CN113723339A - Fatigue driving detection method, storage medium, and electronic device - Google Patents
Fatigue driving detection method, storage medium, and electronic device Download PDFInfo
- Publication number
- CN113723339A CN113723339A CN202111050000.9A CN202111050000A CN113723339A CN 113723339 A CN113723339 A CN 113723339A CN 202111050000 A CN202111050000 A CN 202111050000A CN 113723339 A CN113723339 A CN 113723339A
- Authority
- CN
- China
- Prior art keywords
- driver
- fatigue
- fatigue driving
- driving detection
- state
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 claims abstract description 34
- 230000001815 facial effect Effects 0.000 claims description 35
- 208000003464 asthenopia Diseases 0.000 claims description 26
- 238000003066 decision tree Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 230000002618 waking effect Effects 0.000 claims description 5
- 230000035080 detection of muscle activity involved in regulation of muscle adaptation Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241000282372 Panthera onca Species 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a fatigue driving detection method, a storage medium and an electronic device. In the method, the current driving state of the driver can be determined by detecting the fatigue driving of the driver, and then the sparse time strategy of the fatigue driving detection is dynamically set according to the driving state so as to carry out sparse detection on the driver. The scheme of the invention does not carry out fatigue driving detection on the driver in real time, but sparsely carries out fatigue driving detection on the driver, and meanwhile, the sparse interval can be dynamically adjusted according to the current driving state of the driver, so that the calculation resources of the vehicle-mounted system are saved on the premise of ensuring the safety, and the method can be used for a driving early warning system in an intelligent vehicle-mounted system.
Description
Technical Field
The present invention relates to the field of computer engineering application technologies, and in particular, to a method, a storage medium, and an electronic device for detecting fatigue driving of a driver.
Background
With the increasing economic level of people, it is very common for a family to have one or more automobiles. The frequency of traffic accidents is greatly improved while the number of private cars is continuously increased, wherein the traffic accidents caused by fatigue driving are always a great hidden danger.
With the development of science and technology, some researchers are put into early warning and control research on fatigue driving, but in the present, the existing fatigue driving detection scheme still has a large defect and a large development space. Such as: the company of German automobile, daily product and the like adopts indirect measurement, the behavior of a driver is analyzed by methods such as machine learning and the like, but the accuracy is not high, the bad conditions such as misjudgment and the like are easy to occur, and a machine learning system with high real-time property occupies a large part of resources of a vehicle-mounted system; companies such as Toyota, Jaguar and the like adopt a direct measurement mode, and human facial features or electroencephalogram information are used as judgment bases, so that although the accuracy is greatly improved, the cost is correspondingly increased; in other methods, a heart rate monitoring device is worn by a driver, so that the experience of the driver is poor, the vehicle is provided with related instruments, but the utilization rate is low, and the method is difficult to popularize generally.
Disclosure of Invention
In view of the above technical problem, a fatigue driving detection method, system and electronic device for a driver solving the above problems or at least partially solving the above problems are proposed.
An object of the first aspect of the present invention is to provide a method for detecting fatigue driving of a driver, which is used for detecting a driving state of the driver by using a method of occupying vehicle-mounted resources as little as possible.
It is a further object of the first aspect of the present invention to effectively utilize the facial information of the driver to detect fatigue driving of the driver, thereby improving the accuracy of the detection result without increasing the detection cost.
It is an object of the second aspect of the invention to provide a machine-readable storage medium.
It is an object of the third aspect of the invention to provide an electronic device.
In particular, according to a first aspect of the present invention, there is provided a fatigue driving detection method for a driver, comprising:
detecting fatigue driving of a driver;
when detecting that a driver is in a normal state, setting a sparse time strategy for fatigue driving detection;
determining the starting time point of the next round of fatigue driving detection according to a sparse time strategy;
and detecting whether the current time point reaches the starting time point of the next round of fatigue driving detection, and if so, carrying out the new round of fatigue driving detection on the driver.
Optionally, the step of detecting fatigue driving of the driver comprises:
capturing facial features of a driver;
calculating to obtain the current fatigue state value of the driver according to the captured facial features;
and determining the driving state of the driver according to the fatigue state value.
Optionally, the step of capturing facial features of the driver comprises:
acquiring N frames of face images of a driver in the process of driving a vehicle;
facial features of each frame of face image are extracted from the N frames of face images.
Optionally, the facial features include eye features and mouth features, and the step of extracting the facial features of each of the N frames of facial images includes:
for each frame face image, determining an eye image and a mouth image within the frame face image respectively;
extracting eye features from the eye image;
mouth features are extracted from the mouth image.
Optionally, the step of calculating the current fatigue state value of the driver according to the captured facial features comprises:
calculating according to each eye feature to obtain an eye fatigue state value;
calculating a mouth fatigue state value according to each mouth feature; and is
The step of determining the driving state of the driver from the fatigue state value includes:
respectively carrying out normalization processing on all eye fatigue state values and mouth fatigue state values;
and taking the normalized eye fatigue state value and the normalized mouth fatigue state value as judgment nodes, and deciding the driving state of the driver by utilizing a pre-established fatigue state decision tree.
Optionally, the normal state comprises an awake state and a fatigued state; and when the driver is in a normal state, setting a sparse time strategy for fatigue driving detection, wherein the step comprises the following steps of:
when a driver is in a waking state, setting a first sparse time strategy to enable the time interval between the fatigue driving detection of the current round and the fatigue driving detection of the next round to be a default value;
and when the driver is in a fatigue state, setting a second sparse time strategy so that the time interval between the fatigue driving detection of the current round and the next round is smaller than the time interval between the fatigue driving detection of the current round and the previous round.
Optionally, after the step of detecting fatigue driving of the driver, the method further comprises:
and when detecting that the driver is in a fatigue state, generating and outputting prompt information.
Optionally, the step of detecting fatigue driving of the driver comprises:
detecting a start event of a vehicle;
upon detection of a start event, an initial detection of fatigue driving is made to the driver to initialize the driver's driving state.
According to a second aspect of the invention, there is also provided a machine-readable storage medium having stored thereon a machine-executable program which, when executed by a processor, implements a method for fatigue driving detection for a driver according to any of the preceding.
According to a third aspect of the invention, the invention also provides an electronic device comprising a memory, a processor and a machine executable program stored on the memory and run on the processor, and the processor when executing the machine executable program implements a method of fatigue driving detection for a driver according to any of the preceding.
The invention provides a fatigue driving detection method for a driver, a storage medium and electronic equipment. By adopting the scheme of the invention, the sparse time strategy of fatigue driving detection can be dynamically set according to the current driving state of the driver, so that sparse detection is carried out on the driver. Compared with the existing fatigue driving detection method, the scheme of the invention does not carry out fatigue driving detection on the driver in real time, but sparsely carries out fatigue driving detection on the driver, and meanwhile, the sparse interval can be dynamically adjusted according to the current driving state of the driver, so that on the premise of ensuring the safety, the calculation resources of the vehicle-mounted system are saved, and the method can be used for a driving early warning system in an intelligent vehicle-mounted system.
Furthermore, in the process of detecting the fatigue driving of the driver, the invention can effectively judge the current driving state of the driver by the facial information of the driver, thereby improving the accuracy of detecting the fatigue driving.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Some specific embodiments of the invention will be described in detail hereinafter, by way of illustration and not limitation, with reference to the accompanying drawings. The same reference numbers in the drawings identify the same or similar elements or components. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the drawings:
FIG. 1 is a schematic flow diagram of a method for driver fatigue detection according to one embodiment of the present invention;
FIG. 2 is a schematic model diagram of a fatigue state decision tree, according to one embodiment of the present invention;
FIG. 3 is a schematic detailed flow diagram of a method for driver fatigue detection according to an embodiment of the present invention;
fig. 4 is a schematic block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
In the field of fatigue driving detection, the fatigue driving detection efficiency and accuracy are always concerned, in order to improve the judgment efficiency and accuracy of fatigue driving detection, in some fatigue detection methods, a Viola-Jones frame feature matrix is used for face pre-judgment, in the pre-judgment process, in order to reduce the calculation amount of a Haar value and improve the face recognition speed, an Adaboost algorithm and cascade analysis are adopted to realize the rapid recognition of a face, eye segmentation processing is realized according to color space conversion, and whether a driver is in a fatigue state or not is evaluated according to a PERCLOS value and early warning is carried out. Although the method can effectively identify whether the driver is in a fatigue state, the resource consumption problem of the whole vehicle-mounted system when the algorithm is deployed at the vehicle-mounted end is not fully considered, and after all, other modules which are very important, such as wireless communication, alarm control, voice control and the like, exist in the vehicle-mounted system.
In other fatigue detection methods, 5G and car networking technologies are applied to a fatigue driving early warning system in order to improve the rate of fatigue driving. The information acquisition system in the system adopts a CCD image sensor, a novel photoelectric conversion system device, has small volume and high sensitivity, and improves the timeliness and the accuracy of information acquisition. Aiming at the problems of blurring, ghosting, chromatic aberration or serious exposure without imaging and the like in information processing, Gamma correction and Gaussian filtering image processing technology are adopted for improvement. Therefore, the characteristics of high-speed 5G transmission, ultrahigh bandwidth and the like are utilized to realize rapid information transmission. However, the scheme depends on a real-time facial expression capturing system, and meanwhile, 5G is adopted for information transmission, the high-efficiency mode brings high resource consumption, and the accuracy rate of facial information only depending on a driver is high, but the accuracy rate can be further improved.
In order to solve the foregoing technical problem, an embodiment of the present invention provides a method for detecting fatigue driving of a driver, so as to implement detection of a driving state of the driver by a method that occupies as little vehicle-mounted resources as possible.
Fig. 1 is a schematic flow chart of a method for detecting fatigue driving of a driver according to an embodiment of the present invention. Referring to fig. 1, in some embodiments of the present invention, a fatigue driving detection method for a driver may include steps S102 to S108.
Step S102 detects fatigue driving of the driver.
Step S104, when detecting that the driver is in a normal state, setting a sparse time strategy for fatigue driving detection;
step S106, determining the starting time point of the next round of fatigue driving detection according to a sparse time strategy;
and step S108, detecting whether the current time point reaches the starting time point of the next round of fatigue driving detection, and if so, carrying out a new round of fatigue driving detection on the driver.
According to the embodiment of the invention, the current driving state of the driver can be determined by detecting the fatigue driving of the driver, and then the sparse time strategy of the fatigue driving detection is dynamically set according to the driving state, so that the driver is subjected to sparse detection. Compared with the existing fatigue driving detection method, the embodiment of the invention does not carry out fatigue driving detection on the driver in real time, but carries out fatigue driving detection on the driver sparsely, and meanwhile, the sparse time strategy can carry out dynamic adjustment according to the current driving state of the driver, so that on the premise of ensuring the safety, the calculation resources of the vehicle-mounted system are saved, and the method can be used for a driving early warning system in an intelligent vehicle-mounted system.
For step S102, in some embodiments, facial features of the driver may be captured, a current fatigue state value of the driver may be calculated according to the captured facial features, and then the driving state of the driver may be determined according to the fatigue state value, so as to achieve the purpose of detecting fatigue driving of the driver.
In order to improve the accuracy of the fatigue driving detection result when capturing the facial features of the driver, N frames of facial images of the driver during driving of the vehicle may be collected, and the facial features of each frame of facial image in the N frames of facial images may be extracted, so as to calculate the fatigue state value of the driver according to the facial features, thereby determining the current driving state of the driver.
The N frames of face images can be acquired by a camera device, for example, the face of the driver is captured by the camera for a short time, so as to acquire the N frames of face images of the driver in the process of driving the vehicle. The imaging device may be a vehicle-mounted camera, a camera mounted at the rear, or the like, and the present invention is not particularly limited thereto.
The facial features may include eye features and mouth features. In this case, the step of extracting the facial features of each of the N frames of face images may further include the steps of: for each frame face image, determining an eye image and a mouth image in the frame face image respectively; extracting eye features from the eye image; mouth features are extracted from the mouth image. That is, the eye feature and the mouth feature are extracted for each frame image, and N eye features and N mouth features may be extracted for N frame images.
The fatigue state value is a physical quantity that can reflect the driving state of the driver, and when the facial feature is the eye feature and the mouth feature, the fatigue state value may be the eye fatigue state value and the mouth fatigue state value, respectively.
In order to more accurately determine the driving state of the driver, in some embodiments, when the current fatigue state value of the driver is calculated according to the captured facial features, the corresponding eye fatigue state value and mouth fatigue state value may be calculated according to each of the eye features and mouth features, that is, for N eye features and N mouth features, N eye fatigue state values and N mouth fatigue state values may be calculated, and the driving state of the driver may be determined according to all the eye fatigue state values and the mouth fatigue state values that are calculated.
The eye fatigue state value may be calculated in various ways, and in some embodiments of the present invention, if the eye fatigue state value is represented by an EAR, the EAR may be calculated by the following formula.
Wherein p is1And p4Representing the left and right end points of the eye, p2And p6Then represent the upper left and lower left endpoints of the eye, p3And p5Then the upper right endpoint and the lower right endpoint of the eye are represented.
The mouth fatigue state value may be calculated in a manner similar to the calculation of the eye fatigue state value. Illustratively, how the mouth fatigue state value is expressed by MAR, the MAR value can be calculated by the following formula.
Wherein p is1' and p4' represents the left and right end points of the mouth, p2' and p6' then represents the upper left end point and the lower left end point of the mouth, p3' and p5' then represents the upper right end point and the lower right end point of the mouth.
After the eye fatigue state value and the mouth fatigue state value are obtained through calculation, the driving state of the driver can be decided according to the eye fatigue state and the mouth fatigue state value.
In consideration of practical application, the aspect ratios of the eyes of different individuals are different to different degrees, and a driver may blink due to special conditions (such as strong light) during the driving process of a vehicle, which inevitably affects the accuracy of the detection result of fatigue driving. In view of this, in some embodiments, assuming that N frames of facial images are acquired, one eye fatigue state value and one mouth fatigue state value are obtained for each frame of facial image. That is, the N frame face images may correspond to the N eye fatigue state values and the N mouth fatigue state values, and in this case, the step of determining the driving state of the driver based on the fatigue state values may further include the following steps 1 and 2.
Step 1: all the eye fatigue state values and mouth fatigue state values are normalized.
The normalization in this step is a process of averaging all eye fatigue state values and all mouth partial strain state values, respectively. If the normalized eye fatigue state value and the normalized mouth fatigue state value are expressed by mean and MMAR, respectively, mean can be calculated by the following formula.
MMAR can be calculated by the following formula.
Step 2: and taking the normalized eye fatigue state value and the normalized mouth fatigue state value as judgment nodes, and deciding the driving state of the driver by utilizing a pre-established fatigue state decision tree.
Decision trees are a common machine learning algorithm, and are tree structures in which each internal node represents a test on an attribute, each branch represents a test output, and each leaf node represents a category. According to the use scene of the fatigue driving detection, a fatigue state decision tree can be established in advance so as to be used for deciding the driving state of the driver.
Therefore, through the step 1 and the step 2, the influence caused by different eye aspect ratios of different individuals can be eliminated, the influence caused by blinking due to special conditions is lightened, and the accuracy of the fatigue driving detection result is improved. Meanwhile, the eye characteristics and the mouth characteristics of the driver are integrated, the driving state of the driver is determined through the fatigue state decision tree, the facial information of the driver is effectively utilized, the accuracy of a fatigue driving detection result is further ensured, and the detection cost cannot be increased.
In some embodiments, a fatigue state decision tree may be built as shown in FIG. 2. As can be seen from fig. 2, the eye fatigue state value is a root node, the mouth fatigue state value is a determination node (i.e., a child node), the driving states (including the fatigue state, and the awake state) are leaf nodes, and whether the eye fatigue state value and the mouth fatigue state value are greater than a preset threshold value is used as a classification criterion of the driving states. The preset threshold may be set as needed to make the classification of the driving state more accurate, for example, the preset threshold may be set to 0.2.
The normal state in step S104 may include an awake state and a fatigued state.
When the driver is in the waking state, a first sparse time strategy can be set, so that the time interval between the fatigue driving detection of the current round and the fatigue driving detection of the next round is a default value. The default value is a sparse interval for the driver to perform the ticket driving detection in the waking state, and may be preset according to actual requirements, for example, the default value may be preset to 10min, 30min, and the like.
When the driver is in a fatigue state, a second sparse time strategy can be set, so that the time interval between the fatigue driving detection of the current round and the fatigue driving detection of the next round is smaller than the time interval between the fatigue driving detection of the current round and the fatigue driving detection of the previous round, which can also be called a sparse interval. That is, when the driver is fatigued, the sparse interval between two adjacent rounds of fatigue driving detection can be dynamically shortened.
By adopting the embodiment of the invention, different sparse time strategies can be set according to the driving state of the driver so as to detect the driver at different sparse intervals, and the sparse intervals can be dynamically adjusted according to the current driving state of the driver, so that not only is the safety ensured, but also the computing resources of a vehicle-mounted system are saved.
Further, the fatigue driving detection method for a driver in any of the foregoing examples may further include, after the step of performing fatigue driving detection on the driver, the step of: and when detecting that the driver is in a fatigue state, generating and outputting prompt information. The prompt information can be output through a voice broadcasting device, for example, when the driver is determined to be in a fatigue state at present, the driver and other passengers in the vehicle can be informed in a broadcasting mode and the like so as to draw necessary attention and ensure driving safety. In other embodiments, the in-vehicle user may also be alerted by activating an alarm or buzzer upon detecting that the driver is in a tired state.
In some embodiments, a start event of the vehicle may be detected during the detection of fatigue driving of the driver, and an initial detection of fatigue driving of the driver may be performed to initialize the driving state of the driver when the start event is detected. The purpose of initializing the driving state here is to determine a sparse interval of initial detection so as to sparsely detect the driver, thereby saving the computational resources of the in-vehicle system.
In addition, when step S108 is executed, a timer or timer may be started, and whether the current time point reaches the starting time point of the next round of fatigue driving detection may be detected by the timer or timer.
Fig. 3 is a schematic detailed flowchart of a fatigue driving detection method for a driver according to an embodiment of the present invention. Referring to fig. 3, in this embodiment, the fatigue driving detecting method for the driver may include steps S302 to S326 as follows.
Step S302, whether the vehicle is started or not is detected. If yes, go to step S304; if not, go on to step S302.
In step S304, N frames of face images of the driver are acquired.
In step S306, the eye image and the mouth image of each frame face image are determined from the N frame face images.
In step S308, corresponding eye features and mouth features are extracted from each of the eye image and the mouth image.
Step S310, calculating according to each eye feature to obtain an eye fatigue state value, and calculating according to each mouth feature to obtain a mouth partial fatigue state value.
In step S312, normalization processing is performed on the N eye fatigue state values and the N mouth fatigue state values, respectively.
And step S314, determining the driving state of the driver through a fatigue state decision tree according to the normalized eye fatigue state value and mouth fatigue state value.
Step S316, judging whether the driver is in a fatigue state, if so, executing step S318; if not, go to step S320.
In step S318, the presentation information is generated and output.
In step S320, it is determined that the driver is in either the awake state or the fatigued state. If the driver is awake. Step S322 is executed; if the driver is in a tired state, step S324 is executed.
Step S322, a first sparse time strategy of fatigue driving detection is set, and the starting time point of the next round of fatigue driving detection is determined according to the first sparse time strategy.
And step S324, setting a second sparse time strategy of fatigue driving detection, and determining the starting time point of the next round of fatigue driving detection according to the second sparse time strategy.
In step S326, it is detected whether the current time point reaches the start time point. If yes, returning to the step S304; if not, go to step S326.
Based on the same inventive concept, in one embodiment, a machine-readable storage medium is also provided. The machine-readable storage medium stores a machine-executable program which, when executed by a processor, implements a method for fatigue driving detection for a driver in accordance with any one or combination of the preceding embodiments.
FIG. 4 is a schematic block diagram of an electronic device in accordance with one embodiment of the present invention. Referring to fig. 4, the present invention also provides an electronic device 400.
Further, the electronic device 400 may be an in-vehicle electronic device, or an edge server, or a cloud server.
Further, the Vehicle-mounted electronic device may specifically be a driving brain, a Vehicle machine, a DHU (integrated machine of entertainment host and meter), an IHU (information entertainment Unit), an IVI (In-Vehicle information entertainment system), or any Vehicle-mounted information interaction terminal.
The electronic device 400 may include a memory 410, a processor 420, and a machine-executable program 411 stored on the memory 410 and running on the processor 420. The processor, when executing the machine executable program, implements a method for driver fatigue detection that implements any one or more of the embodiments described above.
The above embodiments can be combined arbitrarily, and according to any one of the above preferred embodiments or a combination of multiple preferred embodiments, the embodiments of the present invention can achieve the following beneficial effects:
by adopting the scheme of the embodiment of the invention, the initial fatigue driving detection can be carried out on the driving once when the vehicle is started, so that the proper sparse interval of the fatigue driving detection can be kept for the driver in the waking state, and if the driver is detected to be in a fatigue state, the sparse interval of the fatigue driving detection can be dynamically shortened. Compared with the existing fatigue driving detection method, the embodiment of the invention does not carry out fatigue driving detection on the driver in real time, but carries out fatigue driving detection on the driver sparsely, and meanwhile, the sparse time strategy can carry out dynamic adjustment according to the current driving state of the driver, so that on the premise of ensuring the safety, the calculation resources of the vehicle-mounted system are saved, and the method can be used for a driving early warning system in an intelligent vehicle-mounted system. In addition, in the process of detecting the fatigue driving of the driver, the embodiment of the invention can effectively judge the current driving state of the driver by the facial information of the driver, thereby improving the accuracy of detecting the fatigue driving.
Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.
Claims (10)
1. A method for detecting fatigue driving of a driver, comprising:
performing fatigue driving detection on the driver;
when the driver is detected to be in a normal state, setting a sparse time strategy of fatigue driving detection;
determining the starting time point of the next round of fatigue driving detection according to the sparse time strategy;
and detecting whether the current time point reaches the starting time point of the next round of fatigue driving detection, and if so, carrying out the fatigue driving detection of a new round on the driver.
2. The fatigue driving detection method for a driver according to claim 1, wherein the step of performing fatigue driving detection on the driver includes:
capturing facial features of a driver;
calculating to obtain the current fatigue state value of the driver according to the captured facial features;
determining the driving state of the driver according to the fatigue state value.
3. The fatigue driving detection method for a driver according to claim 2, wherein the step of capturing facial features of the driver includes:
acquiring N frames of face images of the driver in the vehicle driving process;
and extracting the facial features of each frame of face image from the N frames of face images.
4. The fatigue driving detection method for a driver according to claim 3, wherein the facial features include eye features and mouth features, and the step of extracting the facial features of each of the N frames of face images includes:
for each frame face image, determining an eye image and a mouth image within the frame face image respectively;
extracting the ocular features from the ocular image;
extracting the mouth feature from the mouth image.
5. The fatigue driving detection method for a driver according to claim 4,
the step of calculating the current fatigue state value of the driver according to the captured facial features comprises the following steps:
calculating an eye fatigue state value according to each eye feature;
calculating a mouth fatigue state value according to each mouth feature; and is
The step of determining the driving state of the driver from the fatigue state value includes:
normalizing all the eye fatigue state values and the mouth fatigue state values respectively;
and taking the normalized eye fatigue state value and the normalized mouth fatigue state value as judgment nodes, and deciding the driving state of the driver by utilizing a pre-established fatigue state decision tree.
6. A fatigue driving detection method for a driver according to claim 1, wherein the normal state includes an awake state and a fatiger state; and when the driver is in a normal state, setting a sparse time strategy for fatigue driving detection, including:
when the driver is in a waking state, setting a first sparse time strategy so as to enable the time interval between the fatigue driving detection of the current round and the fatigue driving detection of the next round to be a default value;
and when the driver is in a fatigue state, setting a second sparse time strategy so that the time interval between the fatigue driving detection of the current round and the fatigue driving detection of the next round is smaller than the time interval between the fatigue driving detection of the current round and the fatigue driving detection of the previous round.
7. The fatigue driving detection method for the driver according to claim 1, further comprising, after the step of performing fatigue driving detection on the driver:
and when the driver is detected to be in a fatigue state, generating and outputting prompt information.
8. The fatigue driving detection method for a driver according to claim 1, wherein the step of performing fatigue driving detection on the driver includes:
detecting a start event of a vehicle;
upon detection of the start event, performing an initial detection of fatigue driving for the driver to initialize a driving state of the driver.
9. A machine readable storage medium having stored thereon a machine executable program which when executed by a processor implements a method for fatigue driving detection for a driver according to any one of claims 1 to 8.
10. An electronic device comprising a memory, a processor and a machine-executable program stored on the memory and run on the processor, and the processor when executing the machine-executable program implements a method for fatigue driving detection for a driver as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111050000.9A CN113723339A (en) | 2021-09-08 | 2021-09-08 | Fatigue driving detection method, storage medium, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111050000.9A CN113723339A (en) | 2021-09-08 | 2021-09-08 | Fatigue driving detection method, storage medium, and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113723339A true CN113723339A (en) | 2021-11-30 |
Family
ID=78682575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111050000.9A Pending CN113723339A (en) | 2021-09-08 | 2021-09-08 | Fatigue driving detection method, storage medium, and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113723339A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104183091A (en) * | 2014-08-14 | 2014-12-03 | 苏州清研微视电子科技有限公司 | System for adjusting sensitivity of fatigue driving early warning system in self-adaptive mode |
| CN104881956A (en) * | 2015-06-17 | 2015-09-02 | 上海大学 | Fatigue driving early warning system |
| CN108482380A (en) * | 2018-03-06 | 2018-09-04 | 知行汽车科技（苏州）有限公司 | The driving monitoring system of automatic adjusument sample frequency |
| CN112183220A (en) * | 2020-09-04 | 2021-01-05 | 广州汽车集团股份有限公司 | Driver fatigue detection method and system and computer storage medium |
| CN112528843A (en) * | 2020-12-07 | 2021-03-19 | 湖南警察学院 | Motor vehicle driver fatigue detection method fusing facial features |
| CN112754498A (en) * | 2021-01-11 | 2021-05-07 | 一汽解放汽车有限公司 | Driver fatigue detection method, device, equipment and storage medium |
-
2021
- 2021-09-08 CN CN202111050000.9A patent/CN113723339A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104183091A (en) * | 2014-08-14 | 2014-12-03 | 苏州清研微视电子科技有限公司 | System for adjusting sensitivity of fatigue driving early warning system in self-adaptive mode |
| CN104881956A (en) * | 2015-06-17 | 2015-09-02 | 上海大学 | Fatigue driving early warning system |
| CN108482380A (en) * | 2018-03-06 | 2018-09-04 | 知行汽车科技（苏州）有限公司 | The driving monitoring system of automatic adjusument sample frequency |
| CN112183220A (en) * | 2020-09-04 | 2021-01-05 | 广州汽车集团股份有限公司 | Driver fatigue detection method and system and computer storage medium |
| CN112528843A (en) * | 2020-12-07 | 2021-03-19 | 湖南警察学院 | Motor vehicle driver fatigue detection method fusing facial features |
| CN112754498A (en) * | 2021-01-11 | 2021-05-07 | 一汽解放汽车有限公司 | Driver fatigue detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101593425B (en) | Machine vision based fatigue driving monitoring method and system | |
| CN111062292B (en) | Fatigue driving detection device and method | |
| WO2021016873A1 (en) | Cascaded neural network-based attention detection method, computer device, and computer-readable storage medium | |
| CN102855617B (en) | Method and system for processing adaptive images | |
| CN110991324B (en) | Fatigue driving detection method based on various dynamic characteristics and Internet of things technology | |
| CN112487922B (en) | Multi-mode human face living body detection method and system | |
| CN110859609B (en) | Multi-feature fusion fatigue driving detection method based on voice analysis | |
| CN105426863B (en) | The method and apparatus for detecting lane line | |
| CN107563346A (en) | One kind realizes that driver fatigue sentences method for distinguishing based on eye image processing | |
| CN102163286B (en) | Pornographic image evaluating method | |
| CN104881956A (en) | Fatigue driving early warning system | |
| CN111104974A (en) | Helmet wearing identification method based on deep learning | |
| CN111832461A (en) | Non-motor vehicle riding personnel helmet wearing detection method based on video stream | |
| CN112183502B (en) | Method for determining driving state of driver, computer storage medium, and electronic device | |
| CN110059541A (en) | A kind of mobile phone usage behavior detection method and device in driving | |
| CN111027534A (en) | Compact double-license-plate detection method and device | |
| CN110222647B (en) | Face in-vivo detection method based on convolutional neural network | |
| CN112241647B (en) | Dangerous driving behavior early warning device and method based on depth camera | |
| CN113343926A (en) | Driver fatigue detection method based on convolutional neural network | |
| CN107315997B (en) | Sight orientation judgment method and system based on rapid feature point positioning | |
| CN113723339A (en) | Fatigue driving detection method, storage medium, and electronic device | |
| CN114120634B (en) | Dangerous driving behavior identification method, device, equipment and storage medium based on WiFi | |
| JPH0793700A (en) | Driver state monitoring device | |
| CN114973214A (en) | Unsafe driving behavior identification method based on face characteristic points | |
| CN112686103B (en) | Fatigue driving monitoring system for vehicle-road cooperation |
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 |