Driver state control system and method based on image information
Technical Field
The invention relates to the field of image information processing, in particular to a driver state control system and method based on image information.
Background
With the development of economy, more and more vehicles are arranged on roads, and the incidence rate of traffic accidents is increased. When a driver drives a vehicle, the driver not only has a relationship with the life safety of the driver, but also shoulders the life safety of passengers and pedestrians on the road. Once a traffic accident happens, not only the life of the user is endangered, but also the safety driving is guaranteed to be vital. However, the posture behaviors of many drivers during driving are often not standard, such as driving to see a mobile phone, talking, thinking about a problem, driving with emotion, eating, smoking, bending down to pick up things, and the like, and the posture behaviors can cause traffic accidents. Accordingly, the applicant has proposed a technique of controlling the running state of the vehicle according to the posture behavior of the driver.
Disclosure of Invention
The invention aims to provide a driver state control system and method based on image information, and aims to solve the problems in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme:
the driver state detection system comprises an image information acquisition module, a vehicle control module and a vehicle driver database, wherein the image information acquisition module is used for acquiring the image information of a current driver at a vehicle driving position, the vehicle driver database is used for storing the head image information of the driver with the vehicle driving authority and a state model of the corresponding driver, and the vehicle control module determines the posture of the driver according to the image information of the current driver to control the running of the vehicle.
Preferably, the vehicle driver database comprises a head image information database and a posture state model database, the head image information database is used for storing head image information of a driver having the authority of driving the vehicle, the posture state model database is used for storing a rest state model, a pre-driving state model and a driving state model of the driver having the authority of driving the vehicle, the image acquisition processing module comprises an image acquisition module and an image extraction module, the image acquisition module is used for acquiring an image of the current driver at the driving position of the vehicle, the image extraction module comprises a head portrait extraction module, a posture extraction module and a safety belt extraction module, the head portrait extraction module is used for extracting the head image information from the acquired image of the driver, and the posture extraction module is used for extracting a human body contour from the acquired image of the driver and determining the posture of the driver and the affiliated state of the posture, the safety belt extraction module extracts wearing information of a safety belt from an acquired image of a driver, the vehicle control module comprises a head image control module, a rest state control module, a pre-driving state control module, a driving state control module and other state control modules, the head image control module comprises a driving authority judgment module and a driving authority control module, the driving authority judgment module is used for matching the extracted head image information with head image information in a vehicle driver database and judging whether the driver at a driving position is the driver with the authority of driving the vehicle, the driving authority control module is used for giving an alarm sound and forbidding the vehicle to be started when the current driver at the driving position does not have the authority of driving the vehicle, the rest state control module is used for forbidding the vehicle to be started when the posture of the driver is determined to belong to the rest state model, the pre-driving state control module comprises a first trigger time judging module and a safety belt checking module, the first trigger time judging module is used for triggering a safety belt extracting module to extract wearing information of a safety belt when the posture of a driver is determined to belong to a pre-driving state model and the time that the posture belongs to the pre-driving state model is longer than first trigger time, the safety belt detecting module judges whether the vehicle is allowed to start or not according to the judgment that whether the wearing of the safety belt meets the standard or not, and the other state control modules forbid the vehicle to start when the posture of the driver does not belong to either a rest state model or the pre-driving state model or the driving state model.
Preferably, the driving state control module comprises a monitoring control module and a second triggering time judgment module, the monitoring control module is used for controlling and continuously acquiring image information of a current driver at a driving position of the vehicle in the running process of the vehicle and determining the posture of the driver according to the image information, and the second triggering time judgment module is used for triggering and controlling the vehicle to decelerate when the posture of the driver is detected not to belong to the driving state model and the time that the posture of the driver does not belong to the driving state model is longer than a second triggering time.
A driver state detection method based on video images comprises the following steps:
step S1: presetting a vehicle driver database;
step S2: and acquiring image information of a current driver on a driving position of the vehicle to control the running of the vehicle.
Preferably, the driver state detection method further includes the steps of:
step S1: presetting a vehicle driver database, wherein head image information of a driver with the vehicle driving authority and a posture state model of the corresponding driver are stored in the vehicle driver database, and the posture state model comprises a rest state model, a pre-driving state model and a driving state model;
step S2: acquiring image information of a current driver on a driving position of a vehicle, extracting head image information from the acquired image information, matching the extracted head image information with pre-stored head image information, judging whether the driver on the driving position is the driver with the authority of driving the vehicle, if the pre-stored head image information can not be matched with the extracted head image information, judging that the current driver on the driving position does not have the authority of driving the vehicle, giving an alarm and prohibiting the vehicle from starting, if the pre-stored head image information can be matched with the extracted head image information, judging that the current driver on the driving position has the authority of driving the vehicle, determining the posture of the driver according to a human body contour in the image information of the driver, and controlling the running of the vehicle according to the determined posture.
Preferably, the controlling the operation of the vehicle according to the determined attitude includes:
prohibiting the vehicle from starting when it is determined that the posture of the driver belongs to the rest state model;
when the posture of the driver is determined to belong to the pre-driving state model, and when the time that the posture of the driver belongs to the pre-driving state model is longer than the first trigger time, triggering and checking whether the driver wears a safety belt and whether the wearing of the safety belt is standard or not, if the wearing of the safety belt is in accordance with the standard, allowing the vehicle to start, and if the wearing of the safety belt is not in accordance with the standard, forbidding the vehicle to start;
when it is determined that the posture of the driver belongs to the driving state model, allowing the vehicle to be in the way of driving, and continuously monitoring the posture of the driver;
when it is determined that the posture of the driver does not belong to either the rest state model, the pre-driving state model, or the driving state model, the vehicle start is prohibited.
Preferably, the checking whether the driver wears the seat belt and whether the wearing of the seat belt is standardized includes the following:
determining the area which should be worn with the safety belt according to the head portrait position of the driver;
obtaining binary image information by performing color segmentation corresponding to the zone wearing the safety belt;
performing edge detection and contour analysis on the binary image information to obtain the contour of the safety belt;
and judging whether the width of the safety belt is larger than a safety belt width threshold value or not according to the contour of the safety belt, if so, judging that the wearing of the safety belt is in accordance with the standard, otherwise, judging that the wearing of the safety belt is not in accordance with the standard.
Preferably, when the vehicle is in the driving process and the posture of the driver is continuously monitored, if the posture of the driver is detected not to belong to the driving state model and the time that the posture of the driver does not belong to the driving state model is longer than the second trigger time, the vehicle is triggered to be controlled to decelerate.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the posture of the driver at the driving position is acquired through image acquisition, and the running state of the automobile is controlled according to the posture, so that the behavior specification of the driver can be kept when the driver drives the automobile, and the probability of traffic accidents in the process of driving the automobile by the driver can be reduced.
Drawings
Fig. 1 is a block diagram of a driver status control system based on image information according to 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.
Referring to fig. 1, in an embodiment of the present invention, a driver state control system based on image information includes an image information obtaining module, a vehicle control module, and a vehicle driver database, where the image information obtaining module is configured to obtain image information of a current driver at a driving position of a vehicle, the vehicle driver database is configured to store head image information of the driver having a permission to drive the vehicle and a state model of the corresponding driver, and the vehicle control module determines a posture of the driver according to the image information of the current driver to control operation of the vehicle.
The driver state control system based on image information comprises a head image information database and a posture state model database, wherein the head image information database is used for storing head image information of a driver with the authority of driving the vehicle, the posture state model database is used for storing a rest state model, a pre-driving state model and a driving state model of the driver with the authority of driving the vehicle, the image acquisition processing module comprises an image acquisition module and an image extraction module, the image acquisition module is used for acquiring an image of the current driver at the driving position of the vehicle, the image extraction module comprises a head portrait extraction module, a posture extraction module and a safety belt extraction module, the head portrait extraction module is used for extracting the head image information from the acquired image of the driver, and the posture extraction module is used for extracting a human body contour from the acquired image of the driver and determining the posture of the driver and the posture of the driver The safety belt extraction module extracts wearing information of a safety belt from a collected image of a driver, the vehicle control module comprises a head image control module, a rest state control module, a pre-driving state control module, a driving state control module and other state control modules, the head image control module comprises a driving authority judgment module and a driving authority control module, the driving authority judgment module is used for matching the extracted head image information with head image information in a vehicle driver database and judging whether the driver on a driving position is the driver with the authority of driving the vehicle, the driving authority control module is used for giving an alarm sound and forbidding the vehicle to start when the driver does not have the authority of driving the vehicle on the driving position, the rest state control module is used for forbidding the vehicle to start when the posture of the driver is determined to belong to a rest state model, the pre-driving state control module comprises a first trigger time judging module and a safety belt checking module, the first trigger time judging module is used for triggering a safety belt extracting module to extract wearing information of a safety belt when the posture of a driver is determined to belong to a pre-driving state model and the time that the posture belongs to the pre-driving state model is longer than first trigger time, the safety belt detecting module judges whether the vehicle is allowed to start or not according to the judgment that whether the wearing of the safety belt meets the standard or not, and the other state control modules forbid the vehicle to start when the posture of the driver does not belong to either a rest state model or the pre-driving state model or the driving state model.
The driver state control system based on the image information comprises a monitoring control module and a second trigger time judgment module, wherein the monitoring control module is used for controlling and continuously acquiring the image information of a current driver at a driving position of the vehicle in the running process of the vehicle and determining the posture of the driver according to the image information, and the second trigger time judgment module is used for triggering and controlling the vehicle to decelerate when the posture of the driver is detected not to belong to a driving state model and the time that the posture of the driver does not belong to the driving state model is longer than the second trigger time.
A driver state detection method based on video images comprises the following steps:
step S1: presetting a vehicle driver database, wherein head image information of a driver with the vehicle driving authority and a posture state model of the corresponding driver are stored in the vehicle driver database, and the posture state model comprises a rest state model, a pre-driving state model and a driving state model;
step S2: acquiring image information of a current driver on a driving position of a vehicle, extracting head image information from the acquired image information, matching the extracted head image information with pre-stored head image information, judging whether the driver on the driving position is the driver with the authority of driving the vehicle, if the pre-stored head image information can not be matched with the extracted head image information, judging that the current driver on the driving position does not have the authority of driving the vehicle, giving an alarm and prohibiting the vehicle from starting, if the pre-stored head image information can be matched with the extracted head image information, judging that the current driver on the driving position has the authority of driving the vehicle, determining the posture of the driver according to a human body contour in the image information of the driver, and controlling the running of the vehicle according to the determined posture.
The driver state control system based on image information controlling the operation of the vehicle according to the determined posture includes the following:
prohibiting the vehicle from starting when it is determined that the posture of the driver belongs to the rest state model;
when the posture of the driver is determined to belong to the pre-driving state model, and when the time that the posture of the driver belongs to the pre-driving state model is longer than the first trigger time, triggering and checking whether the driver wears a safety belt and whether the wearing of the safety belt is standard or not, if the wearing of the safety belt is in accordance with the standard, allowing the vehicle to start, and if the wearing of the safety belt is not in accordance with the standard, forbidding the vehicle to start;
when it is determined that the posture of the driver belongs to the driving state model, allowing the vehicle to be in the way of driving, and continuously monitoring the posture of the driver;
when it is determined that the posture of the driver does not belong to either the rest state model, the pre-driving state model, or the driving state model, the vehicle start is prohibited.
The driver state control system based on image information, which checks whether the driver wears a seat belt and whether the wearing of the seat belt is standardized, includes the following:
determining the area which should be worn with the safety belt according to the head portrait position of the driver;
obtaining binary image information by performing color segmentation corresponding to the zone wearing the safety belt;
performing edge detection and contour analysis on the binary image information to obtain the contour of the safety belt;
and judging whether the width of the safety belt is larger than a safety belt width threshold value or not according to the contour of the safety belt, if so, judging that the wearing of the safety belt is in accordance with the standard, otherwise, judging that the wearing of the safety belt is not in accordance with the standard.
When the vehicle is in the driving process and the posture of the driver is continuously monitored, the driver state control system based on the image information triggers the vehicle to decelerate if the posture of the driver is detected not to belong to the driving state model and the time that the posture of the driver does not belong to the driving state model is longer than a second trigger time.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.