CN115620267A - Driver driving behavior analysis method, system, equipment and storage medium - Google Patents
Driver driving behavior analysis method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN115620267A CN115620267A CN202211325987.5A CN202211325987A CN115620267A CN 115620267 A CN115620267 A CN 115620267A CN 202211325987 A CN202211325987 A CN 202211325987A CN 115620267 A CN115620267 A CN 115620267A
- Authority
- CN
- China
- Prior art keywords
- driver
- driving
- image data
- driving behaviors
- behaviors
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method, a system, equipment and a storage medium for analyzing driving behaviors of a driver, wherein the method comprises the steps of collecting head image data and limb action image data of the driver during vehicle driving, identifying various driving behaviors of the driver, grading various driving behaviors of the driver, calculating grades of various driving behaviors according to weights to obtain comprehensive grades, and classifying the driving behaviors of the driver according to the comprehensive grades; the head image data and the limb action image data of the driver during vehicle driving are collected, various driving behaviors of the driver are identified according to the head image data and the limb action image data, the identification accuracy of the driving behaviors of the driver can be effectively improved, meanwhile, the various driving behaviors of the driver are scored, the scores of the various driving behaviors are calculated according to the weight, comprehensive scores are obtained, the driving behaviors of the driver are classified according to the comprehensive scores, and the effect of classifying the driving behaviors of the driver can be achieved.
Description
Technical Field
The invention relates to the technical field of driving behaviors, in particular to a method, a system and equipment for analyzing a driving behavior of a driver and a storage medium.
Background
With the annual rise of the quantity of all automobile owners, a problem which cannot be ignored is associated: a novice who just takes a driving license has more wrong driving behaviors due to lack of sufficient road driving experience, if the wrong driving behaviors cannot be corrected in time, the safety of the novice can be endangered, the safety of public transportation can be adversely affected, and the novice becomes a genuine 'road killer', so that the driving behaviors of a driver need to be analyzed, and the driving problems of the driver can be effectively known through analyzing the driving behaviors of the driver, so that the potential safety hazard is reduced.
Disclosure of Invention
In view of this, the invention provides a method, a system, a device and a storage medium for analyzing driving behaviors of a driver, which can solve the defects that the prior art has low recognition accuracy and cannot effectively classify the driving behaviors of the driver.
The technical scheme of the invention is realized as follows:
a driver driving behavior analysis method specifically comprises the following steps:
acquiring head image data and limb action image data of a driver during vehicle driving;
recognizing various driving behaviors of a driver according to the collected head image data and the collected limb action image data;
scoring various driving behaviors of the driver, and calculating the scores of the various driving behaviors according to the weight to obtain a comprehensive score;
and classifying the driving behaviors of the driver according to the comprehensive scores, and classifying the normal driving behaviors, the risky driving behaviors and the dangerous driving behaviors, so that the driving behaviors of the driver are analyzed.
As a further alternative of the driver driving behavior analysis method, the driver's various driving behaviors include a head-down driving, a one-handed steering wheel driving, a phone call driving, and a fatigue driving.
As a further alternative of the driver driving behavior analysis method, the recognizing various driving behaviors of the driver according to the collected head image data and limb movement image data specifically includes:
analyzing according to the acquired head image data to obtain the head lowering amplitude when the driver lowers the head and the head lowering time kept when the driver lowers the head, and identifying whether the driver drives with the head down or not;
analyzing according to the collected limb action image data to obtain the time of the driver holding the steering wheel by one hand, and identifying whether the driver drives by holding the steering wheel by one hand or not;
analyzing according to the collected limb action image data to obtain the hand-lifting action of the driver and the time for keeping the hand-lifting action, and identifying whether the driver calls for driving or not;
and analyzing according to the acquired head image data to obtain the eye closing times and the eye closing time of the driver during driving, and identifying whether the driver is in fatigue driving.
As a further alternative of the driver driving behavior analysis method, the collected head image data is analyzed to obtain the eye closing times and the eye closing time of the driver during driving, and whether the driver is tired is identified specifically includes:
identifying an image of an eye range in the head image, and separating the image of the eye range to obtain eye image data;
and analyzing the eye image data to obtain the eye closing times and the eye closing time.
As a further alternative of the driver driving behavior analysis method, the scoring of various driving behaviors of the driver and the calculating of the scores of the various driving behaviors according to the weights to obtain a comprehensive score specifically includes:
presetting the proportion of various driving behaviors of a driver;
and calculating according to the proportion of various driving behaviors of the driver and various driving behaviors of the driver to obtain a comprehensive score.
As a further alternative to the driver driving behavior analysis method, the method further comprises:
and carrying out corresponding early warning on the driver according to the classification result.
A driver driving behavior analysis system, comprising:
the camera module is used for acquiring head image data and limb action image data of a driver during vehicle driving;
the recognition module is used for recognizing various driving behaviors of a driver according to the collected head image data and the collected limb action image data;
the scoring module is used for scoring various driving behaviors of the driver and calculating the scores of the various driving behaviors according to the weight to obtain a comprehensive score;
and the classification module is used for classifying the driving behaviors of the driver according to the comprehensive scores and classifying the normal driving behaviors, the risky driving behaviors and the dangerous driving behaviors.
A computing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of any of the driver driving behavior analysis methods described above when executing the computer program.
A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor, carries out the steps of any of the above-described driver driving behavior analysis methods.
The invention has the beneficial effects that: the head image data and the limb action image data of the driver during vehicle driving are collected, various driving behaviors of the driver are identified according to the head image data and the limb action image data, the identification accuracy of the driving behaviors of the driver can be effectively improved, meanwhile, the various driving behaviors of the driver are scored, the scores of the various driving behaviors are calculated according to the weight, comprehensive scores are obtained, the driving behaviors of the driver are classified according to the comprehensive scores, and the effect of classifying the driving behaviors of the driver can be achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for analyzing driving behavior of a driver according to the present invention;
fig. 2 is a schematic diagram of a driver driving behavior analysis system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. 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.
Referring to fig. 1-2, a method for analyzing driving behavior of a driver specifically includes:
acquiring head image data and limb action image data of a driver during vehicle driving;
recognizing various driving behaviors of a driver according to the collected head image data and the collected limb action image data;
scoring various driving behaviors of the driver, and calculating the scores of the various driving behaviors according to the weight to obtain a comprehensive score;
and classifying the driving behaviors of the driver according to the comprehensive scores, and classifying the normal driving behaviors, the risky driving behaviors and the dangerous driving behaviors, so that the driving behaviors of the driver are analyzed.
In the embodiment, the head image data and the limb action image data of the driver during vehicle driving are collected, various driving behaviors of the driver are identified according to the head image data and the limb action image data, the identification accuracy of the driving behaviors of the driver can be effectively improved, meanwhile, the various driving behaviors of the driver are scored, the scores of the various driving behaviors are calculated according to the weight, comprehensive scores are obtained, the driving behaviors of the driver are classified according to the comprehensive scores, and the effect of classifying the driving behaviors of the driver can be achieved.
The method comprises the following steps that head image data and limb movement image data of a driver during vehicle driving are collected through a camera device; in addition, different driving behaviors have different scoring ratios, and are classified into normal driving behaviors when the comprehensive score is higher than a first threshold, classified into risky driving behaviors when the comprehensive score is lower than the first threshold and higher than a second threshold, and classified into dangerous driving behaviors when the comprehensive score is lower than the second threshold.
Preferably, the driver's various driving behaviors include a low head driving, a one-handed steering wheel driving, a phone call driving, and a fatigue driving.
In the embodiment in the city, the driver holds the steering wheel with one hand to drive the vehicle, and the driver drives the vehicle with low head, makes a call and drives fatigue to drive the vehicle with danger.
Preferably, the recognizing various driving behaviors of the driver according to the acquired head image data and the acquired limb movement image data specifically includes:
analyzing according to the acquired head image data to obtain the head lowering amplitude when the driver lowers the head and the head lowering time kept when the driver lowers the head, and identifying whether the driver drives with the head lowered;
analyzing according to the collected limb action image data to obtain the time of the driver holding the steering wheel by one hand, and identifying whether the driver drives by holding the steering wheel by one hand or not;
analyzing according to the collected limb action image data to obtain the hand-lifting action of the driver and the time for keeping the hand-lifting action, and identifying whether the driver calls for driving or not;
and analyzing according to the acquired head image data to obtain the eye closing times and the eye closing time of the driver during driving, and identifying whether the driver is in fatigue driving.
In the embodiment, when the head-down amplitude when the driver heads down and the head-down time kept when the driver heads down exceed the third threshold, the driver is judged to drive in a head-down mode, when the time that the driver holds the steering wheel by one hand exceeds the fourth threshold, the driver is judged to drive by one hand, when the time that the driver raises the hand and holds the hand exceeds the fifth threshold, the driver is judged to drive in a telephone, when the eye closing times and the eye closing time when the driver drives exceed the sixth threshold, the driver is judged to drive in a fatigue mode, different features are extracted through different images for recognition, and the recognition accuracy can be improved.
Preferably, the acquired head image data is analyzed to obtain the eye closing times and the eye closing time of the driver during driving, and whether the driver is tired is identified, which specifically includes:
identifying an image of an eye range in the head image, and separating the image of the eye range to obtain eye image data;
and analyzing the eye image data to obtain the eye closing times and the eye closing time.
In the embodiment, the head image is segmented to segment the eye region image, so that redundant data can be clarified, and the recognition efficiency can be improved.
Preferably, the scoring of various driving behaviors of the driver and the calculating of the scores of the various driving behaviors according to the weight to obtain the comprehensive score specifically includes:
presetting the proportion of various driving behaviors of a driver;
and calculating according to the proportion of various driving behaviors of the driver and various driving behaviors of the driver to obtain a comprehensive score.
Preferably, the method further comprises:
and carrying out corresponding early warning on the driver according to the classification result.
In the embodiment, different classification results need to send different early warning information to the driver, so that the driver is effectively reminded and corrected; it should be noted that when the driving behavior of the driver is classified as normal driving behavior, the driver does not need to send early warning information, when the driving behavior of the driver is classified as risky driving behavior, the driver sends reminding information and correction scheme information, and when the driving behavior of the driver is classified as dangerous driving behavior, the driver sends correction scheme information and punishment information to the driver.
A driver driving behavior analysis system, comprising:
the camera module is used for acquiring head image data and limb action image data of a driver during vehicle driving;
the recognition module is used for recognizing various driving behaviors of a driver according to the collected head image data and the collected limb action image data;
the scoring module is used for scoring various driving behaviors of the driver and calculating the scores of the various driving behaviors according to the weight to obtain a comprehensive score;
and the classification module is used for classifying the driving behaviors of the driver according to the comprehensive scores and classifying the normal driving behaviors, the risky driving behaviors and the dangerous driving behaviors.
In the embodiment, the head image data and the limb action image data of the driver during vehicle driving are collected, various driving behaviors of the driver are identified according to the head image data and the limb action image data, the identification accuracy of the driving behaviors of the driver can be effectively improved, meanwhile, the various driving behaviors of the driver are scored, the scores of the various driving behaviors are calculated according to the weight, comprehensive scores are obtained, the driving behaviors of the driver are classified according to the comprehensive scores, and the effect of classifying the driving behaviors of the driver can be achieved.
The method comprises the following steps that head image data and limb movement image data of a driver during vehicle driving are collected through a camera device; in addition, different driving behaviors have different scoring ratios, and are classified into normal driving behaviors when the comprehensive score is higher than a first threshold, classified into risky driving behaviors when the comprehensive score is lower than the first threshold and higher than a second threshold, and classified into dangerous driving behaviors when the comprehensive score is lower than the second threshold.
A computing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of any of the driver driving behavior analysis methods described above when executing the computer program.
A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of any of the above-mentioned driver driving behavior analysis methods.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A driver driving behavior analysis method is characterized by specifically comprising the following steps:
acquiring head image data and limb action image data of a driver during vehicle driving;
recognizing various driving behaviors of a driver according to the collected head image data and the collected limb action image data;
scoring various driving behaviors of the driver, and calculating the scores of the various driving behaviors according to the weight to obtain a comprehensive score;
and classifying the driving behaviors of the driver according to the comprehensive scores, and classifying the normal driving behaviors, the risky driving behaviors and the dangerous driving behaviors, so that the driving behaviors of the driver are analyzed.
2. The driver driving behavior analysis method according to claim 1, wherein the driver's various driving behaviors include a low head driving, a one-handed steering wheel driving, a telephone call driving, and a fatigue driving.
3. The method for analyzing the driving behavior of the driver as claimed in claim 2, wherein the identifying of the driving behavior of the driver based on the collected head image data and the collected limb movement image data specifically comprises:
analyzing according to the acquired head image data to obtain the head lowering amplitude when the driver lowers the head and the head lowering time kept when the driver lowers the head, and identifying whether the driver drives with the head lowered;
analyzing according to the collected limb action image data to obtain the time of the driver holding the steering wheel by one hand, and identifying whether the driver drives by holding the steering wheel by one hand or not;
analyzing according to the acquired limb action image data to obtain the hand-lifting action of the driver and the time for keeping the hand-lifting action, and identifying whether the driver makes a call for driving;
and analyzing according to the acquired head image data to obtain the eye closing times and the eye closing time of the driver during driving, and identifying whether the driver is in fatigue driving.
4. The method for analyzing the driving behavior of the driver as claimed in claim 3, wherein the step of analyzing the collected head image data to obtain the eye closing times and the eye closing time of the driver during driving to identify whether the driver is tired comprises:
recognizing an image of an eye range in the head image, and separating the image of the eye range to obtain eye image data;
and analyzing the eye image data to obtain the eye closing times and the eye closing time.
5. The method for analyzing the driving behavior of the driver as claimed in claim 4, wherein the scoring of the driving behaviors of the driver and the calculating of the scores of the driving behaviors according to the weights to obtain the comprehensive score specifically comprises:
presetting the proportion of various driving behaviors of a driver;
and calculating according to the proportion of various driving behaviors of the driver and various driving behaviors of the driver to obtain a comprehensive score.
6. The driver driving behavior analysis method of claim 5, further comprising:
and carrying out corresponding early warning on the driver according to the classification result.
7. A driver driving behavior analysis system, comprising:
the camera module is used for acquiring head image data and limb action image data of a driver during vehicle driving;
the recognition module is used for recognizing various driving behaviors of a driver according to the collected head image data and the collected limb action image data;
the scoring module is used for scoring various driving behaviors of the driver and calculating the scores of the various driving behaviors according to the weight to obtain a comprehensive score;
and the classification module is used for classifying the driving behaviors of the driver according to the comprehensive scores and classifying the normal driving behaviors, the risky driving behaviors and the dangerous driving behaviors.
8. A computing device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the driver driving behavior analysis method of any one of claims 1-7 when executing the computer program.
9. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the driver driving behavior analysis method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211325987.5A CN115620267A (en) | 2022-10-27 | 2022-10-27 | Driver driving behavior analysis method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211325987.5A CN115620267A (en) | 2022-10-27 | 2022-10-27 | Driver driving behavior analysis method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115620267A true CN115620267A (en) | 2023-01-17 |
Family
ID=84865282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211325987.5A Pending CN115620267A (en) | 2022-10-27 | 2022-10-27 | Driver driving behavior analysis method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115620267A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112896175A (en) * | 2021-01-13 | 2021-06-04 | 重庆市索美智能交通通讯服务有限公司 | Driving behavior analysis system and method |
| US20210290134A1 (en) * | 2020-03-18 | 2021-09-23 | Ford Global Technologies, Llc | Systems and methods for detecting drowsiness in a driver of a vehicle |
| CN114758326A (en) * | 2022-03-31 | 2022-07-15 | 深圳市正威智能有限公司 | Real-time traffic post working behavior state detection system |
-
2022
- 2022-10-27 CN CN202211325987.5A patent/CN115620267A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210290134A1 (en) * | 2020-03-18 | 2021-09-23 | Ford Global Technologies, Llc | Systems and methods for detecting drowsiness in a driver of a vehicle |
| CN112896175A (en) * | 2021-01-13 | 2021-06-04 | 重庆市索美智能交通通讯服务有限公司 | Driving behavior analysis system and method |
| CN114758326A (en) * | 2022-03-31 | 2022-07-15 | 深圳市正威智能有限公司 | Real-time traffic post working behavior state detection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110532976B (en) | Fatigue driving detection method and system based on machine learning and multi-feature fusion | |
| CN110766912B (en) | Driving early warning method, device and computer readable storage medium | |
| CN111191545B (en) | Real-time monitoring and analyzing system and method for driver behaviors | |
| CN105303829A (en) | Vehicle driver emotion recognition method and device | |
| CN105956548A (en) | Driver fatigue state detection method and device | |
| CN108682158A (en) | Video analysis and scoring method for early warning and system | |
| CN111814762A (en) | Helmet wearing detection method and device | |
| CN110751381A (en) | Road rage vehicle risk assessment and prevention and control method | |
| CN108682157A (en) | Video analysis and method for early warning and system | |
| CN111526311B (en) | Method and system for judging driving user behavior, computer equipment and storage medium | |
| CN103927548A (en) | Novel vehicle collision avoiding brake behavior detection method | |
| CN112164228A (en) | Helmet-free behavior detection method for driving electric vehicle, electronic device and storage medium | |
| CN112277957B (en) | Early warning method and system for driver distraction correction and storage medium | |
| CN104966059A (en) | Method for detecting phoning behavior of driver during driving based on intelligent monitoring system | |
| CN111860201A (en) | Image recognition and bridge monitoring combined ramp heavy vehicle recognition method and system | |
| CN113408364B (en) | Temporary license plate recognition method, system, device and storage medium | |
| CN112550306A (en) | Vehicle driving assistance system, vehicle including the same, and corresponding method and medium | |
| CN115620267A (en) | Driver driving behavior analysis method, system, equipment and storage medium | |
| CN113920310A (en) | Method and device for detecting steering wheel hands off | |
| CN114841483A (en) | Safety monitoring method and system for logistics freight vehicle | |
| CN110705416B (en) | Safe driving early warning method and system based on driver face image modeling | |
| CN111016913B (en) | Driver state control system and method based on image information | |
| CN109583410B (en) | Driving safety early warning system based on image recognition technology | |
| CN111341106B (en) | Traffic early warning method, device and equipment | |
| CN110287838B (en) | Method and system for monitoring behaviors of driving and playing mobile phone |
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 |