CN110728218A - Dangerous driving behavior early warning method and device, electronic equipment and storage medium - Google Patents
Dangerous driving behavior early warning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110728218A CN110728218A CN201910930462.6A CN201910930462A CN110728218A CN 110728218 A CN110728218 A CN 110728218A CN 201910930462 A CN201910930462 A CN 201910930462A CN 110728218 A CN110728218 A CN 110728218A
- Authority
- CN
- China
- Prior art keywords
- driving
- driving behavior
- image information
- dangerous
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000006399 behavior Effects 0.000 claims abstract description 275
- 238000001514 detection method Methods 0.000 claims abstract description 74
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000003709 image segmentation Methods 0.000 claims description 36
- 238000004590 computer program Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 230000011218 segmentation Effects 0.000 description 8
- 241001282135 Poromitra oscitans Species 0.000 description 6
- 206010048232 Yawning Diseases 0.000 description 6
- 210000003128 head Anatomy 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000003702 image correction Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
- 230000007096 poisonous effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a dangerous driving behavior early warning method, a dangerous driving behavior early warning device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring first driving image information, wherein the first driving image information comprises a driver; preprocessing the first driving image information to obtain second driving image information, wherein the second driving image information comprises driving behaviors; performing characteristic detection on the driving behaviors of the second driving image, and judging whether dangerous driving behaviors are included or not; and if the dangerous driving behavior is contained, sending out an early warning prompt of the dangerous driving behavior. Because the driving behavior of the driver is detected, the early warning prompt for the driver is sent out after the driving behavior of the driver is judged to be dangerous driving behavior, and the early warning prompt for the driver can be effectively carried out after the dangerous driving behavior appears in the driver.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a dangerous driving behavior early warning method and device, electronic equipment and a storage medium.
Background
Along with economic development, more and more people can select to drive by themselves when going out, traffic flow on a road is larger and larger, serious consequences such as road congestion, casualties and the like can be caused if a traffic accident occurs, and a plurality of reasons are caused to the occurrence of the traffic accident, wherein part of the reasons are caused by dangerous driving behaviors of a driver, such as drunk driving, fatigue driving, long-time driving and the like. In the process of driving a vehicle, a driver focuses on driving, and cannot pay attention to driving behaviors, once the driver is in driving conditions such as drunk driving, fatigue driving and long-time driving, the attention of the driver is weaker, however, dangerous driving behaviors of the driver cannot be detected, and therefore early warning cannot be given to the dangerous driving behaviors of the driver.
Disclosure of Invention
The embodiment of the invention provides a method and a device for early warning of dangerous driving behaviors, electronic equipment and a storage medium, which can effectively make an effective early warning of the dangerous driving behaviors of a driver.
In a first aspect, an embodiment of the present invention provides a method for early warning of dangerous driving behavior, including:
acquiring first driving image information, wherein the first driving image information comprises a driver;
preprocessing the first driving image information to obtain second driving image information, wherein the second driving image information comprises driving behaviors;
performing characteristic detection on the driving behaviors of the second driving image, and judging whether dangerous driving behaviors are included or not;
and if the dangerous driving behavior is contained, sending out an early warning prompt of the dangerous driving behavior.
In a second aspect, an embodiment of the present invention provides an early warning device for dangerous driving behavior, including:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring first driving image information which comprises a driver;
the preprocessing module is used for preprocessing the first driving image information to obtain second driving image information, and the second driving image information comprises driving behaviors;
the detection module is used for carrying out characteristic detection on the driving behaviors of the second driving image and judging whether dangerous driving behaviors are included or not;
and the prompt module is used for sending out an early warning prompt of the dangerous driving behavior if the dangerous driving behavior is contained.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the early warning method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the early warning method for dangerous driving behaviors provided by the embodiment of the invention.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the steps in the method for warning dangerous driving behavior provided by the embodiment of the present invention.
In the embodiment of the invention, first driving image information is acquired, wherein the first driving image information comprises a driver; preprocessing the first driving image information to obtain second driving image information, wherein the second driving image information comprises driving behaviors; performing characteristic detection on the driving behaviors of the second driving image, and judging whether dangerous driving behaviors are included or not; and if the dangerous driving behavior is contained, sending out an early warning prompt of the dangerous driving behavior. Because the driving behavior of the driver is detected, the early warning prompt for the driver is sent out after the driving behavior of the driver is judged to be dangerous driving behavior, and the early warning prompt for the driver can be effectively carried out after the dangerous driving behavior appears in the driver.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic system architecture diagram of an application of an early warning method for dangerous driving behaviors according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of an early warning method for dangerous driving behaviors according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of another method for warning dangerous driving behavior according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart illustrating another method for warning dangerous driving behavior according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart illustrating another method for warning dangerous driving behavior according to an embodiment of the present invention;
FIG. 6 is a schematic flow chart illustrating another method for warning dangerous driving behavior according to an embodiment of the present invention;
FIG. 7 is a flowchart illustrating another method for warning dangerous driving behavior according to an embodiment of the present invention;
FIG. 8 is a flowchart illustrating another method for warning dangerous driving behavior according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an early warning device for dangerous driving behaviors according to an embodiment of the present invention;
FIG. 10 is a block diagram of a pre-processing module 902 according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of another dangerous driving behavior warning device provided in the embodiment of the present invention;
fig. 12 is a schematic structural diagram of a first detecting module 903 according to an embodiment of the present invention;
fig. 13 is a schematic structural diagram of another first detecting module 903 according to an embodiment of the present invention;
fig. 14 is a schematic structural diagram of a first prompt module 904 according to an embodiment of the present invention;
fig. 15 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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.
To further clearly describe the invention intent of the present invention, please refer to fig. 1, fig. 1 is a schematic diagram of an alternative system architecture provided by the embodiment of the present invention, as shown in fig. 1, the alternative system architecture 100 includes user terminal devices 101, 102, 103, a network 104, a server 105 and a vehicle-mounted terminal device 106. The network 104 is a medium to provide a communication link between the user terminal devices 101, 102, 103 and the server 105, and the network 104 is also a medium to provide a communication link between the user terminal devices 101, 102, 103 and the in-vehicle terminal device 106. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the user terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or transmit communication data information, and the like, and may also use the user terminal devices 101, 102, 103 to interact with the vehicle-mounted terminal device 106 through the network 104 to acquire image information collected by the vehicle-mounted terminal device 106. Various client applications, such as warning software for dangerous driving behavior, etc., may be installed on the user terminal devices 101, 102, 103.
The user terminal devices 101, 102, 103 may be various electronic devices having a prompt function and supporting voice prompt, vibration prompt, music prompt, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), laptop portable computers, in-vehicle central control and fixed computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for early warning of dangerous driving behavior on the terminal devices 101, 102, 103.
The in-vehicle terminal device 106 may be a device that provides an image capturing function, such as: the vehicle event data recorder, on-vehicle camera, self-defined installation camera etc. can gather the image acquisition equipment of navigating mate image.
It should be noted that the warning method for dangerous driving behaviors provided in the embodiments of the present application is generally executed by a server/terminal device, and accordingly, the warning device for dangerous driving behaviors is generally disposed in the server/terminal device.
In some possible embodiments, the driver may be image-captured using the user terminal device 101, 102, 103 without the vehicle terminal device 106. In other possible embodiments, the vehicle-mounted terminal device 106 may also upload the acquired image information to the server 105 through the network 104 for processing, without going through the user terminal devices 101, 102, 103.
It should be understood that the number of user terminal devices, networks, servers, and in-vehicle terminal devices in fig. 1 is merely illustrative. There may be any number of user terminal devices, networks, servers, and in-vehicle terminal devices, as desired for implementation.
Referring to fig. 2, fig. 2 is a schematic flow chart of an early warning method for dangerous driving behavior according to an embodiment of the present invention, as shown in fig. 2, including the following steps:
201. first driving image information is acquired, and the first driving image information comprises a driver.
The first driving image information can be acquired by a vehicle-mounted terminal arranged in a vehicle, the vehicle-mounted terminal can be an image acquisition device with a shooting function, an acquisition object of the image acquisition device is a driver, and the image acquisition device can be a camera built in a driving recorder or a camera which is arranged at other positions and can acquire images of the driver. The camera can be a 3D camera or a 2D camera, the 3D camera can acquire depth information of an image, and the body posture and driving behavior of a driver can be detected more accurately in an image detection engine based on the image depth information; the 2D camera acquires image information, can detect in an image detection engine based on the 2D image information, and is low in hardware cost; in some possible implementations, the image capturing device may also be a camera of the user end, and at this time, the user end needs to be adjusted to an angle and a posture capable of capturing the image of the driver. The first driving image information may be still picture information or dynamic video stream information.
The driver may also be referred to as a driver or a driver.
In some possible embodiments, when the first driving image information is picture information, the obtaining of the first driving image information may be taking a picture by a camera, and the first driving image information may be multiple-picture information, may be continuous multiple-picture information, and may be taken by the camera at regular time. Or the image frame obtained by intercepting the video stream information shot by the camera. When the first driving image information is captured in the video stream information captured by the camera, the image quality of each video frame in the video stream information may be evaluated according to an image quality evaluation algorithm, and an image frame with the image quality reaching a preset quality threshold may be captured.
202. And preprocessing the first driving image information to obtain second driving image information, wherein the second driving image information comprises driving behaviors.
In this step, the preprocessing may include image correction, image enhancement, graying, image segmentation, and the like for the first driving image information. When the first driving image information is video stream information, the preprocessing further includes decoding the video stream information to obtain video stream image frames, and then performing image correction, image enhancement, graying, image segmentation and other processing on the video stream image frames, where the preprocessing may be performed on a vehicle-mounted terminal device, or on a user terminal device, or in a server. The second driving image information includes driving behaviors, it is understood that the second driving image obtained by preprocessing the first image information further includes driving behaviors of the driver, and the driving behaviors may include a relationship between a hand and a steering wheel, a relationship between a head and a seat, a relationship between a foot and a pedal, a face of a person, and the like of the driver. In some possible embodiments, the second driving image may include at least one of a hand and a steering wheel, a head and a seat, a foot and a pedal, and a face of the driver, and at least one of the above may be understood as including only one item, including multiple items, or including all of them.
203. And performing characteristic detection on the driving behavior of the second driving image.
In this step, the characteristic detection of the driving behavior may be performed by an image detection engine, the image detection engine is trained with an image detection function, the driving behavior of the second driving image may be subjected to characteristic extraction by a convolutional neural network in the image detection engine, and the extracted characteristic value of the driving behavior is compared with the characteristic value of the dangerous driving behavior in the dangerous driving behavior database.
204. And judging whether dangerous driving behaviors are included or not.
And judging whether the similarity between the extracted characteristic value of the driving behavior and the characteristic value of the dangerous driving behavior in the dangerous driving behavior database is greater than or equal to a preset threshold, if so, determining that the driving behavior is the dangerous driving behavior, and if not, determining that the driving behavior is not the dangerous driving behavior. The dangerous driving behavior database stores characteristic values of various dangerous driving behaviors, and the dangerous driving behavior database can be understood as an independent database or a storage area for storing the characteristic values of the dangerous driving behaviors in a large database. If yes, go to step 105, otherwise go to step 106.
205. And sending out early warning prompt of dangerous driving behaviors.
The dangerous driving behavior is determined in step 103, and the early warning prompt may be a voice prompt, a vibration prompt, a music prompt, or the like. The voice prompt may be a prompt to the driver, such as: the vibration prompt can be buzzing vibration, and the music prompt can be used for automatically playing preset music capable of promoting spirit when the driver is in dangerous driving behaviors for a long time or in fatigue driving behaviors. The early warning prompt may be a prompt through a user terminal, or may be a prompt through a vehicle-mounted prompt terminal (such as a vehicle-mounted player), where the early warning prompt may prompt a driver, and may also prompt a traffic department, and in some possible embodiments, may also prompt other people bound with a contact manner, taking family as an example: "lovely user, your family XX is in dangerous driving behavior, please remind him to pay attention to driving safety", etc.
206. And sending out a prompt of normal driving or not sending out any prompt.
The normal prompt can be a voice prompt for a driver, or an information prompt for other people bound with contact information, and the information prompt can be a voice, a short message, a mail or other information notification mode. Voice prompts for the driver such as: "lovely driver, you are now in normal driving behavior, please keep"; prompting other people bound with the contact information can be performed by taking family as an example: "lovely user, your family XX is in normal driving behavior, please be relieved, and remind him to pay attention to driving safety", etc.
It should be noted that the warning method for dangerous driving behaviors provided by the embodiment of the present invention may be applied to a warning device for dangerous driving behaviors, for example: the device can be used for early warning dangerous driving behaviors, such as a mobile phone, a vehicle data recorder, a vehicle-mounted central control, a computer, a server and the like.
In the embodiment of the invention, first driving image information is acquired, wherein the first driving image information comprises a driver; preprocessing the first driving image information to obtain second driving image information, wherein the second driving image information comprises driving behaviors; performing characteristic detection on the driving behaviors of the second driving image, and judging whether dangerous driving behaviors are included or not; and if the dangerous driving behavior is contained, sending out an early warning prompt of the dangerous driving behavior. Because the driving behavior of the driver is detected, the early warning prompt for the driver is sent out after the driving behavior of the driver is judged to be dangerous driving behavior, and the early warning prompt for the driver can be effectively carried out after the dangerous driving behavior appears in the driver.
Referring to fig. 3, fig. 3 is a schematic flowchart illustrating a specific process of step 202 in the embodiment of fig. 2, as shown in fig. 3, including the following steps:
301. and carrying out image segmentation on the first driving image information through an image segmentation algorithm to obtain a plurality of image segmentation areas.
The image segmentation may be one or a combination of methods such as threshold-based segmentation, edge-based segmentation, region-based segmentation, cluster analysis-based image segmentation, wavelet transform-based segmentation, mathematical morphology-based segmentation, and artificial neural network-based segmentation. In the embodiment of the present invention, threshold-based segmentation is preferred, and the image may be segmented by using a histogram, that is, the grayscale histogram of the image is divided into several classes by using one or several thresholds, and pixels in the image whose grayscale values are in the same class are considered to belong to the same feature. The image in the first driving image information is segmented into a plurality of image segmentation areas by an image segmentation algorithm, such as: hand and steering wheel area, foot and pedal area, head and seat area, face area, other areas, etc.
302. And detecting the driving behaviors of the image segmentation areas, and extracting the image segmentation areas containing the driving behaviors to obtain the second driving image information.
The plurality of image segmentation regions are the image segmentation regions obtained in step 301, the detection of the driving behavior of the image segmentation regions may be performed by comparing pixel thresholds of the image segmentation regions, and the pixel thresholds may be understood as pixel thresholds of the template, such as: the method comprises the steps of taking pixel values on templates of a hand and a steering wheel as pixel threshold values, respectively calculating the pixel value of each image segmentation region when detecting a plurality of image segmentation regions, comparing the pixel value with the pixel threshold values, and calculating the similarity between the pixel value of each image segmentation region and the pixel threshold value, if an image segmentation region with the similarity between the pixel value and the pixel threshold value being greater than 98% exists, determining that the image segmentation region comprises the hand and the steering wheel, and taking the image with the maximum similarity as a second driving image when the image segmentation regions exist in a plurality.
Therefore, the first driving image is subjected to image segmentation, the obtained second driving image comprises the driving behaviors, and when the second driving image is detected, other background images can be prevented from being detected, so that the detection calculated amount is reduced, and the detection speed of dangerous driving behaviors is improved.
The image segmentation may be performed on the in-vehicle terminal device, on the user terminal device, or in the server.
Referring to fig. 4, fig. 4 is a schematic flow chart of another warning method for dangerous driving behavior according to an embodiment of the present invention, as shown in fig. 4, including the following steps:
400. the current driving environment condition is acquired.
The driving environment conditions include urban driving environment, highway driving environment, daytime driving environment, night driving environment, provincial or national road driving environment, rural road driving environment, and the like.
The driving environment condition can be judged according to the image acquired by the image acquisition device, for example, when the acquired image contains residential buildings or more pedestrians, the driving environment can be considered as an urban driving environment; when the acquired image contains a speed limit sign of the highway or a service area sign, the highway driving environment can be considered to be adjusted; when the light for acquiring the image is good, the driving environment in the daytime can be considered; when the light of the acquired image is not good, the driving environment at night can be considered; when the acquired image contains a provincial road or national road mark, the image can be regarded as a provincial road or national road driving environment; when the acquired image includes the field and crops, the environment can be considered as a rural road driving environment.
The above-described vehicle driving modes include a fuel-saving mode, a sport mode, an off-road mode, a cruise mode, and the like. The above-described driving mode of the vehicle may be acquired from a control system of the vehicle.
401. And acquiring first driving image information acquired by the image acquisition equipment in a timing or real-time manner according to the current environmental driving condition or the vehicle driving mode.
In the step, the image acquisition device can acquire images of the driver at regular time or in real time, and then the image acquisition device transmits the acquired first driving image information to the user terminal device or the server at regular time or in real time.
The above-described timing acquisition or real-time acquisition may be determined according to the current environmental driving conditions.
For example, when the current driving environment condition is an urban driving environment, the first driving image information acquired by the image acquisition device can be acquired in real time because the urban pedestrian volume and the urban traffic volume are large.
When the current driving environment condition is an expressway driving environment, the driver needs to keep high attention all the time due to high vehicle speed on the expressway, and first driving image information acquired by the image acquisition equipment can be acquired in real time.
When the current driving environment condition is a daytime driving environment, the first driving image information acquired by the image acquisition device can be acquired in real time on a road section with high pedestrian flow and high traffic flow, and the first driving image information acquired by the image acquisition device can be acquired at regular time on a road section with low pedestrian flow and low traffic flow.
When the current driving environment condition is a night driving environment, the night driving condition is poor, the driver needs to keep high attention all the time, and the first driving image information acquired by the image acquisition equipment can be acquired in real time.
When the current driving environment condition is a provincial road or national road driving environment, the first driving image information acquired by the image acquisition equipment can be acquired in real time due to the fact that the traffic flow of the provincial road or national road driving environment is small.
When the current driving environment condition is a rural road driving environment, the first driving image information acquired by the image acquisition equipment can be acquired in real time due to the fact that traffic flow of the rural road driving environment is low and signal quality is low.
The above-described timing acquisition or real-time acquisition may be determined according to the current vehicle driving mode.
For example, when the vehicle is in the fuel-saving mode driving, the first driving image information acquired by the image acquisition device can be acquired at regular time because the vehicle speed is not high.
When the vehicle is in a motion mode, the first driving image information acquired by the image acquisition device can be acquired in real time due to the fact that the vehicle speed is high.
When the vehicle is in the off-road mode, the driver needs to keep high attention all the time due to the complex road condition, and the first driving image information acquired by the image acquisition equipment can be acquired in real time.
When the vehicle is in a cruising mode, the association degree between the vehicle and a driver is low due to low vehicle speed, and the first driving image information collected by the image collecting device can be obtained at regular time.
402. And preprocessing the first driving image information to obtain second driving image information, wherein the second driving image information comprises driving behaviors.
403. And performing characteristic detection on the driving behavior of the second driving image.
404. Judging whether dangerous driving behaviors are included or not; if yes, go to step 405, otherwise go to step 406.
405. And sending out early warning prompt of dangerous driving behaviors.
406. And sending out a prompt of normal driving or not sending out any prompt.
In the embodiment of the invention, the collected image information of the driver is detected in a timing or real-time manner, so that dangerous driving behaviors of the driver can be detected in time. In addition, the acquisition mode is determined according to the current environmental driving condition or the vehicle driving mode, the mode of the first image can be switched under different current environmental driving conditions or vehicle driving modes, and the configuration of resources is optimized under the condition that the timeliness of detection is guaranteed.
Referring to fig. 5, fig. 5 is a schematic flow chart of another warning method for dangerous driving behavior according to an embodiment of the present invention, where as shown in fig. 5, the second driving image information includes a face of a driver, and the dangerous driving behavior includes continuous driving, the method further includes the following steps:
501. and performing face detection on the second driving image at the time of T1 to obtain a first face detection result.
The face detection may be performed on the face in the second driving image, and the first face detection result is used to indicate the features of the face at time T1, that is, to indicate who the driver is at time T1. The first face detection result may be a face feature value extracted by an image detection engine.
502. And performing face detection on the second driving image at the time of T2 to obtain a second face detection result.
The second face detection result is used to indicate the face features at time T2, i.e. to indicate who the driver is at time T2. The second face detection result may be a face feature value extracted by an image detection engine.
503. And calculating the similarity of the first face detection result and the second face detection result.
The similarity calculation may be euclidean distance calculation, cosine calculation, pearson correlation coefficient calculation, or the like between the face feature value in the first face detection result and the face feature value in the second face detection result.
504. Judging whether the driver at the time T1 is the same as the driver at the time T2; if yes, go to step 505, otherwise go to step 506.
And judging whether the time of T1 is the same as the time of T2 according to the similarity obtained by calculation in the step 503. Specifically, a threshold may be preset, so that whether the similarity is greater than the threshold is determined by comparing the similarity with the threshold, and if the similarity is greater than or equal to the threshold, it is indicated that the drivers at time T1 and time T2 are the same, and are the same driver. If the time is less than the time threshold, it is indicated that the driver at the time T1 is not the same as the driver at the time T2, and the driver may be changed by stopping the vehicle halfway. The difference between the time T1 and the time T2 is equal to or greater than a predetermined time, which may be a continuous driving time specified by traffic regulations, for example, 4 hours, or may be set by the driver.
505. If the driving condition is the same, the early warning prompt of continuous driving is sent out.
The early warning prompt of the continuous driving can be a voice prompt, a vibration prompt, a music prompt and the like.
506. If the current state is different from the current state, the current state is kept and no early warning prompt is carried out.
In some possible embodiments, the first detection result and the second detection result may also be driver identity information after identifying the driver. The determination of whether the driver is the same at time T1 and time T2 may be based on driver identification information, which may be information such as name, identification number, age, and the like.
The driver can keep the current state without early warning prompt, so that the condition that the attention of the driver in normal driving is dispersed due to prompt information can be avoided.
Thus, by determining whether the driver at time T1 is the same as the driver at time T2, it can be more accurately determined whether the driver has been driving continuously for a long time.
Referring to fig. 6, fig. 6 is a schematic flowchart illustrating a specific process of step 203 in the embodiment of fig. 2, as shown in fig. 6, including the following steps:
601. and extracting the driving behavior characteristic value of the second driving image.
In the embodiment of the invention, the dangerous driving behaviors comprise illegal driving behaviors, wherein the illegal driving behaviors can be that a user holds a steering wheel with one hand, leaves the steering wheel with two hands, does not watch the front of a road, continuously shakes the body (drunk driving or poisonous driving), places feet on an accelerator and a brake pedal simultaneously, and drives with bare feet, high-heeled shoes, slippers and the like. The driving behavior may include the relationship between the hands and the steering wheel, the relationship between the head and the seat, the relationship between the feet and the pedals, the human face, and the like of the driver. The driving behavior feature value may be extracted by an image detection engine, and specifically, the feature may be extracted by a convolutional neural network in the image detection engine.
602. And calculating the similarity between the driving behavior characteristic value and a preset illegal driving behavior characteristic value.
The driving behavior feature value may be obtained in step 501, and the preset violating driving behavior feature value may be the violating driving behavior feature value stored in the dangerous driving behavior database, and the driving behavior feature value is subjected to traversal comparison with the violating driving behavior feature value in the dangerous driving behavior database, so as to obtain the similarity between the driving behavior feature value and each violating driving behavior feature value in the dangerous driving behavior database. The similarity calculation may be a euclidean distance calculation, a cosine calculation, a pearson correlation coefficient calculation, or the like, between the driving behavior feature value and each of the illegal driving behavior feature values in the dangerous driving behavior database.
603. And judging whether the illegal driving behaviors are included or not based on the similarity of the driving behavior characteristic value and a preset illegal driving behavior characteristic value.
The above determination may be to set a similarity threshold, and determine whether the driving behavior is included by determining a relationship between the similarity between the driving behavior characteristic value and a preset violating driving behavior characteristic value and the similarity threshold, for example: and extracting characteristic values of the hand and the steering wheel, comparing the characteristic values with characteristic values of the illegal driving behaviors that the hand holds the steering wheel with one hand and the two hands leave the steering wheel, and if the similarity between the characteristic values of the hand and the steering wheel and the characteristic values of the illegal driving behaviors that the hand holds the steering wheel with one hand or the two hands leave the steering wheel with two hands is greater than a threshold value, determining that the illegal driving behaviors are contained. And extracting characteristic values of a body (including a head) and a seat, comparing the characteristic values with characteristic values of illegal driving behaviors which are not watched on the front of the road or continuously shaken by the body, and if the similarity between the body (including the head) and the characteristic values of the illegal driving behaviors which are not watched on the front of the road or continuously shaken by the body is greater than a threshold value, determining that the illegal driving behaviors are included.
By comparing the driving behavior with the illegal driving behavior, whether the driver is dangerous driving or not can be quickly judged.
Referring to fig. 7, fig. 7 is another specific flowchart illustrating step 203 in the embodiment of fig. 2, as shown in fig. 7, including the following steps:
701. and extracting the face characteristic value of the driver in the second driving image.
In the embodiment of the present invention, the dangerous driving behavior includes fatigue driving behavior, and the fatigue driving behavior may be that the eyes of the driver are opened to a small degree, the mouth is opened to yawning, the eyes are kneaded by hands, and the like. The driving behavior described above may include the degree of opening of the eyes, the degree or time of opening of the mouth, the relationship between the hands and the eyes, and the like of the driver. The driving behavior feature value may be extracted by an image detection engine, and specifically, the feature may be extracted by a convolutional neural network in the image detection engine.
702. And calculating the similarity between the face characteristic value and preset fatigue face characteristics.
The driving behavior feature value may be obtained in step 501, and the preset fatigue driving behavior feature value may be a fatigue driving behavior feature value stored in the dangerous driving behavior database, and the driving behavior feature value is compared with the fatigue driving behavior feature value in the dangerous driving behavior database in a traversing manner to obtain a similarity between the driving behavior feature value and each fatigue driving behavior feature value in the dangerous driving behavior database. The similarity calculation may be a euclidean distance calculation, a cosine calculation, a pearson correlation coefficient calculation, or the like, between the driving behavior feature value and each of the fatigue driving behavior feature values in the dangerous driving behavior database.
703. And judging whether the fatigue driving behavior is included or not based on the similarity between the face characteristic value and the preset fatigue face characteristic.
The above determination may be to set a similarity threshold, and determine whether the driving behavior is included by determining a relationship between a similarity between the driving behavior feature value and a preset violating driving behavior feature value and the similarity threshold. Specifically, the characteristic values of the hands and the eyes may be extracted and compared with the characteristic value of the fatigue driving behavior of the eyes kneaded by the hands, and if the similarity between the characteristic value of the hand and the eye characteristic value and the characteristic value of the fatigue driving behavior of the eyes kneaded by the hands is greater than a threshold, the fatigue driving behavior may be considered to be included. The feature value of the eye-opening degree may be extracted, and compared with the feature value of the fatigue driving behavior with a small eye-opening degree, and if the similarity between the feature value of the eye-opening degree and the feature value of the fatigue driving behavior with a small eye-opening degree is greater than a threshold value, it may be considered that the fatigue driving behavior is included. The characteristic value of the degree of opening the mouth can be extracted and compared with the characteristic value of the fatigue driving behavior of yawning by opening the mouth, and if the similarity between the characteristic value of the degree of opening the mouth and the characteristic value of the fatigue driving behavior of yawning by opening the mouth is greater than a threshold value, the fatigue driving behavior can be considered to be contained.
In some possible embodiments, the feature value of the mouth opening degree in the continuous second driving image information may be extracted, after the comparison with the feature value of the fatigue driving behavior of yawning on the mouth opening degree, if the feature value is larger than a threshold value, the continuous time is calculated, and whether the fatigue driving behavior of yawning on the mouth opening degree is determined according to the continuous time.
In some possible embodiments, when the driver starts driving the vehicle, the facial image information of the driver may be acquired, the eye opening degree characteristic value in the facial image information may be extracted and stored in the database for comparison with the extracted eye opening degree characteristic value, so that the driver with small eyes may be prevented from being warned frequently.
By carrying out fatigue detection on the face of the driver, whether the face of the driver is in fatigue driving or not can be accurately known.
Referring to fig. 8, fig. 8 is a schematic flow chart of another warning method for dangerous driving behavior according to an embodiment of the present invention, and as shown in fig. 8, the method includes the following steps:
801. first driving image information is acquired, and the first driving image information comprises a driver.
802. And preprocessing the first driving image information to obtain second driving image information, wherein the second driving image information comprises driving behaviors.
803. And performing characteristic detection on the driving behavior of the second driving image.
804. Judging whether dangerous driving behaviors are included or not; if the dangerous driving behavior is included, step 805 is executed, and if the dangerous driving behavior is not included, step 807 is executed.
805. And judging the danger level of the dangerous driving behavior.
The danger level may be 5, and the danger level is directly related to the danger level, for example, the danger level 1 may be one hand holding a steering wheel, eating, etc., the danger level 2 may be no-eye-gaze in front of a road, yawning in mouth, rubbing eyes with hands, etc., the danger level 3 may be small in eye opening degree, continuous shaking of a body, etc., the danger level 4 may be a case where a plurality of levels 1 or 2 are present, and the danger level 5 may be a case where at least one level 3, a plurality of levels 1 or 2 are present.
806. And sending out early warning prompts of corresponding danger levels according to the danger levels of the dangerous driving behaviors.
The danger levels can correspond to different early warning prompts, for example, the early warning prompt corresponding to the danger level of level 1 or level 2 can be a voice prompt, a vibration prompt, a music prompt and the like for the driver, and the danger level of level 3 or above can prompt a traffic management department and a binding contact person while early warning prompt is carried out for the driver.
807. And sending out a prompt of normal driving or not sending out any prompt.
Therefore, different early warning prompts can be made according to different danger levels, and the effect of the early warning prompts is improved.
Referring to fig. 9, fig. 9 is a schematic structural diagram of an early warning device for dangerous driving behaviors according to an embodiment of the present invention, and as shown in fig. 9, the device 900 includes:
an obtaining module 901, configured to obtain first driving image information, where the first driving image information includes a driver;
a preprocessing module 902, configured to preprocess the first driving image information to obtain second driving image information, where the second driving image information includes driving behaviors;
a first detection module 903, configured to perform feature detection on the driving behavior of the second driving image, and determine whether a dangerous driving behavior is included;
the first prompting module 904 is configured to send an early warning prompt of the dangerous driving behavior if the dangerous driving behavior is included.
Optionally, as shown in fig. 10, the preprocessing module 902 includes:
a segmentation unit 9021, configured to perform image segmentation on the first driving image information through an image segmentation algorithm to obtain a plurality of image segmentation areas;
a detecting unit 9022, configured to perform driving behavior detection on the plurality of image partition regions, extract an image partition region including a driving behavior, and obtain the second driving image information.
Optionally, the obtaining module 901 includes:
a first acquisition unit configured to acquire a current driving environment condition or a vehicle driving mode;
and the second acquisition unit is used for acquiring the first driving image information acquired by the image acquisition equipment in a timing or real-time manner according to the current environment driving condition or the vehicle driving mode.
The method is also used for acquiring first driving image information, and the first driving image information comprises a driver.
Optionally, as shown in fig. 11, the second driving image information includes a face of the driver, the dangerous driving behavior includes continuous driving, and the apparatus 900 further includes:
the second detection module 905 is configured to perform face detection on the second driving image at time T1 to obtain a first face detection result;
the third detection module 906 is configured to perform face detection on the second driving image at time T2 to obtain a second face detection result;
a person judgment module 907 configured to judge whether the drivers are the same according to the similarity between the first face detection result and the second face detection result;
a second prompt module 908, configured to send an early warning prompt for continuous driving if the driving times are the same;
wherein the time difference between the T1 time and the T2 time is more than or equal to a preset time.
Optionally, as shown in fig. 12, the dangerous driving behavior includes an illegal driving behavior, and the first detecting module 903 includes:
a first extraction unit 9031 configured to extract a driving behavior feature value of the second driving image;
a first calculating unit 9032, configured to calculate a similarity between the driving behavior characteristic value and a preset violation driving behavior characteristic value;
a first determining unit 9033, configured to determine whether the illegal driving behavior is included based on a similarity between the driving behavior characteristic value and a preset illegal driving behavior characteristic value.
Optionally, as shown in fig. 13, the second driving image information includes a face of the driver, and the first detection module 903 includes:
a second extraction unit 9034, configured to extract a face feature value of a driver in the second driving image;
a second calculating unit 9035, configured to calculate similarity between the face feature value and a preset fatigue face feature;
a second judging unit 9036, configured to judge whether a fatigue driving behavior is included based on a similarity between the face feature value and a preset fatigue face feature.
Optionally, as shown in fig. 14, the first prompting module 904 includes:
a third judgment unit 9041, configured to judge a risk level of the dangerous driving behavior;
and the prompt unit 9042 is configured to send an early warning prompt of a corresponding danger level according to the danger level of the dangerous driving behavior.
The early warning device for dangerous driving behaviors provided by the embodiment of the invention can realize each implementation mode in the method embodiments of fig. 2-8 and corresponding beneficial effects, and is not repeated here for avoiding repetition.
Referring to fig. 15, fig. 15 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 15, including: a memory 1502, a processor 1501 and a computer program stored on the memory and executable on the processor, wherein:
the processor 1501 is configured to call the computer program stored in the memory 1502, and execute the following steps:
acquiring first driving image information, wherein the first driving image information comprises a driver;
preprocessing the first driving image information to obtain second driving image information, wherein the second driving image information comprises driving behaviors;
performing characteristic detection on the driving behaviors of the second driving image, and judging whether dangerous driving behaviors are included or not;
and if the dangerous driving behavior is contained, sending out an early warning prompt of the dangerous driving behavior.
Optionally, the preprocessing the first driving image information performed by the processor 1501 to obtain second driving image information includes:
carrying out image segmentation on the first driving image information through an image segmentation algorithm to obtain a plurality of image segmentation areas;
and detecting the driving behaviors of the image segmentation areas, and extracting the image segmentation areas containing the driving behaviors to obtain the second driving image information.
Optionally, the acquiring the first driving image information performed by the processor 1501 includes:
acquiring a current driving environment condition or a vehicle driving mode;
and acquiring first driving image information acquired by an image acquisition device in a timing or real-time manner according to the current environment driving condition or the vehicle driving mode.
Optionally, the second driving image information includes a face of the driver, the dangerous driving behavior includes continuous driving, and the processor 1501 further performs the steps of:
performing face detection on the second driving image at the time of T1 to obtain a first face detection result;
performing face detection on the second driving image at the time of T2 to obtain a second face detection result;
judging whether the drivers are the same or not according to the similarity of the first face detection result and the second face detection result;
if the driving condition is the same, sending out early warning prompts of continuous driving;
wherein the time difference between the T1 time and the T2 time is more than or equal to a preset time.
Optionally, the dangerous driving behavior includes an illegal driving behavior, and the performing, by the processor 1501, the feature detection on the driving behavior of the second driving image to determine whether the dangerous driving behavior is included includes:
extracting a driving behavior characteristic value of the second driving image;
calculating the similarity between the driving behavior characteristic value and a preset illegal driving behavior characteristic value;
and judging whether the illegal driving behaviors are included or not based on the similarity of the driving behavior characteristic value and a preset illegal driving behavior characteristic value.
Optionally, the second driving image information includes a human face of the driver, the dangerous driving behavior executed by the processor 1501 includes a fatigue driving behavior, and the performing feature detection on the driving behavior of the second driving image and determining whether the dangerous driving behavior is included includes:
extracting a face characteristic value of a driver in the second driving image;
calculating the similarity between the face characteristic value and preset fatigue face characteristics;
and judging whether the fatigue driving behavior is included or not based on the similarity between the face characteristic value and the preset fatigue face characteristic.
Optionally, if the dangerous driving behavior is included, the processor 1501 sends an early warning prompt of the dangerous driving behavior, including:
judging the danger level of the dangerous driving behavior;
and sending out early warning prompts of corresponding danger levels according to the danger levels of the dangerous driving behaviors.
It should be noted that the electronic device provided in the embodiment of the present invention may be applied to an early warning device for dangerous driving behaviors, for example: the device can be used for early warning dangerous driving behaviors, such as a mobile phone, a vehicle data recorder, a vehicle-mounted central control, a computer, a server and the like.
The electronic device provided by the embodiment of the present invention can implement each implementation manner in the method embodiments of fig. 1 to 8, and corresponding beneficial effects, and are not described herein again to avoid repetition.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the embodiment of the warning method for dangerous driving behavior provided in the embodiment of the present invention, and can achieve the same technical effect, and is not described herein again to avoid repetition.
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 a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (10)
1. A dangerous driving behavior early warning method is characterized by comprising the following steps:
acquiring first driving image information, wherein the first driving image information comprises a driver;
preprocessing the first driving image information to obtain second driving image information, wherein the second driving image information comprises driving behaviors;
performing characteristic detection on the driving behaviors of the second driving image, and judging whether dangerous driving behaviors are included or not;
and if the dangerous driving behavior is contained, sending out an early warning prompt of the dangerous driving behavior.
2. The method of claim 1, wherein the preprocessing the first driving image information to obtain second driving image information comprises:
carrying out image segmentation on the first driving image information through an image segmentation algorithm to obtain a plurality of image segmentation areas;
and detecting the driving behaviors of the image segmentation areas, and extracting the image segmentation areas containing the driving behaviors to obtain the second driving image information.
3. The method of claim 1, wherein said obtaining first driving image information comprises:
acquiring a current driving environment condition or a vehicle driving mode;
and acquiring first driving image information acquired by an image acquisition device in a timing or real-time manner according to the current environment driving condition or the vehicle driving mode.
4. The method of claim 1, wherein the second driving image information includes a face of the driver, the dangerous driving behavior includes continuous driving, the method further comprising:
performing face detection on the second driving image at the time of T1 to obtain a first face detection result;
performing face detection on the second driving image at the time of T2 to obtain a second face detection result;
judging whether the drivers are the same or not according to the similarity of the first face detection result and the second face detection result;
if the driving condition is the same, sending out early warning prompts of continuous driving;
wherein the time difference between the T1 time and the T2 time is more than or equal to a preset time.
5. The method of claim 1, wherein the dangerous driving behavior comprises an illegal driving behavior, and the performing the feature detection on the driving behavior of the second driving image to determine whether the dangerous driving behavior is included comprises:
extracting a driving behavior characteristic value of the second driving image;
calculating the similarity between the driving behavior characteristic value and a preset illegal driving behavior characteristic value;
and judging whether the illegal driving behaviors are included or not based on the similarity of the driving behavior characteristic value and a preset illegal driving behavior characteristic value.
6. The method of claim 1, wherein the second driving image information includes a face of the driver, the dangerous driving behavior includes fatigue driving behavior, and the performing the feature detection on the driving behavior of the second driving image to determine whether the dangerous driving behavior is included comprises:
extracting a face characteristic value of a driver in the second driving image;
calculating the similarity between the face characteristic value and preset fatigue face characteristics;
and judging whether the fatigue driving behavior is included or not based on the similarity between the face characteristic value and the preset fatigue face characteristic.
7. The method according to any one of claims 1 to 6, wherein the sending out the warning prompt of the dangerous driving behavior if the dangerous driving behavior is included comprises:
judging the danger level of the dangerous driving behavior;
and sending out early warning prompts of corresponding danger levels according to the danger levels of the dangerous driving behaviors.
8. An early warning device for dangerous driving behavior, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring first driving image information which comprises a driver;
the preprocessing module is used for preprocessing the first driving image information to obtain second driving image information, and the second driving image information comprises driving behaviors;
the first detection module is used for carrying out characteristic detection on the driving behaviors of the second driving image and judging whether dangerous driving behaviors are included or not;
and the first prompt module is used for sending out an early warning prompt of the dangerous driving behavior if the dangerous driving behavior is contained.
9. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor when executing the computer program implementing the steps in the method for warning of dangerous driving behavior as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method for warning of dangerous driving behavior of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910930462.6A CN110728218A (en) | 2019-09-29 | 2019-09-29 | Dangerous driving behavior early warning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910930462.6A CN110728218A (en) | 2019-09-29 | 2019-09-29 | Dangerous driving behavior early warning method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110728218A true CN110728218A (en) | 2020-01-24 |
Family
ID=69219554
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910930462.6A Pending CN110728218A (en) | 2019-09-29 | 2019-09-29 | Dangerous driving behavior early warning method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110728218A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260882A (en) * | 2020-02-04 | 2020-06-09 | 上海博泰悦臻电子设备制造有限公司 | Driving behavior reminding method, system and server |
| CN111898429A (en) * | 2020-06-23 | 2020-11-06 | 内蒙古亿新科技有限公司 | Intelligent logistics system for truck driver |
| CN113538846A (en) * | 2021-07-13 | 2021-10-22 | 北京国基科技股份有限公司 | Port machine driver operation abnormal behavior analysis alarm method and system |
| CN113870551A (en) * | 2021-08-16 | 2021-12-31 | 清华大学 | Roadside monitoring system capable of identifying dangerous and non-dangerous driving behaviors |
| CN113954847A (en) * | 2020-07-20 | 2022-01-21 | 宝能汽车集团有限公司 | Method and device for detecting driver shoes, vehicle and storage medium |
| CN114435373A (en) * | 2022-03-16 | 2022-05-06 | 一汽解放汽车有限公司 | Fatigue driving detection method, device, computer equipment and storage medium |
| CN114842618A (en) * | 2022-04-24 | 2022-08-02 | 北京启辰智达科技有限公司 | Embedded driver behavior state early warning method and device, vehicle and medium |
| CN114971803A (en) * | 2022-06-02 | 2022-08-30 | 支付宝(杭州)信息技术有限公司 | Service processing method and device |
| CN115223104A (en) * | 2022-09-14 | 2022-10-21 | 深圳市睿拓新科技有限公司 | Scene recognition-based method and system for detecting illegal operation behaviors |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160913A (en) * | 2015-08-17 | 2015-12-16 | 上海斐讯数据通信技术有限公司 | Method and apparatus for standardizing driving behaviors of drivers |
| CN105894855A (en) * | 2016-04-22 | 2016-08-24 | 乐视控股（北京）有限公司 | Prompt method and apparatus for dangerous driving |
| CN109584507A (en) * | 2018-11-12 | 2019-04-05 | 深圳佑驾创新科技有限公司 | Driver behavior modeling method, apparatus, system, the vehicles and storage medium |
-
2019
- 2019-09-29 CN CN201910930462.6A patent/CN110728218A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160913A (en) * | 2015-08-17 | 2015-12-16 | 上海斐讯数据通信技术有限公司 | Method and apparatus for standardizing driving behaviors of drivers |
| CN105894855A (en) * | 2016-04-22 | 2016-08-24 | 乐视控股（北京）有限公司 | Prompt method and apparatus for dangerous driving |
| CN109584507A (en) * | 2018-11-12 | 2019-04-05 | 深圳佑驾创新科技有限公司 | Driver behavior modeling method, apparatus, system, the vehicles and storage medium |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260882A (en) * | 2020-02-04 | 2020-06-09 | 上海博泰悦臻电子设备制造有限公司 | Driving behavior reminding method, system and server |
| CN111898429A (en) * | 2020-06-23 | 2020-11-06 | 内蒙古亿新科技有限公司 | Intelligent logistics system for truck driver |
| CN113954847A (en) * | 2020-07-20 | 2022-01-21 | 宝能汽车集团有限公司 | Method and device for detecting driver shoes, vehicle and storage medium |
| CN113538846A (en) * | 2021-07-13 | 2021-10-22 | 北京国基科技股份有限公司 | Port machine driver operation abnormal behavior analysis alarm method and system |
| CN113870551A (en) * | 2021-08-16 | 2021-12-31 | 清华大学 | Roadside monitoring system capable of identifying dangerous and non-dangerous driving behaviors |
| CN114435373A (en) * | 2022-03-16 | 2022-05-06 | 一汽解放汽车有限公司 | Fatigue driving detection method, device, computer equipment and storage medium |
| CN114435373B (en) * | 2022-03-16 | 2023-12-22 | 一汽解放汽车有限公司 | Fatigue driving detection method, device, computer equipment and storage medium |
| CN114842618A (en) * | 2022-04-24 | 2022-08-02 | 北京启辰智达科技有限公司 | Embedded driver behavior state early warning method and device, vehicle and medium |
| CN114971803A (en) * | 2022-06-02 | 2022-08-30 | 支付宝(杭州)信息技术有限公司 | Service processing method and device |
| CN114971803B (en) * | 2022-06-02 | 2024-05-10 | 支付宝(杭州)信息技术有限公司 | Service processing method and device |
| CN115223104A (en) * | 2022-09-14 | 2022-10-21 | 深圳市睿拓新科技有限公司 | Scene recognition-based method and system for detecting illegal operation behaviors |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110728218A (en) | Dangerous driving behavior early warning method and device, electronic equipment and storage medium | |
| CN111274881B (en) | Driving safety monitoring method and device, computer equipment and storage medium | |
| US10915769B2 (en) | Driving management methods and systems, vehicle-mounted intelligent systems, electronic devices, and medium | |
| KR102305914B1 (en) | Driving management methods and systems, in-vehicle intelligent systems, electronic devices, media | |
| CN109584507B (en) | Driving behavior monitoring method, device, system, vehicle and storage medium | |
| CN108564066B (en) | Character recognition model training method and character recognition method | |
| CN110826370B (en) | Method and device for identifying identity of person in vehicle, vehicle and storage medium | |
| US9932000B2 (en) | Information notification apparatus and information notification method | |
| WO2018121006A1 (en) | Method and device for license plate positioning | |
| CN109377694B (en) | Monitoring method and system for community vehicles | |
| CN112990069B (en) | Abnormal driving behavior detection method, device, terminal and medium | |
| CN114679607B (en) | Video frame rate control method and device, electronic equipment and storage medium | |
| CN113111782A (en) | Video monitoring method and device based on salient object detection | |
| CN112699802A (en) | Driver micro-expression detection device and method | |
| CN112633387A (en) | Safety reminding method, device, equipment, system and storage medium | |
| CN111985304A (en) | Patrol alarm method, system, terminal equipment and storage medium | |
| CN114926824A (en) | Method for judging bad driving behavior | |
| CN118405085A (en) | Monitoring method, device, vehicle, electronic equipment and computer program product | |
| CN115713751A (en) | Fatigue driving detection method, device, storage medium and apparatus | |
| CN116311205A (en) | License plate recognition method, license plate recognition device, electronic equipment and storage medium | |
| CN107577995A (en) | The processing method and processing device of view data | |
| CN113283286A (en) | Driver abnormal behavior detection method and device | |
| CN112991717B (en) | Vehicle track display method and related product | |
| CN113781278B (en) | Event prompting method, device, equipment and storage medium based on feature recognition | |
| CN117392634B (en) | Lane line acquisition method and device, storage medium and electronic device |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201028 Address after: 518000 Guangdong city of Shenzhen province Qianhai Shenzhen Hong Kong cooperation zone before Bay Road No. 1 building 201 room A Applicant after: SHENZHEN HAIQUE TECHNOLOGY Co.,Ltd. Address before: 518000 Room 401, building 14, Shenzhen Software Park, Keji Zhonger Road, Yuehai street, Nanshan District, Shenzhen City, Guangdong Province Applicant before: SHENZHEN DANALE TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200124 |