CN112896388B - Riding safety detection method and device, electronic equipment and storage medium - Google Patents
Riding safety detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112896388B CN112896388B CN202110157015.9A CN202110157015A CN112896388B CN 112896388 B CN112896388 B CN 112896388B CN 202110157015 A CN202110157015 A CN 202110157015A CN 112896388 B CN112896388 B CN 112896388B
- Authority
- CN
- China
- Prior art keywords
- riding
- data
- vehicle
- abnormal
- time sequence
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62J—CYCLE SADDLES OR SEATS; AUXILIARY DEVICES OR ACCESSORIES SPECIALLY ADAPTED TO CYCLES AND NOT OTHERWISE PROVIDED FOR, e.g. ARTICLE CARRIERS OR CYCLE PROTECTORS
- B62J45/00—Electrical equipment arrangements specially adapted for use as accessories on cycles, not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62J—CYCLE SADDLES OR SEATS; AUXILIARY DEVICES OR ACCESSORIES SPECIALLY ADAPTED TO CYCLES AND NOT OTHERWISE PROVIDED FOR, e.g. ARTICLE CARRIERS OR CYCLE PROTECTORS
- B62J45/00—Electrical equipment arrangements specially adapted for use as accessories on cycles, not otherwise provided for
- B62J45/40—Sensor arrangements; Mounting thereof
- B62J45/41—Sensor arrangements; Mounting thereof characterised by the type of sensor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62J—CYCLE SADDLES OR SEATS; AUXILIARY DEVICES OR ACCESSORIES SPECIALLY ADAPTED TO CYCLES AND NOT OTHERWISE PROVIDED FOR, e.g. ARTICLE CARRIERS OR CYCLE PROTECTORS
- B62J45/00—Electrical equipment arrangements specially adapted for use as accessories on cycles, not otherwise provided for
- B62J45/40—Sensor arrangements; Mounting thereof
- B62J45/41—Sensor arrangements; Mounting thereof characterised by the type of sensor
- B62J45/414—Acceleration sensors
Abstract
The invention discloses a riding safety detection method, a device, electronic equipment and a storage medium, wherein the method is applied to the electronic equipment installed on a vehicle and specifically comprises the following steps: acquiring various riding characteristic data respectively detected by a plurality of sensors arranged on a vehicle; fitting the various riding characteristic data to obtain time sequence data for representing the riding process of the user; and detecting abnormal points in the time sequence data, and judging whether dangerous riding behaviors occur or not according to the abnormal points. The riding behavior detection based on the edge calculation is realized through the electronic equipment installed on the vehicle volume, the real-time performance of the riding behavior detection and the high-stability result are improved, the data are uploaded to the cloud end through the base station, on one hand, the high-frequency sensor data can directly calculate at the electronic equipment end to reduce the storage pressure of cloud calculation to a certain extent, and then, the problems that the data transmission is delayed and the wrong calculation is caused due to the fact that the base station signal is unstable are effectively avoided.
Description
Technical Field
The invention relates to the technical field of detection, in particular to a riding safety detection method and device, electronic equipment and a storage medium.
Background
Vehicles are frequently used when people go out. In both motor vehicles and non-motor vehicles, frequent use often results in wear of components, which wear is more or less prone to accidents. Of course, safety accidents caused by the use habits of users are also common. In the field of two-wheel traveling, whether a bicycle or a motorcycle, accidents are caused by poor riding behaviors of users and vehicle abnormalities (including vehicle product defects and vehicle faults) due to wearing of parts (such as brake failure) or non-compliance with traffic regulations.
For private cars, the risk is generally born by the consumer after the car is purchased, and the business model of the shared trip not only provides the obligation of trip convenience but also bears the risk accident of the consumer caused by product defects. As with the car insurance of four-wheeled vehicles, the operating companies of shared vehicles need to forejudge the person responsible for the accident and pay a certain amount of compensation. The operation company protects the driving of the user by combining with an insurance company, but accidents caused by poor riding habits and abnormal vehicles (including vehicle product defects and vehicle faults) of the user are borne by the user. Therefore, the judgment on the riding safety of the user is helpful for determining the responsibility and obligation in indemnification disputes. Therefore, it is a very important data evidence to detect the riding behavior of the user in riding the bicycle.
Then, because the two wheels of shared vehicles are large in magnitude and are easily influenced by the environment, if the riding behavior detection of each vehicle is realized through the cloud, the problems of poor real-time performance, easy data loss and high pressure on cloud computing and storage exist.
Disclosure of Invention
In view of the above defects in the prior art, the present invention provides a riding safety detection method, apparatus, device and storage medium.
In order to achieve the above object, the present invention provides a riding safety detection method applied to an electronic device mounted on a vehicle, the riding safety detection method comprising: acquiring various riding characteristic data respectively detected by a plurality of sensors arranged on the vehicle; fitting the various riding characteristic data to obtain time sequence data for representing the riding process of the user; and detecting abnormal points in the time sequence data, and judging whether dangerous riding behaviors occur or not according to the abnormal points.
In a preferred embodiment of the present invention, the determining whether a dangerous riding behavior occurs according to the abnormal point includes: acquiring first time sequence data at the abnormal point and second time sequence data before the user rides to the abnormal point from the beginning; calculating the similarity of the first time sequence data and the second time sequence data; if the similarity is smaller than a preset threshold value, determining that dangerous riding behaviors do not occur; and if the similarity is greater than or equal to the preset threshold value, determining that dangerous riding behaviors occur.
In a preferred embodiment of the present invention, the calculating the similarity between the first time series data and the second time series data includes: and calculating the cosine similarity of the riding speed, the rotating speed and the acceleration at the abnormal point and the riding speed, the rotating speed and the acceleration before the abnormal point from the beginning of riding.
In a preferred embodiment of the present invention, the method further comprises: if dangerous riding behaviors occur, judging whether the time sequence data at the abnormal point is suddenly changed or gradually changed; if sudden change occurs, determining that the dangerous riding behavior is caused by vehicle abnormality; and if the gradual change occurs, determining that the dangerous riding behavior is caused by the riding behavior of the user.
In a preferred embodiment of the present invention, the method further comprises: if dangerous riding behaviors occur, calculating the proportion of the abnormal data of the vehicle in a single direction to the total abnormal data in other directions; if the proportion of the abnormal data in the single direction is higher than the proportion of the total abnormal data in other directions, determining that the dangerous riding behavior is caused by vehicle abnormality; and if the proportion of the abnormal data in the single direction is not higher than the proportion of the total abnormal data in other directions, determining that the dangerous riding behavior is caused by the riding behavior of the user.
In a preferred embodiment of the present invention, the single direction is a vehicle front-rear direction, and the other directions include a vehicle left-right direction and a vehicle up-down direction.
In a preferred embodiment of the present invention, the abnormal data is vehicle acceleration, wherein if the vehicle acceleration changes abnormally in a single direction, it is determined that the dangerous riding behavior is caused by vehicle abnormality; and if the acceleration of the vehicle is abnormal in change in multiple directions, determining that the dangerous riding behavior is caused by the riding behavior of the user.
In a preferred embodiment of the present invention, the detecting the abnormal point in the time-series data includes: acquiring time sequence data of the current moment; predicting to obtain time sequence data of the next moment by utilizing the time sequence data of the current moment; acquiring actual time sequence data at the next moment; calculating an error between the predicted time series data of the next moment and the actual time series data of the next moment; judging whether the errors accord with a preset distribution rule or not; and if the time sequence data does not accord with the preset distribution rule, determining the time sequence data of the next moment as an abnormal point.
In a preferred embodiment of the present invention, the sensor includes an accelerometer, a geomagnetic sensor, and a gyroscope; accordingly, the riding characteristic data comprises: vehicle acceleration, geomagnetic intensity, and vehicle offset angle.
In order to achieve the above object, the present invention further provides a riding safety detecting device, which is mounted on a vehicle, the riding safety detecting device comprising: the acquisition module is used for acquiring various riding characteristic data which are respectively detected by a plurality of sensors arranged on the vehicle; the processing module is used for fitting the various riding characteristic data to obtain time sequence data for representing the riding process of the user; and the detection module is used for detecting abnormal points in the time sequence data and judging whether dangerous riding behaviors occur or not according to the abnormal points.
In order to achieve the above object, the present invention also provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to perform the riding safety detection method as described above.
In order to achieve the above object, the present invention further provides a computer-readable storage medium storing computer instructions for causing a computer to execute the riding safety detection method as described above.
The device or the method provided by the invention has the following technical effects:
1. obtain sensor detection through the electronic equipment of installing on the car volume and obtain the characteristic data of riding, and the fitting forms the chronogenesis data, then detect the anomaly, directly judge dangerous behavior of riding at the vehicle end, realize the behavior of riding based on edge calculation and detect, the real-time of behavior of riding detection and high stability's result has been improved, compare in data and pass through the basic station and reach the high in the clouds, but the sensor data of on the one hand high frequency can reduce the storage pressure of cloud calculation to a certain extent at the electronic equipment end direct calculation, secondly effectively avoid the unstable data transmission delay that leads to of base station signal, lose and arouse miscalculation.
2. Through adopting three kinds of different sensors, including accelerometer, earth magnetism sensor and gyroscope, can gather the characteristics of the different aspects that the user embodies when riding the vehicle respectively, fuse the edge calculation of the realization to the vehicle behavior of riding with the multisensor characteristic.
3. The second time sequence data can reflect historical riding behaviors of the user, the first time sequence data at the abnormal point can be regarded as the current riding behaviors of the user, the similarity of the first time sequence data and the second time sequence data can be calculated to be regarded as the difference between the current riding behaviors of the user and the historical riding behaviors, dangerous riding behaviors are judged through the difference, the current behaviors of the user and the historical behaviors are compared to judge the abnormal degree of the current behaviors, and the dangerous riding behaviors can be accurately judged.
4. Since any operation behavior of the user does not generate any influence and feedback when the vehicle is abnormal, the vehicle is prone to generate continuous abnormal data in a single direction, for example, when a vehicle tire is locked, the acceleration in the riding direction is continuously abnormal, and the proportion of the abnormal data in the direction is much higher than that in other directions. When the user rides and has an accident, multi-azimuth abnormal data can be generated, so that the responsibility and the reason of the accident can be judged based on the abnormal data proportion in a single direction, and whether the accident is caused by the riding behavior of the user or the abnormal vehicle is determined.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of a riding safety detection method of the present invention;
FIG. 2 is a flow chart of another preferred embodiment of the riding safety detection method of the present invention;
FIG. 3 is a schematic structural view of a preferred embodiment of the riding safety detecting device of the present invention;
FIG. 4 is a diagram of an electronic device according to a preferred embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than being drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of each component in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated.
Some exemplary embodiments of the invention have been described for illustrative purposes, and it is to be understood that the invention may be practiced otherwise than as specifically described.
The embodiment of the invention provides a riding safety detection method, which is applied to electronic equipment installed on a vehicle, and the electronic equipment can execute corresponding steps for detecting and judging riding behaviors of a user, so that the edge calculation of the riding behaviors of the user is realized.
Edge computing refers to an open platform integrating network, computing, storage and application core capabilities at one side close to an object or a data source to provide nearest-end services nearby. The application program is initiated at the edge side, so that a faster network service response is generated, and the basic requirements of the industry in the aspects of real-time business, application intelligence, safety, privacy protection and the like are met. The edge computation is between the physical entity and the industrial connection, or on top of the physical entity. And the cloud computing still can access the historical data of the edge computing.
In research, the inventor finds that two-wheeled vehicles are larger in magnitude order than four-wheeled vehicles and are more easily influenced by environmental factors (often appear in remote areas or corners due to small size and convenience in riding), so that the cloud cannot detect riding behaviors of each vehicle in real time, calculation and storage pressure of the cloud is high, and on the other hand, due to the fact that the environment is complex, data transmission is prone to data loss or the real-time performance is poor, therefore, the scheme that the electronic device is installed at the vehicle end and used for achieving edge calculation of user riding behavior detection is provided, and the defects that the cloud is used for detecting and calculating are completely avoided.
The vehicle provided by the embodiment of the invention can be a two-wheel or single-wheel vehicle, and can be applied to real-time detection of riding behaviors of a large number of vehicles. Meanwhile, a sensor for detecting riding characteristic data can be installed on the vehicle, and the sensor can be arranged in the electronic equipment or can be independently arranged on the vehicle.
As shown in fig. 1, the riding safety detection method comprises the following steps:
and S101, acquiring various riding characteristic data respectively detected by a plurality of sensors arranged on the vehicle.
In the embodiment of the invention, the plurality of sensors may be the same sensor or different sensors. As described above, the sensor may be provided on the vehicle alone or on the electronic device, and therefore, if the electronic device is mounted on the vehicle, the sensor is provided on the vehicle. Each sensor detects riding characteristic data, and the riding characteristic data refers to characteristic data capable of reflecting riding of a user, such as speed, acceleration, deflection angle and the like. Accordingly, the sensor may be an accelerometer, a geomagnetic sensor, a gyroscope, or the like.
The electronic equipment acquires the riding characteristic data detected by each sensor for subsequent behavior detection and judgment.
And S102, fitting the multiple riding characteristic data to obtain time sequence data for representing the riding process of the user.
The various riding characteristic data are independent, but characteristics of different angles, such as changes of acceleration and deflection angles, can be reflected in the behavior detection, and the characteristics of the user when turning can be reflected together. Therefore, in the embodiment of the invention, the electronic equipment fits the various riding characteristic data to form a smooth curve changing along with time, so as to obtain the time sequence data capable of representing the riding process of the user. In this embodiment, each riding characteristic data may correspond to one time series data, or a curve fitted with various riding characteristic data may be displayed in one data chart to form one data.
And S103, detecting abnormal points in the time sequence data, and judging whether dangerous riding behaviors occur or not according to the abnormal points.
In the embodiment of the invention, the electronic equipment is arranged on the vehicle, so that the front end of the vehicle fits each riding characteristic data to obtain the corresponding time sequence data, then the abnormal point in the time sequence data is detected, and whether dangerous riding behaviors occur or not is judged according to the abnormal point, thereby realizing the riding safety detection of the vehicle based on edge calculation. The steps executed after determining whether dangerous riding behaviors occur are not limited. In the embodiment of the invention, the electronic equipment can send the detection result to the cloud after the dangerous riding behavior is detected; other subsequent detection and judgment can be performed, for example, the judgment of the behavior is performed, and whether the vehicle is abnormal or the riding behavior of the user is caused is determined.
According to the embodiment of the invention, the riding characteristic data is obtained by acquiring the sensor detection through the electronic equipment installed on the vehicle volume, the time sequence data is formed by fitting, then the abnormal point is detected, the dangerous riding behavior is directly judged at the vehicle end, the riding behavior detection based on edge calculation is realized, the real-time performance and the high stability result of the riding behavior detection are improved, compared with the situation that the data are uploaded to the cloud end through the base station, on one hand, the storage pressure of cloud calculation can be reduced to a certain extent by directly calculating the high-frequency sensor data at the electronic equipment end, and then the error calculation caused by data transmission delay and loss due to the instability of the base station signal is effectively avoided.
The method provided by the embodiment of the invention is particularly suitable for applying edge calculation to the riding behavior detection of vehicles with large magnitude order, and has remarkable beneficial effects in scenes with large magnitude order and large influence of environmental factors on riding vehicles such as two wheels.
Optionally, the sensor in the embodiment of the present invention includes an accelerometer, a geomagnetic sensor, and a gyroscope. Accordingly, the riding characteristic data comprises: vehicle acceleration, geomagnetic intensity, and vehicle offset angle. The sensor can adopt a 9-axis sensor, comprising: a 3-axis accelerometer, a 3-axis magnetic sensor, and a 3-axis gyroscope. The acquisition frequencies of the sensors can be the same or different; of course, different frequencies may be used in different situations, for example, at 100Hz when the user is riding. And under the non-riding condition, no acquisition or low-frequency acquisition is carried out. The electronic device may include an MCU or CPU capable of carrying edge calculations for obtaining corresponding data from each sensor and performing subsequent calculations and determinations.
If the user rides, the sensor data of collection also is riding characteristic data, can obtain 9 dimensions through kalman filter preliminary treatment noise data, can divide into following three part fitting acceleration, earth intensity and turn to:
an accelerometer: the speed abnormality in the front-rear/left-right/up-down directions of the vehicle is evaluated from the three x/y/z axes, respectively. Wherein, the x-axis represents the vehicle front-rear direction, the y-axis represents the vehicle left-right direction, and the z-axis represents the vehicle up-down direction.
A geomagnetic sensor: detecting magnetic field variations
A gyroscope: the degree of deviation of the vehicle from the original direction during forward travel. The original direction refers to the t-1 moment, namely the direction of the previous data uploading each time, and the deviation degree refers to the direction included angle between the t moment and the t-1 moment. The inventors have found that this difference is mainly manifested as whether the steering of the vehicle is smooth or abnormal on the road. For example: at the intersection, if the bicycle turns to the west, the direction of the gyroscope continuously shifts to the west and continuously changes, and if the bicycle is braked emergently or in an emergency, the direction of the vehicle can be unstable in a short time.
In the embodiment of the invention, three different sensors including an accelerometer, a geomagnetic sensor and a gyroscope are adopted, so that the characteristics of different aspects of the user when riding the vehicle can be respectively collected, and the characteristics of multiple sensors are fused to realize the edge calculation of the riding behavior of the vehicle.
As an alternative implementation, in the embodiment of the present invention, the abnormal point may be detected by using an exponential smoothing or a time sequence model, and the time sequence model may be an ARIMA time sequence model. Specifically, the detecting the abnormal point in the time series data includes:
step S11, acquiring time sequence data of the current moment;
step S12, obtaining time sequence data of the next moment by utilizing the time sequence data of the current moment in a prediction mode;
acquiring actual time sequence data at the next moment;
step S13, calculating the error between the predicted time sequence data of the next moment and the actual time sequence data of the next moment;
step S14, judging whether the errors accord with a preset distribution rule or not; specifically, it may be determined whether the error conforms to the positive distribution 3sigma. If not, it is an abnormal point, otherwise it is a normal point.
And S15, if the time sequence data does not accord with the preset distribution rule, determining that the time sequence data at the next moment is an abnormal point.
In the embodiment of the invention, the electronic equipment continuously collects the data detected by the sensor, and then the judgment of the steps S11-S15 is adopted one by one to determine the abnormal point. Because a large number of outliers still exist even after the initial noise reduction is carried out, the abnormal point detection can ignore the influence of single outlier and data abnormal jitter, and thus the trend of signal change is fitted.
Specifically, exponential smoothing generally refers to predicting data at time t +1 through data at time t, collecting data at time t +1, and determining whether an error between the predicted value and an actual value conforms to 3sigma. Predicting the following data in real time based on the data within 10s by exponential smoothing:
y′ t+1 ＝y′ t +a(y t -y′ t )
wherein y' is a predicted value and a is a trend smoothing coefficient.
As an optional implementation mode, after the abnormal point is detected, the detection of the dangerous riding behavior is triggered. The dangerous riding behavior can be detected by adopting a detection model obtained by pre-training. The detection model can take the historical riding behavior data of the user and the riding behavior characteristic data of the current abnormal point as input, and then calculate the similarity of the historical riding behavior data and the riding behavior characteristic data to judge whether dangerous riding behaviors occur at the abnormal point.
Specifically, the determining whether dangerous riding behaviors occur according to the abnormal points includes: acquiring first time sequence data at the abnormal point and second time sequence data before the user rides to the abnormal point from the beginning; calculating the similarity of the first time sequence data and the second time sequence data; if the similarity is smaller than a preset threshold value, determining that dangerous riding behaviors do not occur; and if the similarity is greater than or equal to the preset threshold value, determining that dangerous riding behaviors occur.
In the embodiment of the invention, the second time sequence data can reflect the historical riding behaviors of the user, the first time sequence data at the abnormal point can be regarded as the current riding behaviors of the user, the similarity between the first time sequence data and the second time sequence data can be calculated as the difference between the current riding behaviors of the user and the historical riding behaviors, the dangerous riding behaviors are judged through the difference, the current behaviors of the user and the historical behaviors are compared to judge the abnormal degree of the current behaviors, and the dangerous riding behaviors can be accurately judged.
Further, in this embodiment of the present invention, the calculating the similarity between the first time series data and the second time series data includes: and calculating the cosine similarity of the riding speed, the rotating speed and the acceleration at the abnormal point and the riding speed, the rotating speed and the acceleration before the abnormal point from the beginning of riding. Namely, the dangerous riding behavior of the user is judged by calculating the cosine similarity between the historical data of the riding speed, the rotating speed and the acceleration of the user before the user starts to ride and the abnormal point and the riding speed, the rotating speed and the acceleration of the current abnormal point.
As one of the main points of the embodiment of the present invention, after the dangerous riding behavior is determined, the reason for generating the dangerous riding behavior needs to be determined, that is, the responsible party is determined. Specifically, the riding safety detection method provided by the embodiment of the invention further comprises the following steps: if dangerous riding behaviors occur, judging whether the time sequence data at the abnormal point is suddenly or gradually changed; if sudden change occurs, determining that the dangerous riding behavior is caused by abnormal vehicle; and if the gradual change occurs, determining that the dangerous riding behavior is caused by the riding behavior of the user.
Whether dangerous riding behavior is riding behavior of a user or is caused by vehicle abnormity (including vehicle product defects and vehicle faults) is judged through the difference of sudden change and gradual change of current signals. The part is mainly combined with a multi-sensor to judge the short-time reduction and entropy change of signal abnormity to distinguish sudden change and gradual change. Gradual changes are typically dangerous riding caused by poor riding habits, while abrupt changes are typically vehicle anomalies (including vehicle product defects and vehicle failures).
As shown in fig. 2, an optional riding safety detection method according to an embodiment of the present invention includes:
s21, collecting data detected by an accelerometer, a geomagnetic sensor and a gyroscope;
s22, performing Kalman filtering processing on the acquired data, and fitting to obtain time sequence data;
and S23, detecting abnormal points of the time sequence data by using the time sequence model.
And step S24, judging dangerous riding behaviors when abnormal points are detected.
Step S25, after the dangerous riding behavior is judged, performing judgment duty, wherein the sudden change of the signal is determined to be caused by the abnormality of the vehicle; the signal fade is determined to be caused by the riding behavior of the user.
In an alternative implementation manner of the embodiment of the invention, the cause of the dangerous riding behavior can be judged according to the abnormal data proportion in a single direction. Specifically, the riding safety detection method further comprises the following steps:
if dangerous riding behaviors occur, calculating the proportion of the abnormal data of the vehicle in a single direction to the total abnormal data in other directions; if the proportion of the abnormal data in the single direction is higher than that of the total abnormal data in other directions, determining that the dangerous riding behavior is caused by the abnormality of the vehicle; and if the proportion of the abnormal data in the single direction is not higher than the proportion of the total abnormal data in other directions, determining that the dangerous riding behavior is caused by the riding behavior of the user.
Since any operation behavior of the user does not produce any influence or feedback when the vehicle is abnormal, the vehicle is prone to produce continuous abnormal data in a single direction, for example, when a vehicle tire is locked, the acceleration in the riding direction is subjected to continuous abnormal conditions, and the proportion of the abnormal data in the direction is far higher than that in other directions. When the user rides and has an accident, multi-azimuth abnormal data can be generated, so that the responsibility and the reason of the accident can be judged based on the abnormal data proportion in a single direction, and whether the accident is caused by the riding behavior of the user or the abnormal vehicle is determined.
Optionally, the single direction is a vehicle front-rear direction, and the other directions include a vehicle left-right direction and a vehicle up-down direction.
Specifically, the front-back direction of the vehicle on which the user rides is taken as the x-axis direction, the left-right direction is taken as the y-axis direction, and the up-down direction is taken as the z-axis direction. Data are collected 100 times within 10s, abnormal frequency of the data within 100 times of the x/y/z axis is respectively counted, and a responsible party can be determined through the following steps:
user responsibility: the proportion of data anomalies occurring on the y/z axis > = x axis. In the scene, the abnormal proportion of data generated on the y/z axis is too high, which indicates that abnormal deviation caused by non-vehicle faults occurs before an accident occurs to the vehicle.
Vehicle failure: the x-axis is much higher than the y/z-axis for data anomalies.
Further, the abnormal data may be vehicle acceleration, wherein if the vehicle acceleration changes abnormally in a single direction, it is determined that the dangerous riding behavior is caused by vehicle abnormality; and if the acceleration of the vehicle is abnormal in change in multiple directions, determining that the dangerous riding behavior is caused by the riding behavior of the user.
Tire lock/brake cable is too loose, causing accelerometer changes. An anomaly of the accelerometer changing in one direction, typically a braking anomaly; the abnormality of the multi-directional change of the accelerometer is usually caused by sudden braking. The invention detects the vehicle fault by detecting the unidirectional data abnormality of the accelerometer.
An embodiment of the present invention further provides a riding safety detection device, which is mounted on a vehicle and can be used to execute the riding safety detection method provided in the foregoing embodiment, and as shown in fig. 3, the riding safety detection device includes:
an obtaining module 301, configured to obtain multiple riding characteristic data detected by multiple sensors arranged on the vehicle respectively.
And the processing module 302 is configured to fit the multiple riding characteristic data to obtain time sequence data for representing a riding process of the user.
And the detection module 303 is configured to detect an abnormal point in the time sequence data, and determine whether a dangerous riding behavior occurs according to the abnormal point.
According to the embodiment of the invention, the riding characteristic data is obtained by acquiring the sensor detection through the electronic equipment installed on the vehicle volume, the time sequence data is formed by fitting, then the abnormal point is detected, the dangerous riding behavior is directly judged at the vehicle end, the riding behavior detection based on edge calculation is realized, the real-time performance and the high stability result of the riding behavior detection are improved, compared with the situation that the data are uploaded to the cloud end through the base station, on one hand, the storage pressure of cloud calculation can be reduced to a certain extent by directly calculating the high-frequency sensor data at the electronic equipment end, and then the error calculation caused by data transmission delay and loss due to the instability of the base station signal is effectively avoided.
In a preferred embodiment of the present invention, the detection module includes: a first acquisition unit configured to acquire first time-series data at the abnormal point and second time-series data before the user rides from the start to the abnormal point; a first calculation unit configured to calculate a similarity between the first time-series data and the second time-series data; the determining unit is used for determining that dangerous riding behaviors do not occur if the similarity is smaller than a preset threshold; and if the similarity is greater than or equal to the preset threshold value, determining that dangerous riding behaviors occur.
In a preferred embodiment of the present invention, the calculation unit is specifically configured to calculate cosine similarities of the riding speed, the rotation speed, and the acceleration at the abnormal point and the riding speed, the rotation speed, and the acceleration before the abnormal point from the start of riding.
In a preferred embodiment of the present invention, the apparatus further comprises: the first judgment module is used for judging whether the time sequence data at the abnormal point is suddenly changed or gradually changed if dangerous riding behaviors occur; the first determining module is used for determining that the dangerous riding behavior is caused by abnormal vehicle if sudden change occurs; and if the gradual change occurs, determining that the dangerous riding behavior is caused by the riding behavior of the user.
In a preferred embodiment of the present invention, the apparatus further comprises: the second judgment module is used for calculating the proportion of the abnormal data of the vehicle in a single direction to the total abnormal data of other directions if dangerous riding behaviors occur; the second determination module is used for determining that the dangerous riding behavior is caused by vehicle abnormity if the proportion of the abnormal data in the single direction is higher than that of the total abnormal data in other directions; and if the proportion of the abnormal data in the single direction is not higher than the proportion of the total abnormal data in other directions, determining that the dangerous riding behavior is caused by the riding behavior of the user.
In a preferred embodiment of the present invention, the single direction is a vehicle front-rear direction, and the other directions include a vehicle left-right direction and a vehicle up-down direction.
In a preferred embodiment of the present invention, the abnormal data is vehicle acceleration, wherein if the vehicle acceleration changes abnormally in a single direction, it is determined that the dangerous riding behavior is caused by vehicle abnormality; and if the acceleration of the vehicle is abnormal in change in multiple directions, determining that the dangerous riding behavior is caused by the riding behavior of the user.
In a preferred embodiment of the present invention, the detection module includes: the second acquisition unit is used for acquiring time sequence data of the current moment; the prediction unit is used for predicting the time sequence data of the next moment by utilizing the time sequence data of the current moment; the acquisition unit is used for acquiring actual time sequence data at the next moment; a second calculation unit configured to calculate an error between the predicted time series data of the next time and the actual time series data of the next time; the judging unit is used for judging whether the errors accord with a preset distribution rule or not; and if the time sequence data does not accord with the preset distribution rule, determining that the time sequence data at the next moment is an abnormal point.
The above description of the specific embodiments may refer to method embodiments, which are not repeated herein.
In an embodiment of the present invention, an electronic device is further provided, where the electronic device may be a background server in the foregoing embodiment, and an internal structure diagram of the electronic device may be as shown in fig. 4. The electronic device comprises a processor, a memory and a network interface which are connected through a system bus. Wherein the processor of the electronic device is configured to provide computing and control capabilities. The memory of the electronic equipment comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the electronic device is used for connecting and communicating with an external electronic device through a network. The computer program is executed by a processor to realize a riding safety detection method. The electronic device may further include a display screen and an input device, where the display screen may be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device may be a touch layer covered on the display screen, or may be a key, a trackball, or a touch pad arranged on a housing of the electronic device.
On the other hand, the electronic device may not include a display screen and an input device, and those skilled in the art will understand that the structure shown in fig. 4 is only a block diagram of a part of the structure related to the present application, and does not constitute a limitation of the electronic device to which the present application is applied, and a specific electronic device may include more or less components than those shown in the figure, or combine some components, or have different component arrangements.
In one embodiment, an electronic device is provided, mounted on a vehicle, comprising at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to perform the steps of:
acquiring various riding characteristic data respectively detected by a plurality of sensors arranged on the vehicle;
fitting the various riding characteristic data to obtain time sequence data for representing the riding process of the user;
and detecting abnormal points in the time sequence data, and judging whether dangerous riding behaviors occur or not according to the abnormal points.
In one embodiment, a readable storage medium is provided, the computer readable storage medium having stored thereon computer instructions for causing the computer to perform:
acquiring various riding characteristic data respectively detected by a plurality of sensors arranged on the vehicle;
fitting the various riding characteristic data to obtain time sequence data for representing the riding process of the user;
and detecting abnormal points in the time sequence data, and judging whether dangerous riding behaviors occur or not according to the abnormal points.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. A riding safety detection method is applied to electronic equipment installed on a vehicle, and comprises the following steps:
acquiring various riding characteristic data respectively detected by a plurality of sensors arranged on the vehicle;
fitting the various riding characteristic data to obtain time sequence data for representing the riding process of the user;
detecting abnormal points in the time sequence data, and judging whether dangerous riding behaviors occur or not according to the abnormal points;
the riding safety detection method further comprises the following steps:
if dangerous riding behaviors occur, calculating the proportion of the abnormal data of the vehicle in a single direction to the total abnormal data in other directions;
if the proportion of the abnormal data in the single direction is higher than the proportion of the total abnormal data in other directions, determining that the dangerous riding behavior is caused by vehicle abnormality;
and if the proportion of the abnormal data in the single direction is not higher than the proportion of the total abnormal data in other directions, determining that the dangerous riding behavior is caused by the riding behavior of the user.
2. The riding safety detection method according to claim 1, wherein the judging whether dangerous riding behaviors occur according to the abnormal points comprises:
acquiring first time sequence data at the abnormal point and second time sequence data before the user rides to the abnormal point from the beginning;
calculating the similarity of the first time sequence data and the second time sequence data;
if the similarity is smaller than a preset threshold value, determining that dangerous riding behaviors do not occur;
and if the similarity is greater than or equal to the preset threshold value, determining that dangerous riding behaviors occur.
3. The riding safety detection method according to claim 2, wherein the calculating the similarity of the first time series data and the second time series data comprises:
and calculating the cosine similarity of the riding speed, the rotating speed and the acceleration at the abnormal point and the riding speed, the rotating speed and the acceleration before the abnormal point from the beginning of riding.
4. The riding safety detection method according to claim 1, wherein the abnormal data is vehicle acceleration, wherein,
if the acceleration of the vehicle changes abnormally in a single direction, determining that the dangerous riding behavior is caused by the abnormality of the vehicle;
and if the acceleration of the vehicle is abnormally changed in multiple directions, determining that the dangerous riding behavior is caused by the riding behavior of the user.
5. The riding safety detection method according to claim 1, wherein the detecting abnormal points in the time series data comprises:
acquiring time sequence data of the current moment;
predicting to obtain time sequence data of the next moment by utilizing the time sequence data of the current moment;
acquiring actual time sequence data at the next moment;
calculating an error between the predicted time series data of the next moment and the actual time series data of the next moment;
judging whether the errors accord with a preset distribution rule or not;
and if the time sequence data does not accord with the preset distribution rule, determining that the time sequence data at the next moment is an abnormal point.
6. A riding safety detection method is applied to electronic equipment installed on a vehicle, and comprises the following steps:
acquiring various riding characteristic data respectively detected by a plurality of sensors arranged on the vehicle;
fitting the various riding characteristic data to obtain time sequence data for representing the riding process of the user;
detecting abnormal points in the time sequence data, and judging whether dangerous riding behaviors occur or not according to the abnormal points;
the riding safety detection method further comprises the following steps:
if dangerous riding behaviors occur, judging whether the time sequence data at the abnormal point is suddenly changed or gradually changed;
if sudden change occurs, determining that the dangerous riding behavior is caused by vehicle abnormality;
and if the gradual change occurs, determining that the dangerous riding behavior is caused by the riding behavior of the user.
7. The utility model provides a safety inspection device rides which characterized in that installs on the vehicle, the safety inspection device rides includes:
the acquisition module is used for acquiring various riding characteristic data respectively detected by a plurality of sensors arranged on the vehicle;
the processing module is used for fitting the various riding characteristic data to obtain time sequence data for representing the riding process of the user;
the detection module is used for detecting abnormal points in the time sequence data and judging whether dangerous riding behaviors occur or not according to the abnormal points;
the device further comprises: the second judgment module is used for calculating the proportion of the abnormal data of the vehicle in a single direction to the total abnormal data of other directions if dangerous riding behaviors occur; the second determining module is used for determining that the dangerous riding behavior is caused by vehicle abnormity if the proportion of the abnormal data in the single direction is higher than that of the total abnormal data in other directions; and if the proportion of the abnormal data in the single direction is not higher than the proportion of the total abnormal data in other directions, determining that the dangerous riding behavior is caused by the riding behavior of the user.
8. The utility model provides a safety inspection device rides which characterized in that installs on the vehicle, the safety inspection device rides includes:
the acquisition module is used for acquiring various riding characteristic data respectively detected by a plurality of sensors arranged on the vehicle;
the processing module is used for fitting the various riding characteristic data to obtain time sequence data for representing the riding process of the user;
the detection module is used for detecting abnormal points in the time sequence data and judging whether dangerous riding behaviors occur or not according to the abnormal points;
the device further comprises: the first judgment module is used for judging whether the time sequence data at the abnormal point is suddenly changed or gradually changed if dangerous riding behaviors occur; the first determination module is used for determining that the dangerous riding behavior is caused by vehicle abnormity if sudden change occurs; and if the gradual change occurs, determining that the dangerous riding behavior is caused by the riding behavior of the user.
9. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to perform the cycling safety detection method according to any one of claims 1-5 or 6.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions for causing a computer to execute the riding safety detection method according to any one of claims 1-5 or 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110157015.9A CN112896388B (en) | 2021-02-04 | 2021-02-04 | Riding safety detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110157015.9A CN112896388B (en) | 2021-02-04 | 2021-02-04 | Riding safety detection method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112896388A CN112896388A (en) | 2021-06-04 |
| CN112896388B true CN112896388B (en) | 2022-11-22 |
Family
ID=76122363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110157015.9A Active CN112896388B (en) | 2021-02-04 | 2021-02-04 | Riding safety detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112896388B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005263196A (en) * | 2003-12-02 | 2005-09-29 | Calsonic Kansei Corp | On-vehicle apparatus control system |
| JP2020166541A (en) * | 2019-03-29 | 2020-10-08 | 株式会社日本総合研究所 | Accident responsibility identifying method, operation assisting method, accident responsibility identifying device, and computer program |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210133871A1 (en) * | 2014-05-20 | 2021-05-06 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle operation feature usage recommendations |
| CN105489007A (en) * | 2015-12-16 | 2016-04-13 | 浙江中科正方电子技术有限公司 | Vehicle management method and system |
| CN108089962A (en) * | 2017-11-13 | 2018-05-29 | 北京奇艺世纪科技有限公司 | A kind of method for detecting abnormality, device and electronic equipment |
| CN111846046B (en) * | 2019-04-03 | 2022-05-20 | 杭州青奇科技有限公司 | System, method and device for detecting safety of bicycle |
| CN110807436B (en) * | 2019-11-07 | 2022-10-18 | 深圳鼎然信息科技有限公司 | Dangerous driving behavior recognition and dangerous event prediction method, device and storage medium |
| CN111862386A (en) * | 2020-07-03 | 2020-10-30 | 上海钧正网络科技有限公司 | Accident recording method, device, medium and server for vehicle |
-
2021
- 2021-02-04 CN CN202110157015.9A patent/CN112896388B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005263196A (en) * | 2003-12-02 | 2005-09-29 | Calsonic Kansei Corp | On-vehicle apparatus control system |
| JP2020166541A (en) * | 2019-03-29 | 2020-10-08 | 株式会社日本総合研究所 | Accident responsibility identifying method, operation assisting method, accident responsibility identifying device, and computer program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112896388A (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107757525B (en) | Autonomous vehicle fault mode management system and method | |
| US8521357B2 (en) | Impaired operation detection method | |
| CN111311914B (en) | Vehicle driving accident monitoring method and device and vehicle | |
| US8155798B2 (en) | Method and device for determining the roll angle of a motorcycle | |
| US9469343B2 (en) | System, method, and computer-readable recording medium for lane keeping control | |
| JP2004352116A (en) | Vehicular and driver's behavior analyzing system | |
| CN110660194A (en) | Driving monitoring early warning method and system | |
| CN111038480B (en) | Automatic driving execution system and automatic driving control command execution method | |
| KR102239992B1 (en) | Methods for warning of vehicle collision and Apparatuses thereof | |
| JP2019523486A (en) | Method for detecting and verifying traffic vehicle anomalous stress recorded by an in-vehicle device adapted to obtain data relating to traffic vehicle movement and / or driving parameters | |
| CN102529850B (en) | Safe state monitoring method of motor vehicle based on wheel load type intelligent sensing | |
| CN101480946A (en) | Wheel load-based type intelligent sensing wheel brake performance monitoring methods | |
| CN101480904A (en) | Method for monitoring dynamic load of intelligent sensing wheel based on wheel load | |
| US20230281744A1 (en) | Vehicle rating system | |
| JP2021526476A (en) | Tread wear monitoring system and method | |
| CN112896388B (en) | Riding safety detection method and device, electronic equipment and storage medium | |
| US10528989B1 (en) | Vehicle rating system | |
| US20230026459A1 (en) | Method and device for classifying an accident event involving a two-wheeled vehicle | |
| CN114162241A (en) | Multi-person riding detection method, device and system for electric bicycle and electronic equipment | |
| CN107921962B (en) | Method for operating a driver assistance system in a motor vehicle and motor vehicle | |
| CN115938114A (en) | Processing system, method, device, terminal and medium for automatic driving vehicle data | |
| CN114655343A (en) | Riding state detection method and device and electric bicycle | |
| FR3015413A1 (en) | METHOD FOR DETECTING A CURVED CROSS SECTION OF A TRANSVERSE TILT FROM A MOTOR VEHICLE MOVING THEREWITH | |
| US20240118175A1 (en) | System and method for identifying a tire contact length from radial acceleration signals | |
| US11682289B1 (en) | Systems and methods for integrated traffic incident detection and response |
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 |