system for intelligent classroom | |
| CA2820428A1 (en) | Symbiotic helper | |
| Camp et al. | Reading and spelling in good and poor readers | |
| Briand et al. | Retroactive semantic priming in a lexical decision task | |
| CN115205764B (en) | Online learning concentration monitoring method, system and medium based on machine vision | |
| CN104077568A (en) | High-accuracy driver behavior recognition and monitoring method and system | |
| Alyüz et al. | Towards an emotional engagement model: Can affective states of a learner be automatically detected in a 1: 1 learning scenario? | |
| Haines et al. | Using automated computer vision and machine learning to code facial expressions of affect and arousal: Implications for emotion dysregulation research | |
| CN112581832B (en) | Learning style-based critical driving risk evaluation intervention method and system | |
| Zhou et al. | An evaluation method for visual search stability in urban tunnel entrance and exit sections based on markov chain | |
| CN112489370A (en) | Detection method and system for fatigue driving | |
| Noll et al. | Fostering Reading Comprehension of Learning Tasks with Pictorial Symbols: A Qualitative Study of the Subjective Views and Reading Paths of Children with and without Special Needs. | |
| TAMURA et al. | Unconscious but slowly activated grammatical knowledge of Japanese EFL learners: A case of tough movement | |
| Griffith et al. | Sleep-deprivation effect on human performance: a meta-analysis approach | |
| Alyuz et al. | Towards understanding emotional reactions of driver-passenger dyads in automated driving | |
| Metcalfe et al. | An exploration of the impact of contextual information on the emotion recognition ability of autistic adults | |
| Goulet | Investigation of the cognitive mechanisms of same and different judgments | |
| Kulkarni et al. | Driver drowsiness monitoring system | |
| Barisic et al. | Driver model for Take-Over-Request in autonomous vehicles | |
| AU2021102962A4 (en) | A system for driver behavior analysis based on mood detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for 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: 20210312 |