CN110188645A - For the method for detecting human face of vehicle-mounted scene, device, vehicle and storage medium - Google Patents
For the method for detecting human face of vehicle-mounted scene, device, vehicle and storage medium Download PDFInfo
- Publication number
- CN110188645A CN110188645A CN201910431152.XA CN201910431152A CN110188645A CN 110188645 A CN110188645 A CN 110188645A CN 201910431152 A CN201910431152 A CN 201910431152A CN 110188645 A CN110188645 A CN 110188645A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- face
- mounted scene
- face area
- interest
- 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.)
- Granted
Links
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Abstract
The application proposes a kind of for the method for detecting human face of vehicle-mounted scene, device, vehicle and storage medium, belongs to computer application technology.Wherein, this method comprises: obtaining the collected real-time video in the vehicle-mounted scene；Extract each frame image in the real-time video；The face area-of-interest set in the vehicle-mounted scene constructed according to each frame image and in advance detects in the vehicle-mounted scene with the presence or absence of face.Thus, pass through this method for detecting human face for vehicle-mounted scene, face area-of-interest set in building vehicle-mounted scene in advance, to only detect face in face area-of-interest, not only reduce the computation complexity of recognition of face, computing resource has been saved, and recognition accuracy can have been improved to avoid erroneous detection and missing inspection.
Description
Technical field
This application involves computer application technology more particularly to a kind of method for detecting human face for vehicle-mounted scene,
Device, vehicle and storage medium.
Background technique
With economic rapid development, the ownership of various countries' motor vehicle also rapid growth.But the increasing of vehicle guaranteeding organic quantity
Length also results in taking place frequently for traffic accident.With the continuous maturation of modern computer technology, can be driven by being arranged in the car
The person's of sailing behavioral value system, burglary-resisting system etc., improve the security performance of vehicle.Many onboard safety systems all rely on face
Identification technology.
In the related technology, it is usually carried out vehicle-mounted by the Face detection and tracking method in traditional computer vision algorithm
Recognition of face in environment.But since there is a serious shortage in the supply for vehicle environment narrow space, computing resource, and traditional computer regards
Feel that the computation complexity of algorithm is high, carries out face knowledge in a vehicle-mounted environment so as to cause by the application of traditional computer vision algorithm
Not, more computing resource can be not only occupied, but also is easy to produce erroneous detection and missing inspection, recognition accuracy is low.
Summary of the invention
The application propose for the method for detecting human face of vehicle-mounted scene, device, vehicle and storage medium, for solving phase
In the technology of pass, the application of traditional computer vision algorithm is subjected to recognition of face in a vehicle-mounted environment, can not only occupy more meter
Resource is calculated, and is easy to produce erroneous detection and missing inspection, the low problem of recognition accuracy.
The method for detecting human face for vehicle-mounted scene that the application one side embodiment proposes, comprising: obtain collected
For the real-time video in the vehicle-mounted scene；Extract each frame image in the real-time video；According to each frame figure
Face area-of-interest set in picture and the vehicle-mounted scene constructed in advance detects in the vehicle-mounted scene with the presence or absence of people
Face.
The human face detection device for vehicle-mounted scene that the application another aspect embodiment proposes, comprising: video acquisition mould
Block, for obtaining the collected real-time video in the vehicle-mounted scene；Image zooming-out module, it is described real-time for extracting
Each frame image in video；Face detection module, the vehicle-mounted field for constructing according to each frame image and in advance
Face area-of-interest set in scape detects in the vehicle-mounted scene with the presence or absence of face.
The vehicle that the application another further aspect embodiment proposes comprising: memory, processor and storage are on a memory simultaneously
The computer program that can be run on a processor, which is characterized in that the processor is realized as previously described when executing described program
The method for detecting human face for vehicle-mounted scene.
The computer readable storage medium that the application another further aspect embodiment proposes, is stored thereon with computer program,
It is characterized in that, the method for detecting human face for being used for vehicle-mounted scene as previously described is realized when described program is executed by processor.
The computer program that the another aspect embodiment of the application proposes, when which is executed by processor, to realize this Shen
The method for detecting human face of vehicle-mounted scene please be used for described in embodiment.
It is provided by the embodiments of the present application for the method for detecting human face of vehicle-mounted scene, device, vehicle, computer-readable storage
Medium and computer program, the available collected real-time video in vehicle-mounted scene, and extract in real-time video
Each frame image, and then the face area-of-interest set in the vehicle-mounted scene constructed according to each frame image and in advance, detection
It whether there is face in vehicle-mounted scene.As a result, by constructing the face area-of-interest set in vehicle-mounted scene in advance, thus only
Face is detected in face area-of-interest, not only reduces the computation complexity of recognition of face, has saved computing resource, and
Recognition accuracy can be improved to avoid erroneous detection and missing inspection.
The additional aspect of the application and advantage will be set forth in part in the description, and will partially become from the following description
It obtains obviously, or recognized by the practice of the application.
Detailed description of the invention
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is a kind of flow diagram of the method for detecting human face for vehicle-mounted scene provided by the embodiment of the present application；
Fig. 2 is process signal of the another kind provided by the embodiment of the present application for the method for detecting human face of vehicle-mounted scene
Figure；
Fig. 3 is a kind of structural schematic diagram of the human face detection device for vehicle-mounted scene provided by the embodiment of the present application；
Fig. 4 is the structural schematic diagram of vehicle provided by the embodiment of the present application.
Specific embodiment
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element.The embodiments described below with reference to the accompanying drawings are exemplary,
It is intended for explaining the application, and should not be understood as the limitation to the application.
The application of traditional computer vision algorithm is carried out people in the related technology by the embodiment of the present application in a vehicle-mounted environment
Face identification, can not only occupy more computing resource, but also be easy to produce erroneous detection and missing inspection, the low problem of recognition accuracy mentions
A kind of method for detecting human face for vehicle-mounted scene out.
Method for detecting human face provided by the embodiments of the present application for vehicle-mounted scene, it is available collected for vehicle-mounted
Real-time video in scene, and extract each frame image in real-time video, and then construct according to each frame image and in advance
Face area-of-interest set in vehicle-mounted scene, detection vehicle-mounted scene is interior to whether there is face.As a result, by constructing vehicle in advance
The face area-of-interest set carried in scene not only reduces face to only detect face in face area-of-interest
The computation complexity of identification has saved computing resource, and can improve recognition accuracy to avoid erroneous detection and missing inspection.
Below with reference to the accompanying drawings it is situated between to provided by the present application for the method for detecting human face of vehicle-mounted scene, device, vehicle, storage
Matter and computer program are described in detail.
Fig. 1 is a kind of flow diagram of the method for detecting human face for vehicle-mounted scene provided by the embodiment of the present application.
As shown in Figure 1, this is used for the method for detecting human face of vehicle-mounted scene, comprising the following steps:
Step 101, the collected real-time video in the vehicle-mounted scene is obtained.
It should be noted that the method for detecting human face for vehicle-mounted scene of the embodiment of the present application, it can be by the application institute
The human face detection device for vehicle-mounted scene provided executes.In actual use, for vehicle-mounted provided by the embodiment of the present application
The human face detection device of scene can be only fitted in any vehicle, to execute the Face datection side for vehicle-mounted scene of the application
Method.
In the embodiment of the present application, the video information in camera acquisition vehicle can be installed in the car, that is, be directed to vehicle
The video information in scene is carried, and then will be in the storage equipment of collected video information storage in the car.Wherein, camera
Quantity and installation site can be arranged according to actual recognition of face demand.For example, if only need to the face of driver into
Row detection, then can install a camera in the suitable position in front of driver's seat；If desired seats all in vehicle are multiplied
Visitor face detected, then can be respectively mounted camera in the suitable position in front of each seat, if a camera can
To collect the image at each seat in vehicle, one camera only can also be installed in suitable position, acquire in vehicle and own
The image at seat.
As a kind of possible implementation, the human face detection device for vehicle-mounted scene of the embodiment of the present application can root
According to current temporal information, for the real-time video in vehicle-mounted scene needed for acquisition in the storage equipment of vehicle, alternatively,
It can be according to historical time information, for the history video in vehicle-mounted scene needed for acquisition in the storage equipment of vehicle.
As a kind of possible implementation, can also be taken the photograph by the modes such as wired connection or wireless network connection, foundation
As head and for the communication connection between the human face detection device of vehicle-mounted scene, so that camera can be by the vehicle-mounted of acquisition
Real-time video in scene is transmitted directly to the human face detection device for vehicle-mounted scene, real-time in vehicle-mounted scene to realize
The acquisition of video.
Step 102, each frame image in the real-time video is extracted.
It in the embodiment of the present application, can be to real-time after getting the real-time video of acquisition being directed in vehicle-mounted scene
Each frame image in video is identified, to determine in the corresponding time range of real-time video obtained, is in vehicle environment
No includes face.Therefore, each frame image in real-time video can be extracted, i.e., real-time video is read as unit of frame
It takes, it may be necessary to save each frame image in real-time video.
Step 103, the face area-of-interest in the vehicle-mounted scene constructed according to each frame image and in advance
Set detects in the vehicle-mounted scene with the presence or absence of face.
Wherein, face area-of-interest refers to preset face corresponding region in the picture.It should be noted that working as
It may include that multiple face senses are emerging in face area-of-interest set when needing to carry out Face datection to multiple positions in vehicle
Interesting region.
In the embodiment of the present application, due in a vehicle-mounted environment, where the face of the passenger at driver and each seat
Position is all relatively-stationary, therefore can be obtained in the image that camera acquires according to the installation site of camera in vehicle
The priori knowledge of human face region, to construct the face area-of-interest set in vehicle-mounted scene in advance.
It can be according to pre- after extracting each frame image in real-time video as a kind of possible implementation
The face area-of-interest set for first constructing vehicle-mounted scene determines the face area-of-interest in each frame image, and then detects
It whether include face in the face area-of-interest of each frame image, to determine vehicle according to the testing result of each frame image
It carries and whether there is face in scene.I.e. in a kind of possible way of realization of the embodiment of the present application, above-mentioned steps 103 be can wrap
It includes:
The face area-of-interest in each frame image is determined according to the face area-of-interest set；
Judge in the face area-of-interest in each frame image with the presence or absence of face；
If so, determining that there are faces in the vehicle-mounted scene；
If it is not, then determining that face is not detected in the vehicle-mounted scene.
As a kind of possible implementation, each face area-of-interest in face area-of-interest set can be used
Each face area-of-interest pixel coordinate in the picture indicates, thus extract each frame image in real-time video it
Afterwards, it according to the pixel coordinate of face area-of-interest each in face area-of-interest set, determines each in real-time video
Each face area-of-interest in frame image.Judge that each face in each frame image is interested using Face datection algorithm later
It whether there is face in region.
Specifically, can determine and exist in the image if in image including face area-of-interest there are face
Face, it can determine that there are faces in vehicle-mounted scene；If being not present in each face area-of-interest in each frame image
Face then can be determined that and face be not detected in vehicle-mounted scene.
It needs, the quantity of the face area-of-interest in face area-of-interest set, with progress Face datection
Actual scene it is related.If only carrying out Face datection to a position in vehicle, for example Face datection only is carried out to operator seat,
It then can only include a face in face area-of-interest set；If desired face inspection is carried out to multiple positions in vehicle
It surveys, for example Face datection is carried out to seats all in vehicle, then may include multiple face senses in face area-of-interest set
Interest region, i.e., the quantity for the face area-of-interest for including in face area-of-interest set and need to carry out Face datection
The quantity of position is identical.
Optionally, when needing to carry out multiple positions in vehicle Face datection, and the corresponding camera in each position
When, the corresponding relationship of the mark of camera and the mark of camera and face area-of-interest can also be preset.To mention
It, can be according to the mark of camera that acquires the real-time video and preset after each frame image for taking out real-time video
The mark of camera and the corresponding relationship of face area-of-interest, determine the real-time video from face area-of-interest set
Corresponding face area-of-interest, and then according to the corresponding face area-of-interest of the real-time video, determine each frame image
In face area-of-interest.
In the embodiment of the present application, however, it is determined that there are faces in vehicle-mounted scene, then can determine in vehicle-mounted scene and detect
Face；Otherwise, then it can determine and not detect face in vehicle-mounted scene.
Method for detecting human face provided by the embodiments of the present application for vehicle-mounted scene, it is available collected for vehicle-mounted
Real-time video in scene, and extract each frame image in real-time video, and then construct according to each frame image and in advance
Face area-of-interest set in vehicle-mounted scene, detection vehicle-mounted scene is interior to whether there is face.As a result, by constructing vehicle in advance
The face area-of-interest set carried in scene not only reduces face to only detect face in face area-of-interest
The computation complexity of identification has saved computing resource, and can improve recognition accuracy to avoid erroneous detection and missing inspection.
In a kind of possible way of realization of the application, the face area-of-interest set in vehicle-mounted scene can be according to vehicle
The priori knowledges such as camera and the positional relationship that needs the seat for carrying out Face datection in scene are carried to be constructed；Or it can be with
It is constructed in advance according to the probability of occurrence of face each position in vehicle environment.
Below with reference to Fig. 2, the method for detecting human face provided by the embodiments of the present application for vehicle-mounted scene is carried out further
Explanation.
Fig. 2 is process signal of the another kind provided by the embodiment of the present application for the method for detecting human face of vehicle-mounted scene
Figure.
As shown in Fig. 2, this is used for the method for detecting human face of vehicle-mounted scene, comprising the following steps:
Step 201, the positional relationship of camera and target seat in the vehicle-mounted scene is determined.
Wherein, target seat refers to the seat for needing to carry out Face datection in current vehicle-mounted scene.For example, current vehicle-mounted
It needs to carry out Face datection to driver in scene, then target seat is operator seat；If needing in current vehicle-mounted scene to all
Passenger carries out Face datection, then target seat is all seats in vehicle.
In the embodiment of the present application, face area-of-interest set can be according to camera in vehicle-mounted scene in vehicle-mounted scene
It is constructed with the positional relationship of target seat.Wherein, in vehicle-mounted scene camera and target seat positional relationship, be in camera
It is just had determined when installation.
Optionally, camera and target in vehicle-mounted scene can be determined by establishing the three-dimensional system of coordinate in vehicle-mounted scene
The positional relationship of seat.For example, can using the central point in vehicle environment as coordinate origin, with lateral direction of car horizontal direction be X
Axis, using vehicle forward direction as Y-axis, three-dimensional system of coordinate is established by Z axis of direction perpendicular to the ground, and determine in camera respectively
Coordinate and target backrest central point coordinate in three-dimensional system of coordinate of the heart point in three-dimensional system of coordinate, and then basis
The coordinate and coordinate of the target backrest central point in three-dimensional system of coordinate of camera central point, that is, can determine that vehicle-mounted scene
The positional relationship of interior camera and target seat.For example, may include that camera central point is leaned on target seat in positional relationship
Carry on the back the line of the linear distance and camera central point and target backrest central point between central point respectively with X-axis, Y
The parameters such as angle of axis, Z axis.
As a kind of possible implementation, if target seat has multiple, camera has one, then can determine respectively
The positional relationship of camera and each target seat；If target seat has multiple, i.e., each target seat correspondence with camera
One camera can then determine the positional relationship between the corresponding target seat of each camera respectively.
It should be noted that determining the method for the positional relationship of camera and target seat and position in vehicle-mounted scene
The parameter for including in relationship can include but is not limited to situation listed above.It in actual use, can be pre- according to actual needs
If determining the parameter for including in the method and positional relationship of the positional relationship of camera and target seat in vehicle-mounted scene, this
Application embodiment does not limit this.
Step 202, according to the positional relationship of camera and target seat in the vehicle-mounted scene, the vehicle-mounted scene is constructed
Interior face area-of-interest set；Wherein, the face area-of-interest set has at least one face area-of-interest.
It should be noted that there is at least one face area-of-interest, and face in face area-of-interest set
The quantity of face area-of-interest is identical as the quantity of target seat in area-of-interest set.For example, if the number of target seat
Amount has one, then has a face area-of-interest in face area-of-interest set；If the quantity of target seat have it is multiple,
Then there are in face area-of-interest set multiple face area-of-interests.
Work as passenger since the height of the mankind is in relatively fixed range as a kind of possible implementation
When being sitting in seat, face and the relative position of seat also compared with fix.Therefore, in a kind of possible reality of the embodiment of the present application
In existing form, it can be determined in target seat according to the height ranges of position and the mankind of the target seat in vehicle-mounted scene
The position of human body, and then according to the proportionate relationship of human head and body, determine position of the face in target seat.It is later
The position of target seat corresponding face and camera can be determined according to the positional relationship of determining camera and target seat
Relationship, so as to determine position of the face in the image that camera is shot, i.e. target according to the acquisition parameters of camera
The corresponding face area-of-interest of seat.If the quantity of target seat has multiple, can determine respectively according to the method described above
The corresponding face area-of-interest of each target seat, to constitute face area-of-interest set.
It should be noted that the proportionate relationship of the height ranges of the mankind and human head and body, can be according to right
What the statistical data of human physiological's feature obtained, and the Face datection for vehicle-mounted scene that can be set in advance in the application fills
In setting.
Further, if not being available the positional relationship building face area-of-interest set of camera and target seat,
Then face area-of-interest set can be determined according to the probability of occurrence of face each position in a vehicle-mounted environment.I.e. in the application
In a kind of possible way of realization of embodiment, face area-of-interest set can also be constructed in advance by following steps:
It obtains for the sample video image in the vehicle-mounted scene；
Face datection is carried out to the sample video image based on Face datection algorithm, in the determination vehicle-mounted scene
Face probability of occurrence thermal map；
The face area-of-interest set in the vehicle-mounted scene is constructed according to the face probability of occurrence thermal map；Wherein,
The face area-of-interest set has at least one face area-of-interest.
Wherein, sample video image can be the history in a period of time acquired by the camera in vehicle-mounted scene
Video image, for example can be the history video image in the times such as one month, three months.It is understood that vehicle-mounted scene
Interior sample video image can recorde in the corresponding time range of the sample video image, face each position in vehicle-mounted scene
The appearance situation set.
It should be noted that in actual use, the duration of the sample video image of acquisition can be preset according to actual needs,
The embodiment of the present application does not limit this.
As a kind of possible implementation, the camera in vehicle environment can be arrived collected video image storage
In storage equipment in vehicle-mounted scene, so as to obtain from the storage equipment in vehicle environment for the sample in vehicle-mounted scene
This video image.It is based on Face datection algorithm later, Face datection is carried out to each frame image in sample video image, in turn
According to position of the face in every frame image is detected, the face probability of occurrence thermal map in vehicle-mounted scene is determined, so as to root
According to face probability of occurrence thermal map, the face area-of-interest set in vehicle-mounted maternity leave is constructed.
Specifically, including the appearance of each region of face in the image that camera acquires in face probability of occurrence thermal map
Probability, so as to be determined as face area-of-interest, according to determining for the highest one or more regions of probability of occurrence
One or more face area-of-interests construct face area-of-interest set.
It should be noted that the Face datection algorithm for carrying out Face datection to sample video image, can be in advance
It is preset.In actual use, the detection accuracy according to required for concrete application scene, the computing capability for calculating equipment etc. are joined
Number, selects suitable Face datection algorithm, and the application implementation does not limit this.
Step 203, the collected real-time video in the vehicle-mounted scene is obtained.
Step 204, each frame image in the real-time video is extracted.
Step 205, the face area-of-interest in the vehicle-mounted scene constructed according to each frame image and in advance
Set detects in the vehicle-mounted scene with the presence or absence of face.
The specific implementation process and principle of above-mentioned steps 203-205, is referred to the detailed description of above-described embodiment, herein
It repeats no more.
Step 206, and if it exists, the current frame image that then will test out face is sent to the terminal device of user and mentions
It wakes up.
It, can be according to actual application scenarios, to vehicle-mounted scene in a kind of possible way of realization of the embodiment of the present application
In Face datection result make different subsequent processings.
As a kind of possible implementation, if actual application scenarios be it is antitheft, can determine in vehicle-mounted scene
When detecting face, the current frame image that will test out face is sent to the terminal device of user and reminds, so that user can
Discriminate whether being that stranger opens vehicle according to the facial image got.
Further, if face occurs in continuous multiple frames image, the corresponding video clip of multiple image can be sent
To the terminal device of user, i.e., in a kind of possible way of realization of the embodiment of the present application, above-mentioned steps 206 can also include:
When continuous multiple frames image detection goes out face, the continuous multiple frames image is sent to use in a manner of video clip
The terminal device at family.
It should be noted that if determine in continuous multiple frames image face occur, then it can be by the continuous multiple frames image pair
The video clip answered is intercepted from real-time video and is come out, and is sent to the terminal device of user, so that feedback result is more
Vividly, it accurately, checks and judges convenient for user.
Preferably, user can also preset the terminal device that can receive feedback information, and receive feedback information
Time.For example, user can forbid the human face detection device for vehicle-mounted scene to send facial image letter when using vehicle
Breath or video information, to avoid garbage is frequently got；When vehicle is not used, opens and send human face image information or view
The function of frequency information.
It can also be to vehicle after obtaining the face recognition result in vehicle-mounted scene as a kind of possible implementation
The face quantity carried in environment is counted, and statistical data is sent to the terminal device of user.Specifically, if it is determined that vehicle-mounted
Face is not present in scene, then can determine that the face quantity in vehicle-mounted scene is 0；If it is determined that there are face in vehicle-mounted scene,
The quantity that the area-of-interest of face can then be will test out is determined as face quantity in vehicle environment；Alternatively, can also be right
The facial characteristics of each face detected is identified and is compared, and to determine the different faces detected, and then is determined
Face quantity in vehicle-mounted scene.
It optionally, can will be in the vehicle-mounted scene that counted every time when statistical data to be sent to the terminal device of user
Face quantity be sent to the terminal device of user in real time, can also be according to the time cycle of user preset, by preset time week
The summation of the face quantity counted in phase is sent to the terminal device of user.
It should be noted that in actual use, the feedback system of the terminal device, statistical data that receive statistical data is timely
Between period etc., can be default according to practical application scene and user demand, the embodiment of the present application does not limit this.
For example, it when the human face detection device for vehicle-mounted scene of the embodiment of the present application is applied in taxi, connects
The terminal device for receiving statistical data is the data statistics platform of the mobile phone of driver, taxi company, receives the pre- of statistical data
If the time cycle is 1 day, then the passengers quantity in taxi can be determined, and count according to each face recognition result
The summation of daily passengers quantity is sent to the mobile phone of driver and the data statistics platform of taxi company, for driver
And taxi company understands the operation situation of vehicle.
As a kind of possible implementation, the face recognition result of the embodiment of the present application can be also used for driver fatigue
Detection, smoke detection, detection, the line-of-sight detection etc. of making a phone call safe drivings scene, it is only necessary to using corresponding recognizer to this
Apply for that the Face datection result of embodiment carries out further identifying processing, to determine that driver drives with the presence or absence of nonstandard danger
Sail behavior.
It, then can be using preset face recognition algorithms to detecting specifically, if it is determined that there are faces in vehicle-mounted scene
Facial image carry out identifying processing, in the facial image that confirmly detects with the presence or absence of preset dangerous driving behavior, if
In the presence of then driver can be reminded by modes such as buzzer, voice promptings.
It should be noted that being used for the method for detecting human face of vehicle-mounted scene provided by the embodiment of the present application, can reduce
The computation complexity of recognition of face scene, application scenarios can include but is not limited to situation listed above.
Method for detecting human face provided by the embodiments of the present application for vehicle-mounted scene, by determining camera in vehicle-mounted scene
Vehicle-mounted scene is constructed and according to the positional relationship of camera in vehicle-mounted scene and target seat with the positional relationship of target seat
Interior face area-of-interest set, and the collected real-time video in vehicle-mounted scene is obtained, later according to extraction
Real-time video in each frame image and the face area-of-interest set in the vehicle-mounted scene that constructs in advance, detect vehicle-mounted field
It whether there is face in scape, and then determining that the current frame image that will test out face is sent out when detecting face in vehicle-mounted scene
The terminal device for giving user is reminded.As a result, by constructing the face area-of-interest set in vehicle-mounted scene in advance, with
And Face datection result is fed back into user, and the computation complexity of recognition of face is not only reduced, computing resource has been saved, it mentions
Recognition accuracy has been risen, and has improved interactivity and scalability, has further improved user experience.
In order to realize above-described embodiment, the application also proposes a kind of human face detection device for vehicle-mounted scene.
Fig. 3 is a kind of structural schematic diagram of the human face detection device for vehicle-mounted scene provided by the embodiments of the present application.
As shown in figure 3, this is used for the human face detection device 30 of vehicle-mounted scene, comprising:
Video acquiring module 31, for obtaining the collected real-time video in the vehicle-mounted scene；
Image zooming-out module 32, for extracting each frame image in the real-time video；
Face detection module 33, the face in the vehicle-mounted scene for constructing according to each frame image and in advance
Area-of-interest set detects in the vehicle-mounted scene with the presence or absence of face.
In actual use, the human face detection device provided by the embodiments of the present application for vehicle-mounted scene, can be configured
In any vehicle, to execute the method for detecting human face for being previously used for vehicle-mounted scene.
Human face detection device provided by the embodiments of the present application for vehicle-mounted scene, it is available collected for vehicle-mounted
Real-time video in scene, and extract each frame image in real-time video, and then construct according to each frame image and in advance
Face area-of-interest set in vehicle-mounted scene, detection vehicle-mounted scene is interior to whether there is face.As a result, by constructing vehicle in advance
The face area-of-interest set carried in scene not only reduces face to only detect face in face area-of-interest
The computation complexity of identification has saved computing resource, and can improve recognition accuracy to avoid erroneous detection and missing inspection.
In a kind of possible way of realization of the application, the above-mentioned human face detection device 30 for vehicle-mounted scene, further includes:
Face area-of-interest set constructs module, for constructing the face area-of-interest in the vehicle-mounted scene in advance
Set；
Wherein, the face area-of-interest set building module is specifically used for:
Determine the positional relationship of camera and target seat in the vehicle-mounted scene；
According to the positional relationship of camera and target seat in the vehicle-mounted scene, the face in the vehicle-mounted scene is constructed
Area-of-interest set；Wherein, the face area-of-interest set has at least one face area-of-interest.
Further, in the alternatively possible way of realization of the application, the above-mentioned Face datection for vehicle-mounted scene is filled
Set 30, further includes:
Face area-of-interest set constructs module, for constructing the face area-of-interest in the vehicle-mounted scene in advance
Set；
Wherein, the face area-of-interest set building module is specifically used for:
It obtains for the sample video image in the vehicle-mounted scene；
Face datection is carried out to the sample video image based on Face datection algorithm, in the determination vehicle-mounted scene
Face probability of occurrence thermal map；
The face area-of-interest set in the vehicle-mounted scene is constructed according to the face probability of occurrence thermal map；Wherein,
The face area-of-interest set has at least one face area-of-interest.
Further, in the application in another possible way of realization, above-mentioned face detection module 33 is specifically used for:
The face area-of-interest in each frame image is determined according to the face area-of-interest set；
Judge in the face area-of-interest in each frame image with the presence or absence of face；
If so, determining that there are faces in the vehicle-mounted scene；
If it is not, then determining that face is not detected in the vehicle-mounted scene.
Further, in the application in another possible way of realization, the above-mentioned Face datection for vehicle-mounted scene is filled
Set 30, further includes:
Reminding module will test out the current frame image of face after detecting face in the vehicle-mounted scene
The terminal device for being sent to user is reminded.
Further, in the application in another possible way of realization, above-mentioned reminding module is also used to:
When continuous multiple frames image detection goes out face, the continuous multiple frames image is sent to use in a manner of video clip
The terminal device at family.
It should be noted that it is aforementioned to Fig. 1, the solution of the method for detecting human face embodiment shown in Fig. 2 for vehicle-mounted scene
The human face detection device 30 for vehicle-mounted scene that explanation is also applied for the embodiment is released, details are not described herein again.
Human face detection device provided by the embodiments of the present application for vehicle-mounted scene, by determining camera in vehicle-mounted scene
Vehicle-mounted scene is constructed and according to the positional relationship of camera in vehicle-mounted scene and target seat with the positional relationship of target seat
Interior face area-of-interest set, and the collected real-time video in vehicle-mounted scene is obtained, later according to extraction
Real-time video in each frame image and the face area-of-interest set in the vehicle-mounted scene that constructs in advance, detect vehicle-mounted field
It whether there is face in scape, and then determining that the current frame image that will test out face is sent out when detecting face in vehicle-mounted scene
The terminal device for giving user is reminded.As a result, by constructing the face area-of-interest set in vehicle-mounted scene in advance, with
And Face datection result is fed back into user, and the computation complexity of recognition of face is not only reduced, computing resource has been saved, it mentions
Recognition accuracy has been risen, and has improved interactivity and scalability, has further improved user experience.
In order to realize above-described embodiment, the application also proposes a kind of vehicle.
Fig. 4 is the structural schematic diagram of the vehicle of one embodiment of the invention.
As shown in figure 4, above-mentioned vehicle 200 includes:
Memory 210 and processor 220 connect the bus 230 of different components (including memory 210 and processor 220),
Memory 210 is stored with computer program, realizes when processor 220 executes described program and is used for described in the embodiment of the present application
The method for detecting human face of vehicle-mounted scene.
Bus 230 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Vehicle 200 typically comprises various electronic readable medium.These media can be it is any can be by vehicle 200
The usable medium of access, including volatile and non-volatile media, moveable and immovable medium.
Memory 210 can also include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 240 and/or cache memory 250.Vehicle 200 may further include other removable/nonremovable
, volatile/non-volatile computer system storage medium.Only as an example, storage system 260 can be used for reading and writing not removable
Dynamic, non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").Although not shown in fig 4, it can provide
Disc driver for being read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to removable anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 230.Memory 210 may include that at least one program produces
Product, the program product have one group of (for example, at least one) program module, and it is each that these program modules are configured to perform the application
The function of embodiment.
Program/utility 280 with one group of (at least one) program module 270, can store in such as memory
In 210, such program module 270 includes --- but being not limited to --- operating system, one or more application program, other
It may include the realization of network environment in program module and program data, each of these examples or certain combination.Journey
Sequence module 270 usually executes function and/or method in embodiments described herein.
Vehicle 200 can also be logical with one or more external equipments 290 (such as keyboard, sensing equipment, display 291 etc.)
Letter, can also be enabled a user to one or more equipment interact with the vehicle 200 communicate, and/or with make the vehicle 200
Any equipment (such as network interface card, modem etc.) that can be communicated with one or more of the other calculating equipment communicates.This
Kind communication can be carried out by input/output (I/O) interface 292.Also, vehicle 200 can also by network adapter 293 with
One or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.Such as
Shown in figure, network adapter 293 is communicated by bus 230 with other modules of vehicle 200.It should be understood that although not showing in figure
Out, other hardware and/or software module can be used in conjunction with vehicle 200, including but not limited to: microcode, device driver, superfluous
Remaining processing unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
Program of the processor 220 by operation storage in memory 210, thereby executing various function application and data
Processing.
It should be noted that the implementation process and technical principle of the vehicle of the present embodiment are referring to aforementioned to the embodiment of the present application
The method for detecting human face for vehicle-mounted scene explanation, details are not described herein again.
Vehicle provided by the embodiments of the present application can execute the foregoing method for detecting human face for being used for vehicle-mounted scene,
The collected real-time video in vehicle-mounted scene is obtained, and extracts each frame image in real-time video, and then according to every
Face area-of-interest set in one frame image and the vehicle-mounted scene constructed in advance, detection vehicle-mounted scene is interior to whether there is people
Face.As a result, by constructing the face area-of-interest set in vehicle-mounted scene in advance, to only be examined in face area-of-interest
Survey face, not only reduce the computation complexity of recognition of face, saved computing resource, and can to avoid erroneous detection and missing inspection,
Improve recognition accuracy.
In order to realize above-described embodiment, the application also proposes a kind of computer readable storage medium.
Wherein, the computer readable storage medium, is stored thereon with computer program, when which is executed by processor,
To realize the method for detecting human face for being used for vehicle-mounted scene described in the embodiment of the present application.
In order to realize above-described embodiment, the application another further aspect embodiment provides a kind of computer program, which is located
When managing device execution, to realize the method for detecting human face for being used for vehicle-mounted scene described in the embodiment of the present application.
In a kind of optional way of realization, the present embodiment can be using any group of one or more computer-readable media
It closes.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable to deposit
Storage media for example may be-but not limited to-system, device or the device of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor
Part, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: to have
The electrical connection of one or more conducting wires, portable computer diskette, hard disk, random access memory (RAM), read-only memory
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
It further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It is fully executed on consumer electronic devices, partly executes on consumer electronic devices, held as an independent software package
Row, partially part executes in devices in remote electronic or completely in devices in remote electronic or service on consumer electronic devices
It is executed on device.In the situation for being related to devices in remote electronic, devices in remote electronic can pass through the network of any kind --- packet
It includes local area network (LAN) or wide area network (WAN)-is connected to consumer electronic devices, or, it may be connected to external electronic device (example
It is such as connected using ISP by internet).
Those skilled in the art will readily occur to its of the application after considering specification and practicing the invention applied here
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or
The common knowledge in the art that person's adaptive change follows the general principle of the application and do not invent including the application
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the application are wanted by right
It asks and points out.
It should be understood that the application is not limited to the precise structure that has been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.Scope of the present application is only limited by the accompanying claims.
Claims (14)
1. a kind of method for detecting human face for vehicle-mounted scene characterized by comprising
Obtain the collected real-time video in the vehicle-mounted scene；
Extract each frame image in the real-time video；
The face area-of-interest set in the vehicle-mounted scene constructed according to each frame image and in advance, described in detection
It whether there is face in vehicle-mounted scene.
2. the method according to claim 1, wherein being constructed in the vehicle-mounted scene in advance by following steps
Face area-of-interest set:
Determine the positional relationship of camera and target seat in the vehicle-mounted scene；
According to the positional relationship of camera and target seat in the vehicle-mounted scene, the face sense constructed in the vehicle-mounted scene is emerging
Interesting regional ensemble；Wherein, the face area-of-interest set has at least one face area-of-interest.
3. the method according to claim 1, wherein being constructed in the vehicle-mounted scene in advance by following steps
Face area-of-interest set:
It obtains for the sample video image in the vehicle-mounted scene；
Face datection is carried out to the sample video image based on Face datection algorithm, with the face in the determination vehicle-mounted scene
Probability of occurrence thermal map；
The face area-of-interest set in the vehicle-mounted scene is constructed according to the face probability of occurrence thermal map；Wherein, described
Face area-of-interest set has at least one face area-of-interest.
4. the method according to claim 1, wherein the institute constructed according to each frame image and in advance
The face area-of-interest set in vehicle-mounted scene is stated, is detected in the vehicle-mounted scene with the presence or absence of face, comprising:
The face area-of-interest in each frame image is determined according to the face area-of-interest set；
Judge in the face area-of-interest in each frame image with the presence or absence of face；
If so, determining that there are faces in the vehicle-mounted scene；
If it is not, then determining that face is not detected in the vehicle-mounted scene.
5. method according to claim 1 to 4, which is characterized in that be in the detection vehicle-mounted scene
It is no there are after face, the method also includes:
If it exists, then the current frame image that will test out face is sent to the terminal device of user and reminds.
6. according to the method described in claim 5, it is characterized by further comprising:
When continuous multiple frames image detection goes out face, the continuous multiple frames image is sent to user's in a manner of video clip
Terminal device.
7. a kind of human face detection device for vehicle-mounted scene characterized by comprising
Video acquiring module, for obtaining the collected real-time video in the vehicle-mounted scene；
Image zooming-out module, for extracting each frame image in the real-time video；
Face detection module, the face in the vehicle-mounted scene for constructing according to each frame image and in advance are interested
Regional ensemble detects in the vehicle-mounted scene with the presence or absence of face.
8. device according to claim 7, which is characterized in that further include:
Face area-of-interest set constructs module, for constructing the face area-of-interest collection in the vehicle-mounted scene in advance
It closes；
Wherein, the face area-of-interest set building module is specifically used for:
Determine the positional relationship of camera and target seat in the vehicle-mounted scene；
According to the positional relationship of camera and target seat in the vehicle-mounted scene, the face sense constructed in the vehicle-mounted scene is emerging
Interesting regional ensemble；Wherein, the face area-of-interest set has at least one face area-of-interest.
9. device according to claim 7, which is characterized in that further include:
Face area-of-interest set constructs module, for constructing the face area-of-interest collection in the vehicle-mounted scene in advance
It closes；
Wherein, the face area-of-interest set building module is specifically used for:
It obtains for the sample video image in the vehicle-mounted scene；
Face datection is carried out to the sample video image based on Face datection algorithm, with the face in the determination vehicle-mounted scene
Probability of occurrence thermal map；
The face area-of-interest set in the vehicle-mounted scene is constructed according to the face probability of occurrence thermal map；Wherein, described
Face area-of-interest set has at least one face area-of-interest.
10. device according to claim 7, which is characterized in that the face detection module is specifically used for:
The face area-of-interest in each frame image is determined according to the face area-of-interest set；
Judge in the face area-of-interest in each frame image with the presence or absence of face；
If so, determining that there are faces in the vehicle-mounted scene；
If it is not, then determining that face is not detected in the vehicle-mounted scene.
11. device according to any one of claims 7 to 10, which is characterized in that further include:
Reminding module, after detecting face in the vehicle-mounted scene, the current frame image that will test out face is sent
It is reminded to the terminal device of user.
12. device according to claim 11, which is characterized in that the reminding module is also used to: in continuous multiple frames image
When detecting face, the continuous multiple frames image is sent to the terminal device of user in a manner of video clip.
13. a kind of vehicle characterized by comprising memory, processor and be stored on the memory and can be at the place
The computer program run on reason device when the processor executes the computer program, is realized as appointed in claim 1 to 6
The method for detecting human face of vehicle-mounted scene is used for described in one.
14. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Such as the method for detecting human face described in any one of claims 1 to 6 for vehicle-mounted scene is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431152.XA CN110188645B (en) | 2019-05-22 | 2019-05-22 | Face detection method and device for vehicle-mounted scene, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910431152.XA CN110188645B (en) | 2019-05-22 | 2019-05-22 | Face detection method and device for vehicle-mounted scene, vehicle and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110188645A true CN110188645A (en) | 2019-08-30 |
| CN110188645B CN110188645B (en) | 2022-10-21 |
Family
ID=67717301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910431152.XA Active CN110188645B (en) | 2019-05-22 | 2019-05-22 | Face detection method and device for vehicle-mounted scene, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110188645B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414833A (en) * | 2020-03-16 | 2020-07-14 | 北京嘀嘀无限科技发展有限公司 | Target detection tracking method, target detection tracking device, and storage medium |
| CN113561908A (en) * | 2021-07-27 | 2021-10-29 | 奇瑞新能源汽车股份有限公司 | Control method and device of vehicle-mounted face recognition equipment |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202472864U (en) * | 2012-03-06 | 2012-10-03 | 上海骏聿数码科技有限公司 | Driver fatigue early warning device |
| CN103873741A (en) * | 2014-04-02 | 2014-06-18 | 北京奇艺世纪科技有限公司 | Method and device for substituting area of interest in video |
| CN104494564A (en) * | 2014-12-22 | 2015-04-08 | 清华大学苏州汽车研究院（吴江） | Vehicle anti-theft system based on human face recognition |
| CN104527570A (en) * | 2014-12-22 | 2015-04-22 | 清华大学苏州汽车研究院（吴江） | Vehicle anti-theft system based on panoramic picture |
| CN204415338U (en) * | 2014-12-22 | 2015-06-24 | 清华大学苏州汽车研究院（吴江） | A kind of Vehicle Anti-Theft System based on recognition of face |
| CN204547917U (en) * | 2015-04-15 | 2015-08-12 | 郭帅 | The overcrowding detection alarm system of a kind of car |
| CN104850771A (en) * | 2015-04-30 | 2015-08-19 | 广东欧珀移动通信有限公司 | Identity verification method and related equipment |
| US20150286884A1 (en) * | 2014-04-04 | 2015-10-08 | Xerox Corporation | Machine learning approach for detecting mobile phone usage by a driver |
| CN105691367A (en) * | 2016-01-25 | 2016-06-22 | 大连楼兰科技股份有限公司 | Bus initiative braking method and system based on association of images and heartbeat monitoring |
| CN106599774A (en) * | 2016-10-31 | 2017-04-26 | 深圳市元征科技股份有限公司 | Vehicle alarm method and device |
| CN106709420A (en) * | 2016-11-21 | 2017-05-24 | 厦门瑞为信息技术有限公司 | Method for monitoring driving behaviors of driver of commercial vehicle |
| CN106934355A (en) * | 2017-02-28 | 2017-07-07 | 西交利物浦大学 | In-car hand detection method based on depth convolutional neural networks |
| CN107766835A (en) * | 2017-11-06 | 2018-03-06 | 贵阳宏益房地产开发有限公司 | traffic safety detection method and device |
| CN207173533U (en) * | 2017-09-11 | 2018-04-03 | 马芳武 | A kind of vehicle-mounted intelligent video monitoring and recognition of face anti-theft alarm system |
| CN108021856A (en) * | 2016-10-31 | 2018-05-11 | 比亚迪股份有限公司 | Light for vehicle recognition methods, device and vehicle |
| CN108629316A (en) * | 2018-05-08 | 2018-10-09 | 东北师范大学人文学院 | A kind of video accident detection method of various visual angles |
| CN109766841A (en) * | 2019-01-10 | 2019-05-17 | 深圳大学 | Vehicle checking method, device and computer readable storage medium |
| CN109784290A (en) * | 2019-01-23 | 2019-05-21 | 科大讯飞股份有限公司 | A kind of object detection method, device, equipment and readable storage medium storing program for executing |
-
2019
- 2019-05-22 CN CN201910431152.XA patent/CN110188645B/en active Active
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202472864U (en) * | 2012-03-06 | 2012-10-03 | 上海骏聿数码科技有限公司 | Driver fatigue early warning device |
| CN103873741A (en) * | 2014-04-02 | 2014-06-18 | 北京奇艺世纪科技有限公司 | Method and device for substituting area of interest in video |
| US20150286884A1 (en) * | 2014-04-04 | 2015-10-08 | Xerox Corporation | Machine learning approach for detecting mobile phone usage by a driver |
| CN104494564A (en) * | 2014-12-22 | 2015-04-08 | 清华大学苏州汽车研究院（吴江） | Vehicle anti-theft system based on human face recognition |
| CN104527570A (en) * | 2014-12-22 | 2015-04-22 | 清华大学苏州汽车研究院（吴江） | Vehicle anti-theft system based on panoramic picture |
| CN204415338U (en) * | 2014-12-22 | 2015-06-24 | 清华大学苏州汽车研究院（吴江） | A kind of Vehicle Anti-Theft System based on recognition of face |
| CN204547917U (en) * | 2015-04-15 | 2015-08-12 | 郭帅 | The overcrowding detection alarm system of a kind of car |
| CN104850771A (en) * | 2015-04-30 | 2015-08-19 | 广东欧珀移动通信有限公司 | Identity verification method and related equipment |
| CN105691367A (en) * | 2016-01-25 | 2016-06-22 | 大连楼兰科技股份有限公司 | Bus initiative braking method and system based on association of images and heartbeat monitoring |
| CN106599774A (en) * | 2016-10-31 | 2017-04-26 | 深圳市元征科技股份有限公司 | Vehicle alarm method and device |
| CN108021856A (en) * | 2016-10-31 | 2018-05-11 | 比亚迪股份有限公司 | Light for vehicle recognition methods, device and vehicle |
| CN106709420A (en) * | 2016-11-21 | 2017-05-24 | 厦门瑞为信息技术有限公司 | Method for monitoring driving behaviors of driver of commercial vehicle |
| CN106934355A (en) * | 2017-02-28 | 2017-07-07 | 西交利物浦大学 | In-car hand detection method based on depth convolutional neural networks |
| CN207173533U (en) * | 2017-09-11 | 2018-04-03 | 马芳武 | A kind of vehicle-mounted intelligent video monitoring and recognition of face anti-theft alarm system |
| CN107766835A (en) * | 2017-11-06 | 2018-03-06 | 贵阳宏益房地产开发有限公司 | traffic safety detection method and device |
| CN108629316A (en) * | 2018-05-08 | 2018-10-09 | 东北师范大学人文学院 | A kind of video accident detection method of various visual angles |
| CN109766841A (en) * | 2019-01-10 | 2019-05-17 | 深圳大学 | Vehicle checking method, device and computer readable storage medium |
| CN109784290A (en) * | 2019-01-23 | 2019-05-21 | 科大讯飞股份有限公司 | A kind of object detection method, device, equipment and readable storage medium storing program for executing |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414833A (en) * | 2020-03-16 | 2020-07-14 | 北京嘀嘀无限科技发展有限公司 | Target detection tracking method, target detection tracking device, and storage medium |
| CN113561908A (en) * | 2021-07-27 | 2021-10-29 | 奇瑞新能源汽车股份有限公司 | Control method and device of vehicle-mounted face recognition equipment |
| CN113561908B (en) * | 2021-07-27 | 2023-06-23 | 奇瑞新能源汽车股份有限公司 | Control method and device of vehicle-mounted face recognition equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110188645B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11449727B2 (en) | Method, storage medium and electronic device for detecting vehicle crashes | |
| CN108319901B (en) | Biopsy method, device, computer equipment and the readable medium of face | |
| CN106815574B (en) | Method and device for establishing detection model and detecting behavior of connecting and calling mobile phone | |
| CN110378965A (en) | Determine the method, apparatus, equipment and storage medium of coordinate system conversion parameter | |
| KR101473957B1 (en) | Apparatus and method for determining insurance premium based on driving pattern recognition | |
| WO2021052010A1 (en) | Method and apparatuses for face orientation estimation and network training, and electronic device and storage medium | |
| CN111652087B (en) | Car inspection method, device, electronic equipment and storage medium | |
| CN108389392A (en) | A kind of traffic accident responsibility identification system based on machine learning | |
| CN109766755A (en) | Face identification method and Related product | |
| EP3706095A1 (en) | Evaluation device, evaluation system, vehicle, and program | |
| CN111126158A (en) | Automatic ticket checking method, device and system based on face recognition | |
| CN110188645A (en) | For the method for detecting human face of vehicle-mounted scene, device, vehicle and storage medium | |
| CN109858470A (en) | Method and apparatus for output information | |
| CN111460938A (en) | Vehicle driving behavior real-time monitoring method and device | |
| CN108449571A (en) | A kind of car monitoring method and equipment | |
| CN110490752A (en) | Car insurance analysis and automatic recommendation service system and its working method based on driving behavior data | |
| CN110363193A (en) | Vehicle recognition methods, device, equipment and computer storage medium again | |
| CN108957460A (en) | Detection method, equipment and the computer readable storage medium of vehicle distances | |
| CN110803170B (en) | Driving assistance system with intelligent user interface | |
| CN111950499A (en) | Method for detecting vehicle-mounted personnel statistical information | |
| CN111241918A (en) | Vehicle anti-tracking method and system based on face recognition | |
| CN114677848B (en) | Perception early warning system, method, device and computer program product | |
| CN114166234A (en) | System, method, device, processor and computer storage medium for selecting navigation route and road damage identification early warning based on road damage measurement | |
| JP7182167B2 (en) | Risk determination device, risk determination method, and program | |
| CN112560685A (en) | Facial expression recognition method and device and storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211011 Address after: 100176 101, floor 1, building 1, yard 7, Ruihe West 2nd Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Applicant after: Apollo Zhilian (Beijing) Technology Co.,Ltd. Address before: 2 / F, baidu building, No. 10, Shangdi 10th Street, Haidian District, Beijing 100085 Applicant before: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |