CN111932716B - Driving behavior detection method and device - Google Patents
Driving behavior detection method and device Download PDFInfo
- Publication number
- CN111932716B CN111932716B CN202010818758.1A CN202010818758A CN111932716B CN 111932716 B CN111932716 B CN 111932716B CN 202010818758 A CN202010818758 A CN 202010818758A CN 111932716 B CN111932716 B CN 111932716B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- coordinate system
- acceleration value
- quaternion
- accelerometer
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P15/00—Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
- G01P15/18—Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration in two or more dimensions
Abstract
The invention provides a driving behavior detection method and a driving behavior detection device, which comprise the following steps: obtaining a static acceleration value; acquiring a starting acceleration value; obtaining a rotation quaternion q according to the starting acceleration numerical value and a vehicle coordinate system; acquiring a motion acceleration value; acquiring a driving acceleration value according to the motion acceleration value and the static acceleration value; converting the running acceleration value of the vehicle into a vehicle running acceleration value of a vehicle coordinate system by rotating the quaternion q; and obtaining driving behavior analysis data according to the vehicle travelling acceleration value. The invention has the beneficial effects that: the acceleration sensor has the advantages that the acceleration in the vehicle direction can be acquired under the condition that the sensor equipment is installed in any posture, the utilization value of the acceleration sensor in the field of driving behavior detection is improved, and the acceleration sensor is more convenient both in the problems of equipment installation and deployment and in the aspects of data utilization and analysis.
Description
Technical Field
The invention relates to the technical field of intelligent driving detection, in particular to a driving behavior detection method and device.
Background
As a main vehicle in modern society, automobiles play a very important role in the transportation of people. Although the automobile brings convenience to people in mobile life, the life and property of people are threatened by severe driving environment, traffic jam, lack of good vehicle maintenance and the like. According to the statistics of the world health organization, traffic accidents have become one of ten death causes in the world. Traffic safety is an important issue in many countries today.
Research has shown that most traffic accidents are caused by human factors, such as abnormal driving behavior of the driver. Therefore, it is necessary to detect the driving behavior of the driver to remind the driver or report to the information platform for early warning. Real-time driving behavior detection can effectively improve driving safety. Typical abnormal driving behaviors include sudden braking, sudden acceleration, sudden turning, rollover, serpentine driving and the like. These accidents are caused by drunk driving, fatigue driving of the driver, and malicious racing.
In order to improve the driver's awareness of the driving behavior of the driver and perform early warning if necessary, so as to avoid potential accidents, many researches and products related to driving behavior detection are already available at present. These studies and products, in a large sense, fall into two main categories: from external detection and the vehicle itself. The former mainly refers to infrastructure deployed on a road in advance or a portable detection instrument held by a traffic police man for detection, and the latter mainly refers to various sensing and detection devices installed on a vehicle body for monitoring and detecting the driving condition of the vehicle in real time.
The detection scheme of the 3-axis acceleration sensor and the gyroscope has the advantages of low cost and low power consumption, and the sensor has strong correlation on the acquisition of the acceleration and the angular velocity of the vehicle and the detection of abnormal driving behaviors. The biggest problem of the detection scheme is that when the installation posture of the sensor is uncertain, the acceleration data of the sensor cannot directly reflect the acceleration of the automobile in all directions. One of the key issues in using an accelerometer for driving behavior detection is how to obtain the acceleration in the forward direction of the vehicle, i.e. how to correctly reflect the acceleration in each direction of the vehicle, especially the acceleration in the forward direction, by the value of the accelerometer. The existing detection mode seriously depends on the relative orientation relation between the accelerometer and the vehicle body, and the best installation mode is that the 3 axes of the accelerometer are completely overlapped with the coordinate space of the vehicle, so that the data of the accelerometer can truly reflect the acceleration of the vehicle. The installation mode is very limited in the originally limited space of the automobile body, and the mode of embedding the detection equipment into the automobile body through cooperation with an automobile manufacturer is very difficult in actual popularization. How to install an accelerometer in any posture and still obtain the acceleration of the vehicle in the advancing direction is a technical difficulty.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the defects of the prior art, a driving behavior detection method and device based on quaternion are provided.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows: a driving behavior detection method, comprising:
obtaining a static acceleration value of an accelerometer coordinate system when the vehicle is in a static state;
acquiring a starting acceleration value of an accelerometer coordinate system when a vehicle is started for the first time and moves forwards in an accelerated manner;
obtaining a rotation quaternion q of the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system and the vehicle coordinate system;
acquiring a motion acceleration value of an accelerometer coordinate system of a vehicle in a driving process;
acquiring a driving acceleration value of an accelerometer coordinate system according to the motion acceleration value and the static acceleration value;
converting the running acceleration numerical value of the accelerometer coordinate system into a vehicle running acceleration numerical value of the vehicle coordinate system through the rotation quaternion q;
analyzing the driving behavior according to the vehicle travelling acceleration value to obtain driving behavior analysis data;
and judging whether the vehicle has abnormal driving behaviors or not, and if so, giving an alarm to the driving behavior analysis data according to preset alarm information.
Further, in the step of converting the running acceleration value of the accelerometer coordinate system into the vehicle running acceleration value of the vehicle coordinate system by rotating the quaternion q, the running acceleration value of the accelerometer coordinate system is converted by a quaternion conversion formula, wherein the quaternion conversion formula is as follows:
wherein d is a quaternion form of a vehicle advancing acceleration value of a vehicle coordinate system, m is a quaternion form of a starting acceleration value of an accelerometer coordinate system, q is a rotation quaternion of two three-dimensional spaces, and q is a rotation quaternion of two three-dimensional spaces-1Is an inverse matrix of q and is,
is a cross product operation of the matrix.
Further, in the step of obtaining the rotation quaternion q of the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system and the vehicle coordinate system, an optimization function f is set, the optimization function f is minimized through a gradient descent algorithm, wherein,
further, the gradient descent algorithm comprises an iteration number, an iteration rate and an iteration precision, wherein the iteration number is 4000-.
Further, before the step of analyzing the driving behavior according to the vehicle running acceleration value of the vehicle coordinate system, the method further comprises the step of smoothing the vehicle running acceleration value through an average sliding window.
Further, in the step of judging whether the vehicle has abnormal driving behaviors or not and if so, carrying out alarm prompting on the driving behavior analysis data according to preset alarm information, the method also comprises the step of uploading the alarm information to a cloud server.
The invention also relates to a driving behavior detection device, which comprises an acquisition module, a calculation module, a conversion module, an analysis module, a judgment module and a prompt module,
the acquisition module is used for acquiring a static acceleration value of an accelerometer coordinate system when the vehicle is in a static state, acquiring a starting acceleration value of the accelerometer coordinate system when the vehicle is started for the first time and moves forwards in an accelerated manner, and acquiring a movement acceleration value of the accelerometer coordinate system when the vehicle is in a driving process;
the calculation module is used for acquiring a driving acceleration value of an accelerometer coordinate system according to the motion acceleration value and the static acceleration value;
the conversion module is used for obtaining a rotation quaternion q of the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system and the vehicle coordinate system, and converting the running acceleration value of the accelerometer coordinate system into a vehicle running acceleration value of the vehicle coordinate system through the rotation quaternion q;
the analysis module is used for analyzing the driving behavior according to the vehicle travelling acceleration value to obtain driving behavior analysis data;
the judging module is used for judging whether the vehicle has abnormal driving behaviors;
the prompting module is used for giving an alarm for the driving behavior analysis data according to preset alarm information.
Further, the calculation module is further configured to convert the driving acceleration value of the accelerometer coordinate system through a quaternion conversion formula, where the quaternion conversion formula is:
wherein d is a quaternion form of a vehicle advancing acceleration value of a vehicle coordinate system, m is a quaternion form of a starting acceleration value of an accelerometer coordinate system, q is a rotation quaternion of two three-dimensional spaces, and q is a rotation quaternion of two three-dimensional spaces-1Is the inverse of the matrix of q,
is a cross product operation of the matrix.
The vehicle driving acceleration control device further comprises a smoothing module, wherein the smoothing module is used for smoothing the vehicle driving acceleration value through an average sliding window.
Further, the system further comprises a communication module, and the communication module is used for uploading the alarm information to a cloud server.
The invention has the beneficial effects that: the acceleration sensor has the advantages that the acceleration in the vehicle direction can be acquired under the condition that the sensor equipment is installed in any posture, the utilization value of the acceleration sensor in the field of driving behavior detection is improved, and the acceleration sensor is more convenient both in the problems of equipment installation and deployment and in the aspects of data utilization and analysis. By adopting the method, the landing and popularization of the driving behavior detection scheme based on the acceleration sensor can be effectively improved, and the method also has certain research value in other traffic fields carrying the acceleration sensor.
Detailed Description
The technical solutions in the embodiments of the present invention are 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.
It should be noted that the description of the invention relating to "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying any relative importance or implicit indication of the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Example 1
A driving behavior detection method, comprising:
obtaining the static acceleration value of the accelerometer coordinate system when the vehicle is in a static state,
when the vehicle is at rest, the accelerometer only has acceleration readings in one direction, and because the installation posture of the accelerometer is uncertain, the acceleration readings of each axis of the accelerometer when the vehicle is at rest are required to confirm the orientation of gravity in the accelerometer coordinate system;
acquiring a starting acceleration value of an accelerometer coordinate system when the vehicle is started for the first time and accelerates to move forwards,
when the vehicle is started for the first time and the front movement of the vehicle is accelerated, the accelerometer coordinate system can generate an acceleration value in a second direction, namely a starting acceleration value, and the acceleration value in the direction is recorded and stored;
obtaining a rotation quaternion q of the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system and the vehicle coordinate system,
and obtaining a rotation quaternion q between the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system, the static acceleration value of the accelerometer coordinate system and the vehicle coordinate system, wherein one quaternion can be written into the form of the following formula (1):
q＝a+bi+cj+dk，(a，b，c，d∈R) (1)
the rotation of the two three-dimensional spatial coordinate systems can be expressed in the form of a quaternion matrix multiplication, as shown in equation (2):
where u and v each represent a vector in two three-dimensional spaces, which are represented in the formula as a quaternion. q is two rotational quaternions in three dimensions, q-1Is an inverse matrix of q and is,
is a cross product operation of the matrix;
acquiring a motion acceleration value of an accelerometer coordinate system of a vehicle in a driving process;
acquiring a driving acceleration value of an accelerometer coordinate system according to the motion acceleration value and the static acceleration value;
the running acceleration value of the accelerometer coordinate system is converted into a vehicle running acceleration value of the vehicle coordinate system through the rotation quaternion q,
after the rotation quaternion q between the accelerometer coordinate system and the vehicle coordinate system is obtained, the acceleration value of the accelerometer coordinate system can be obtained, namely the acceleration value of the accelerometer coordinate system can be subjected to rotation calculation through a formula (2), and then the vehicle travelling acceleration value of the vehicle coordinate system can be obtained;
analyzing the driving behavior according to the vehicle running acceleration value to obtain driving behavior analysis data,
the acceleration in three directions in the vehicle coordinate system can be known by analyzing the vehicle travelling acceleration value of the converted vehicle coordinate system, wherein the vehicle coordinate system comprises X, Y, Z three directions, X corresponds to the front and back directions of the vehicle, Y corresponds to the left and right directions of the vehicle, and Z corresponds to the up and down directions of the vehicle;
judging whether the vehicle has abnormal driving behavior, if so, giving an alarm to the driving behavior analysis data according to the preset alarm information,
when the abnormal driving behavior of the vehicle is judged, the driving behavior analysis result can be fed back to the user through the interpersonal interactive interface, and the abnormal condition of the vehicle can be informed to the user, family members or a traffic bureau through the technologies such as telephone, short message push and the like. The vehicle-mounted display equipment is connected, so that a driver can be reminded of driving behavior abnormity in real time, and finally, the driving behavior can be stored in the cloud end to store driving records.
As can be seen from the above description, the beneficial effects of the present invention are: the acceleration sensor has the advantages that the acceleration in the vehicle direction can be acquired under the condition that the sensor equipment is installed in any posture, the utilization value of the acceleration sensor in the field of driving behavior detection is improved, and the acceleration sensor is more convenient both in the problems of equipment installation and deployment and in the aspects of data utilization and analysis. By adopting the method, the landing and popularization of the driving behavior detection scheme based on the acceleration sensor can be effectively improved, and the method also has certain research value in other traffic fields carrying the acceleration sensor.
Example 2
On the basis of embodiment 1, in the step of converting the running acceleration value of the accelerometer coordinate system into the vehicle running acceleration value of the vehicle coordinate system by rotating the quaternion q, the running acceleration value of the accelerometer coordinate system is converted by a quaternion conversion formula, wherein the quaternion conversion formula is as follows:
wherein d is a quaternion form of a vehicle advancing acceleration value of a vehicle coordinate system, m is a quaternion form of a starting acceleration value of an accelerometer coordinate system, q is a rotation quaternion of two three-dimensional spaces, and q is a rotation quaternion of two three-dimensional spaces-1Is the inverse of the matrix of q,
is a cross product operation of the matrix.
In this embodiment, the vector of the accelerometer coordinate system can be converted into the vector of the vehicle coordinate system by rotating the quaternion q, the motion acceleration value of the accelerometer coordinate system is first converted into the quaternion form m, and a formula is adopted according to the calculated quaternion q
And converting the m to obtain a quaternion form d of the vehicle advancing acceleration value of the vehicle coordinate system, and finally converting the quaternion form d into a vector mode to obtain the vehicle advancing acceleration value of the vehicle coordinate system.
Example 3
On the basis of the embodiment 2, in the step of obtaining the rotation quaternion q of the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system and the vehicle coordinate system, the method further comprises the step of setting an optimization function f, and minimizing the optimization function f through a gradient descent algorithm, wherein,
in this embodiment, in order to ensure the accuracy and precision of the rotational quaternion q, the transformation calculation needs to be optimized by using a gradient descent algorithm, first a target optimization function f is set,
where d is the quaternion form of the vehicle travel acceleration value of the vehicle coordinate system and m is the quaternion form of the start acceleration value of the accelerometer coordinate system, since it is not necessary to know the specific quaternion of the vehicle travel direction, d may be defined as a unit vector, specifically,
d＝0+1i+0j+0k
the objective is to minimize the optimization function f so that q can be obtained by knowing d and m.
It should be noted that gradient descent is an iterative process, and by continuously calculating the gradient of the function and continuously giving a small increment to the function in the negative gradient direction, the function value gradually approaches the minimum value after multiple iterations.
Example 4
On the basis of embodiment 3, the gradient descent algorithm comprises an iteration number, an iteration rate and an iteration precision, wherein the iteration number is 4000-.
In this embodiment, the gradient descent algorithm is very convenient for programming implementation and calculation, and is a commonly used minimization function method in engineering. The gradient descent is an iterative process, the gradient of the function is continuously calculated, a small increment of the function in the negative gradient direction is continuously given, and after multiple iterations, the function value gradually approaches the minimum value. In this embodiment, after a plurality of tests, considering calculation efficiency and accuracy, parameters of the gradient descent algorithm are adjusted to: the number of iterations (epochs) was 5000, the iteration rate (eta) was 0.0002, and the iteration precision (accuracy) was 0.0001.
Example 5
On the basis of embodiment 4, before the step of analyzing the driving behavior according to the vehicle traveling acceleration value of the vehicle coordinate system, the method further includes smoothing the vehicle traveling acceleration value through an average sliding window.
In the embodiment, the average sliding window is adopted to carry out smoothing processing on the vehicle advancing acceleration value, so that the response speed can be improved, and the quality of the average value is not influenced.
Example 6
On the basis of the embodiment 5, in the step of judging whether the vehicle has abnormal driving behaviors or not and giving an alarm to the driving behavior analysis data according to the preset alarm information if the vehicle has abnormal driving behaviors, the method further comprises the step of uploading the alarm information to a cloud server.
In the embodiment, the warning information is uploaded to the cloud server, so that a background manager can acquire the vehicle state in time, for example, when a vehicle accident occurs, the background service personnel can assist a user of the vehicle to perform services such as warning, calling and rescuing and the like by acquiring the vehicle state; or the traffic bureau carries out evidence collection of illegal driving behavior identification according to the vehicle state, and the like.
Example 7
The invention also relates to a driving behavior detection device based on quaternion, which comprises an acquisition module, a calculation module, a conversion module, an analysis module, a judgment module and a prompt module,
the acquisition module is used for acquiring a static acceleration value of an accelerometer coordinate system when the vehicle is in a static state, acquiring a starting acceleration value of the accelerometer coordinate system when the vehicle is started for the first time and moves forwards in an accelerated manner, and acquiring a movement acceleration value of the accelerometer coordinate system when the vehicle is in a driving process;
when the vehicle is at rest, the accelerometer only has acceleration readings in one direction, and because the installation posture of the accelerometer is uncertain, the direction of gravity in an accelerometer coordinate system needs to be confirmed by reading the acceleration readings of each axis of the accelerometer when the vehicle is at rest, when the vehicle is started for the first time and the front motion of the vehicle is accelerated, the accelerometer coordinate system generates an acceleration value in a second direction, namely a starting acceleration value, and the acceleration value in the direction is recorded and stored, so that a rotation quaternion q between the accelerometer coordinate system and the vehicle coordinate system is obtained in a subsequent step according to the starting acceleration value of the accelerometer coordinate system.
The calculation module is used for acquiring a driving acceleration value of an accelerometer coordinate system according to the motion acceleration value and the static acceleration value;
and subtracting the static acceleration value of the accelerometer coordinate system when the vehicle is static from the motion acceleration value of the accelerometer coordinate system when the vehicle is in the running process, so as to obtain the running acceleration value of the accelerometer coordinate system when the vehicle is in the running process.
The conversion module is used for obtaining a rotation quaternion q of the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system and the vehicle coordinate system, and converting the running acceleration value of the accelerometer coordinate system into a vehicle running acceleration value of the vehicle coordinate system through the rotation quaternion q;
a quaternion can be written in the form of the following equation (1):
q＝a+bi+cj+dk，(a，b，c，d∈R) (1)
the rotation of the two three-dimensional spatial coordinate systems can be expressed in the form of a quaternion matrix multiplication, as shown in equation (2):
where u and v each represent a vector in two three-dimensional spaces, which are represented in the formula as a quaternion. q is two rotational quaternions in three dimensions, q-1Is the inverse of the matrix of q,
the acceleration value of the accelerometer coordinate system can be conveniently converted into the acceleration value of the vehicle coordinate system through the formula (1) and the formula (2) for the cross multiplication operation of the matrix.
The analysis module is used for analyzing the driving behavior according to the vehicle travelling acceleration value to obtain driving behavior analysis data;
the vehicle coordinate system comprises X, Y, Z three directions, wherein X corresponds to the front and back directions of the vehicle, Y corresponds to the left and right directions of the vehicle, and Z corresponds to the up and down directions of the vehicle, and the states of the vehicle, such as emergency braking, emergency acceleration, emergency deceleration, emergency turn, collision, rollover and the like, can be judged by analyzing the acceleration values in the three directions of the vehicle coordinate system, wherein the emergency braking, the emergency acceleration, the emergency deceleration, the collision and the rollover are judged by using an accelerometer, and the emergency turn is judged by using a gyroscope.
The judging module is used for judging whether the vehicle has abnormal driving behaviors;
when the acceleration value of at least one of the X, Y, Z three axes of the vehicle coordinate system exceeds the preset value, the abnormal vehicle running can be judged.
The prompting module is used for giving an alarm for the driving behavior analysis data according to preset alarm information.
In order to inform the driver of the vehicle condition in time, the driver can be reminded in real time through the prompting module, for example, the driver is reminded of the emergency of turning, the emergency of braking and the like.
Example 8
On the basis of embodiment 7, the calculation module is further configured to convert the driving acceleration value of the accelerometer coordinate system by using a quaternion conversion formula, where the quaternion conversion formula is:
wherein d is a quaternion form of a vehicle advancing acceleration value of a vehicle coordinate system, m is a quaternion form of a starting acceleration value of an accelerometer coordinate system, q is a rotation quaternion of two three-dimensional spaces, and q is a rotation quaternion of two three-dimensional spaces-1Is the inverse of the matrix of q,
is a cross product operation of the matrix.
In this embodiment, the vector of the accelerometer coordinate system can be converted into the vector of the vehicle coordinate system by rotating the quaternion q, the motion acceleration value of the accelerometer coordinate system is first converted into the quaternion form m, and a formula is adopted according to the calculated quaternion q
And converting the m to obtain a quaternion form d of the vehicle advancing acceleration value of the vehicle coordinate system, and finally converting the quaternion form d into a vector mode to obtain the vehicle advancing acceleration value of the vehicle coordinate system.
Example 9
On the basis of the embodiment 8, the vehicle running acceleration control device further comprises a smoothing processing module, wherein the smoothing processing module is used for smoothing the vehicle running acceleration value through an average sliding window.
In this embodiment, the smoothing module performs smoothing on the vehicle traveling acceleration value by using an average sliding window, so that the influence on the quality of the average value can be reduced while the response speed is increased.
Example 10
On the basis of embodiment 9, still include communication module, communication module is used for uploading alarm information to the high in the clouds server.
In the embodiment, the warning information can be uploaded to the cloud server through the communication module, so that a background manager can acquire the vehicle state in time, for example, when a vehicle accident occurs, the background service personnel can assist a user of the vehicle to perform services such as alarming, calling and rescuing and the like by acquiring the vehicle state; or the traffic bureau carries out evidence collection of illegal driving behavior identification according to the vehicle state, and the like.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (4)
1. A driving behavior detection method, comprising:
obtaining a static acceleration value of an accelerometer coordinate system when the vehicle is in a static state;
acquiring a starting acceleration value of an accelerometer coordinate system when a vehicle is started for the first time and moves forwards in an accelerated manner;
obtaining a rotation quaternion q of the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system and the vehicle coordinate system;
acquiring a motion acceleration value of an accelerometer coordinate system of a vehicle in a driving process;
acquiring a driving acceleration value of an accelerometer coordinate system according to the motion acceleration value and the static acceleration value;
converting the running acceleration numerical value of the accelerometer coordinate system into a vehicle running acceleration numerical value of the vehicle coordinate system through the rotation quaternion q;
analyzing the driving behavior according to the vehicle travelling acceleration value to obtain driving behavior analysis data;
judging whether the vehicle has abnormal driving behaviors or not, and if so, giving an alarm to the driving behavior analysis data according to preset alarm information;
in the step of obtaining the rotation quaternion q of the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system and the vehicle coordinate system, an optimization function f is set, the optimization function f is minimized through a gradient descent algorithm, wherein,
the gradient descent algorithm comprises iteration times, an iteration rate and an iteration precision, wherein the iteration times are 4000-;
the method comprises the steps of judging whether the vehicle has abnormal driving behaviors or not, if so, carrying out alarm prompting on driving behavior analysis data according to preset alarm information, and uploading the alarm information to a cloud server;
in the step of converting the running acceleration value of the accelerometer coordinate system into the vehicle running acceleration value of the vehicle coordinate system by rotating the quaternion q, the running acceleration value of the accelerometer coordinate system is converted by a quaternion conversion formula, wherein the quaternion conversion formula is as follows:
wherein d is a quaternion form of a vehicle advancing acceleration value of a vehicle coordinate system, m is a quaternion form of a starting acceleration value of an accelerometer coordinate system, q is a rotation quaternion of two three-dimensional spaces, and q is a rotation quaternion of two three-dimensional spaces-1Is the inverse of the matrix of q,
is a cross product operation of the matrix.
2. The driving behavior detection method according to claim 1, characterized in that: before the step of analyzing the driving behavior according to the vehicle running acceleration value of the vehicle coordinate system, the method further comprises the step of smoothing the vehicle running acceleration value through an average sliding window.
3. A driving behavior detection device characterized in that: comprises an acquisition module, a calculation module, a conversion module, an analysis module, a judgment module and a prompt module,
the acquisition module is used for acquiring a static acceleration value of an accelerometer coordinate system when the vehicle is in a static state, acquiring a starting acceleration value of the accelerometer coordinate system when the vehicle is started for the first time and moves forwards in an accelerated manner, and acquiring a movement acceleration value of the accelerometer coordinate system when the vehicle is in a driving process;
the calculation module is used for acquiring a driving acceleration value of an accelerometer coordinate system according to the motion acceleration value and the static acceleration value;
the calculation module is further configured to convert the driving acceleration value of the accelerometer coordinate system through a quaternion conversion formula, where the quaternion conversion formula is:
wherein d is a quaternion form of a vehicle advancing acceleration value of a vehicle coordinate system, m is a quaternion form of a starting acceleration value of an accelerometer coordinate system, q is a rotation quaternion of two three-dimensional spaces, and q is a rotation quaternion of two three-dimensional spaces-1Is the inverse of the matrix of q,
is a cross product operation of the matrix; the conversion module is used for obtaining a rotation quaternion q of the accelerometer coordinate system and the vehicle coordinate system according to the starting acceleration value of the accelerometer coordinate system and the vehicle coordinate system, and converting the running acceleration value of the accelerometer coordinate system into a vehicle running acceleration value of the vehicle coordinate system through the rotation quaternion q;
the conversion module is further configured to set an optimization function f, which is minimized by a gradient descent algorithm, wherein,
the gradient descent algorithm comprises iteration times, an iteration rate and an iteration precision, wherein the iteration times are 4000-;
the analysis module is used for analyzing the driving behavior according to the vehicle travelling acceleration value to obtain driving behavior analysis data;
the judging module is used for judging whether the vehicle has abnormal driving behaviors;
the prompting module is used for giving an alarm to the driving behavior analysis data according to preset alarm information;
still include communication module, communication module is used for uploading to the high in the clouds server warning message.
4. The driving behavior detection device according to claim 3, characterized in that: the vehicle acceleration smoothing device further comprises a smoothing processing module which is used for smoothing the vehicle running acceleration value through the average sliding window.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010818758.1A CN111932716B (en) | 2020-08-14 | 2020-08-14 | Driving behavior detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010818758.1A CN111932716B (en) | 2020-08-14 | 2020-08-14 | Driving behavior detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111932716A CN111932716A (en) | 2020-11-13 |
| CN111932716B true CN111932716B (en) | 2022-06-21 |
Family
ID=73310994
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010818758.1A Active CN111932716B (en) | 2020-08-14 | 2020-08-14 | Driving behavior detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111932716B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102167041A (en) * | 2011-01-07 | 2011-08-31 | 深圳市航天星网通讯有限公司 | Method for determining driving state of vehicle based on acceleration sensor |
| CN203673064U (en) * | 2013-10-04 | 2014-06-25 | 吉林大学 | Electromagnetic positioning device |
| CN104596693A (en) * | 2015-01-12 | 2015-05-06 | 武汉理工大学 | System and method for measuring a plurality of multi-dimensional motion parameters for fighting training |
| CN105270411A (en) * | 2015-08-25 | 2016-01-27 | 南京联创科技集团股份有限公司 | Analysis method and device of driving behavior |
| CN108068823A (en) * | 2017-12-06 | 2018-05-25 | 上海评驾科技有限公司 | A kind of vehicle drive behavioral value method |
| CN207637164U (en) * | 2017-11-10 | 2018-07-20 | 厦门大学 | A kind of vehicle-mounted fatigue driving monitoring system |
| CN111415532A (en) * | 2020-03-30 | 2020-07-14 | 辽宁省交通高等专科学校 | Transportation impact recorder based on Internet of things and recording method thereof |
-
2020
- 2020-08-14 CN CN202010818758.1A patent/CN111932716B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102167041A (en) * | 2011-01-07 | 2011-08-31 | 深圳市航天星网通讯有限公司 | Method for determining driving state of vehicle based on acceleration sensor |
| CN203673064U (en) * | 2013-10-04 | 2014-06-25 | 吉林大学 | Electromagnetic positioning device |
| CN104596693A (en) * | 2015-01-12 | 2015-05-06 | 武汉理工大学 | System and method for measuring a plurality of multi-dimensional motion parameters for fighting training |
| CN105270411A (en) * | 2015-08-25 | 2016-01-27 | 南京联创科技集团股份有限公司 | Analysis method and device of driving behavior |
| CN207637164U (en) * | 2017-11-10 | 2018-07-20 | 厦门大学 | A kind of vehicle-mounted fatigue driving monitoring system |
| CN108068823A (en) * | 2017-12-06 | 2018-05-25 | 上海评驾科技有限公司 | A kind of vehicle drive behavioral value method |
| CN111415532A (en) * | 2020-03-30 | 2020-07-14 | 辽宁省交通高等专科学校 | Transportation impact recorder based on Internet of things and recording method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 基于超宽带和惯导数据融合的高精度室内定位系统;朱澄卓;《中国优秀硕士学位论文全文数据库 信息科技辑》;20190415(第4期);I135-180 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111932716A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103043057B (en) | Abnormal driving based on vehicle position information judges and warning system | |
| CN107161097B (en) | Vehicle running intelligent security system based on Beidou Navigation System | |
| CN109466488B (en) | Automatic vehicle collision rescue alarm system | |
| KR102205240B1 (en) | Unexpected Impulse Change Collision Detector | |
| US7739087B2 (en) | Method and device for analying collision driving data | |
| US20180286152A1 (en) | In-vehicle control device and in-vehicle recording system | |
| CN105976450A (en) | Unmanned vehicle data processing method and device, and black box system | |
| CN107633683B (en) | Off-site law enforcement management system for vehicle overload | |
| CN107757541B (en) | Accident monitoring method and device | |
| CN111081051A (en) | Vehicle accident handling method and device, accident monitoring equipment, vehicle-mounted terminal and storage medium | |
| CN103700160A (en) | Motor vehicle onboard terminal based on microsensor and driving behavior judgment method | |
| US10249112B2 (en) | Vehicle state monitoring apparatus, vehicle state monitoring system, and vehicle state monitoring method | |
| CN110092256B (en) | Method and system for monitoring upstairs of electric vehicle riding elevator and monitoring device | |
| JP2007293536A (en) | Accident information collecting system and accident information recording device | |
| CN105489007A (en) | Vehicle management method and system | |
| CN105818815A (en) | Method for detecting road condition information by using OBD (On-Board Diagnostics) | |
| CN112193207A (en) | Intelligent vehicle-mounted interconnection safety system based on 5G technology | |
| CN201540600U (en) | Vehicular video recording device | |
| CN107895484A (en) | A kind of car networking sensor group system based on big data | |
| CN106467059A (en) | A kind of rollover alarming method and apparatus based on 3-axis acceleration sensor | |
| CN112537254A (en) | Vehicle and vehicle early warning method and device | |
| KR20100090048A (en) | The system for collecting and analyzing information related to driver's automobile manipulation | |
| CN206383949U (en) | Driving safety system based on the pure image procossings of ADAS | |
| CN111932716B (en) | Driving behavior detection method and device | |
| CN117022323A (en) | Intelligent driving vehicle behavior analysis and prediction system and method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |