CN113212126B - Cabin self-adaptive real-time intelligent regulation and control method and system applied to automobile - Google Patents

Cabin self-adaptive real-time intelligent regulation and control method and system applied to automobile Download PDF

Info

Publication number
CN113212126B
CN113212126B CN202110668111.XA CN202110668111A CN113212126B CN 113212126 B CN113212126 B CN 113212126B CN 202110668111 A CN202110668111 A CN 202110668111A CN 113212126 B CN113212126 B CN 113212126B
Authority
CN
China
Prior art keywords
automobile
driver
front windshield
eyes
pixel point
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110668111.XA
Other languages
Chinese (zh)
Other versions
CN113212126A (en
Inventor
胡卫红
牟露
黄昕
周恩泽
宁向利
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Xiaoma Lixing Technology Co ltd
Original Assignee
Shenzhen Xiaoma Lixing Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Xiaoma Lixing Technology Co ltd filed Critical Shenzhen Xiaoma Lixing Technology Co ltd
Priority to CN202110668111.XA priority Critical patent/CN113212126B/en
Publication of CN113212126A publication Critical patent/CN113212126A/en
Application granted granted Critical
Publication of CN113212126B publication Critical patent/CN113212126B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60J—WINDOWS, WINDSCREENS, NON-FIXED ROOFS, DOORS, OR SIMILAR DEVICES FOR VEHICLES; REMOVABLE EXTERNAL PROTECTIVE COVERINGS SPECIALLY ADAPTED FOR VEHICLES
    • B60J3/00—Antiglare equipment associated with windows or windscreens; Sun visors for vehicles
    • B60J3/04—Antiglare equipment associated with windows or windscreens; Sun visors for vehicles adjustable in transparency
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60J—WINDOWS, WINDSCREENS, NON-FIXED ROOFS, DOORS, OR SIMILAR DEVICES FOR VEHICLES; REMOVABLE EXTERNAL PROTECTIVE COVERINGS SPECIALLY ADAPTED FOR VEHICLES
    • B60J1/00—Windows; Windscreens; Accessories therefor
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
    • B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
    • B60R16/037—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for occupant comfort, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
    • B60R16/0373—Voice control
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
    • G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
    • G—PHYSICS
    • 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
    • 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
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships

Abstract

The invention discloses a cabin self-adaptive real-time intelligent regulation and control method and system applied to an automobile, belongs to the technical field of an in-automobile environment regulation method system, and relates to an intelligent traffic Internet of things application service, wherein the cabin self-adaptive real-time intelligent regulation and control method applied to the automobile comprises the following steps: step S1: and splicing the small-size liquid crystal film units to form a large-size liquid crystal film splicing structure, and compounding to form the multi-site automobile front windshield. According to the invention, the tracking speed and the tracking accuracy are high, the positions of the eyes of the automobile driver can be accurately tracked without a large amount of iteration, a real-time effect is achieved, the detection accuracy is high, the real-time requirement can be completely met, multiple detection technologies are provided, the anti-interference capability is strong, the driver does not need to pull the light screen to shade the sun by separating the palm of the driver from the steering wheel, the self-adaptive control can be carried out according to the actual condition of the driver, and the shading effect can be automatically regulated and controlled according to the voice control.

Description

Cabin self-adaptive real-time intelligent regulation and control method and system applied to automobile
Technical Field
The invention belongs to the technical field of an in-vehicle environment regulation method and system, and particularly relates to a cabin self-adaptive real-time intelligent regulation and control method and system applied to an automobile.
Background
Along with the development of automobile technology, the functions of vehicles are increasingly abundant, and great convenience is provided for the driving and the use of vehicle owners, for example, the Chinese patent discloses a method and a system for self-adaptive adjustment of environment in vehicles based on environmental changes (patent No. CN 108791309B), which solves the technical problem that when the temperature in the vehicles is adjusted, the manual adjustment is usually needed, when the drivers drive the vehicles, the manual adjustment of the temperature in the vehicles generates certain safety hazards, for the adjustment of the light intensity in the vehicles, except for the way of opening lamps in the vehicles, the way of opening and closing windows is adopted, the windows on the left side and the right side of the vehicles are pasted with a layer of solar film in order to shield the sunlight and avoid the sunlight directly irradiating the vehicles, especially in summer, when the vehicles are exposed to the sunlight, the vehicles can select to open and close the windows, but if the windows on both sides of the vehicles are closed, the brightness in the vehicle can be influenced, but the window can not be opened in the driving process of the vehicle (for example, when the vehicle drives on a highway, the current adjusting mode of the environment in the vehicle is not humanized, the illumination adjustment is changed according to the different illumination intensity changes at two sides of the vehicle, the specific conditions of different driving directions and different time of the vehicle are considered, good customer experience is provided, meanwhile, the priority of manual adjustment can be higher than the priority of automatic adjustment, so that the intelligent automatic adjustment can be manually adjusted in a humanized manner under the condition that the intelligent automatic adjustment is not suitable for specific personnel in the vehicle, the technical problem is solved, but the patent still has some defects, the considered front windshield cannot be considered to interfere with a driver, the existing front windshield for the vehicle is anti-interference, still use manual formula light screen, it pulls the light screen to need the navigating mate palm to break away from the steering wheel and carry out the sunshade, the effect is comparatively fixed like this, can't carry out adaptive control according to navigating mate's actual conditions, and illumination intensity check out test set has some not enough, the sensitivity to light is not enough, it is especially sensitive to the temperature easily to receive environmental impact, the reliability and the stability of system remain to be improved, and the cost is not low, consequently, need urgently in the present stage to solve above-mentioned problem with a real-time intelligent regulation and control method of passenger cabin self-adaptation and system of being applied to the car.
Disclosure of Invention
The invention aims to: in order to solve the problems that the consideration is one-sided, the interference of the illumination of the front windshield to drivers cannot be considered, the existing front windshield for the automobile is anti-interference, a manual type light screen is still used, the palm of the driver is required to be separated from a steering wheel to pull the light screen to shade the sun, the effect is fixed, self-adaptive control cannot be performed according to the actual situation of the drivers, illumination intensity detection equipment has some defects, the sensitivity to light is not enough, the system is easily influenced by the environment and particularly sensitive to the temperature, the reliability and the stability of the system are to be improved, and the cost is not low, and the method and the system for self-adaptive real-time intelligent regulation and control of the cabin applied to the automobile are provided.
In order to achieve the purpose, the invention adopts the following technical scheme:
a cabin self-adaptive real-time intelligent regulation and control method applied to an automobile comprises the following steps:
step S1: splicing the small-sized liquid crystal film units to form a large-sized liquid crystal film splicing structure, and compounding to form the multi-site front windshield for the automobile;
step S21: detecting the head-on illumination intensity of the front windshield of the automobile, establishing a characteristic curve between the output illumination intensity and the input illumination intensity of BH1750FVI by adopting a least square method, and processing an optical signal by the micro singlechip according to the characteristic curve;
step S22: tracking the eyes of the automobile driver, positioning the eyes based on rules, filtering the skin color to obtain a face area, and tracking the eyes of the automobile driver by using a Kalman filtering method;
step S23: detecting the eye opening angle of a driver, detecting the eye region texture by using an LBP texture detection operator with robustness to illumination, calculating the second moment, entropy and marginal distribution second moment of the eye region texture as a characteristic vector, and classifying the characteristic vector by using an SVM (support vector machine) to achieve the purpose of opening and closing detection;
step S24: recognizing the voice command;
step S3: the method comprises the steps of self-adaptive real-time intelligent regulation and control of the transmittance of the front windshield for the automobile, finding out the closest environment brightness value in a comfort level lookup table of an automobile driver, taking a driving signal under a working scene corresponding to the closest environment brightness value as a lookup result, sending the lookup result to a driving device, and driving PDLC dimming glass by the driving device according to the driving signal.
As a further description of the above technical solution:
the step S1 specifically includes:
step S11: flatly paving a plurality of small-sized liquid crystal film units on a dust-free working platform according to a certain rule;
step S12: electrically connecting two small-size liquid crystal film units which are adjacently arranged to form a large-size liquid crystal film splicing structure;
step S13: and compounding the large-size liquid crystal film splicing structure into the middle of two layers of front windshield glass for the automobile, and gluing the two layers of front windshield glass at high temperature and high pressure to integrally form an automobile front windshield glass product.
As a further description of the above technical solution:
the step S21 specifically includes:
step S211: when external light rays at a position, corresponding to a main driving position, of the front windshield of the automobile irradiate on the photosensitive diode PD, photocurrent is generated;
step S212: converting the photocurrent to a PD voltage by an operational amplifier AMP;
step S213: the PD voltage is converted into digital data which can be identified by the micro single chip microcomputer by the A/D converter.
As a further description of the above technical solution:
the step S213 further includes: the micro single chip microcomputer automatically collects data required by calibration of the illumination intensity characteristic curve, calculates unknown illumination intensity data processing work according to the characteristic curve, establishes the characteristic curve between the output and input illumination intensities of BH1750FVI by adopting a least square method, and processes optical signals according to the characteristic curve.
As a further description of the above technical solution:
the step S22 specifically includes:
step S221: segmenting the facial complexion of the vehicle driverAccording to the non-linear relation of the human face complexion of the automobile driver in the YCbCr space, the YCbCr for the color space is obtained by the non-linear segmented color transformation 2 To represent;
step S222: the probability that any pixel point in the face image of the automobile driver belongs to the skin can be obtained through the established skin color Gaussian distribution, and for a certain pixel point s, the pixel point s is firstly converted from an RGB space to a YCbCr space and then is converted to the YCbCr space 2 Color space, obtaining chroma values (Cb ', Cr');
step S223: calculating the skin color likelihood of each pixel point of the detected color image, obtaining the maximum skin color likelihood of the whole image, dividing the skin color likelihood of each pixel point by the maximum skin color likelihood to obtain a value, representing the probability of the pixel point belonging to the skin as the gray value of the pixel point, thereby obtaining the skin color likelihood image, and then obtaining a segmentation image of the skin color through threshold value setting;
step S224: after the input face image of the automobile driver is subjected to skin color segmentation, a binary image containing a face region is obtained, and the image is subjected to corrosion operation to remove existing isolated noise;
step S225: carrying out segmentation processing on the face image by using an 8-connectivity algorithm, and calculating the size of each connected domain to filter out a region with a relatively small area;
step S226: based on regular human eye positioning, the human face area after skin color filtering contains a certain number of holes, because the nostrils of eyebrow eyes and the mouth position of a human are not skin colors, the holes in the binary image are easy to form, if no holes exist in a certain area or the number of the holes is less than a certain number, the area can be excluded;
step S227: calculating the area of each hole, and excluding holes with too small area;
step S228: and tracking the eyes of the automobile driver by using a Kalman filtering method.
As a further description of the above technical solution:
the step S221 further includes: firstly, each pixel point R, G, B in the skin area is converted into Y, Cb and Cr to be expressed, and each pixel point is obtainedThe chromatic values (Cb, Cr) of the pixel points are converted to YCbCr by non-linear segment transformation 2 In coordinate space, the statistical chrominance is CbCr 2 The chroma distribution diagram is obtained, and the value of the chroma distribution diagram is divided by the maximum value of the chroma distribution diagram to obtain the normalized chroma distribution diagram, namely the skin color distribution can be represented by a Gaussian model N (m, C), wherein m is a mean value, and C is a covariance matrix.
As a further description of the above technical solution:
the step S23 specifically includes:
step S231: firstly, accurately extracting an eye region;
step S232: then, detecting the texture of the eye region by using an LBP texture detection operator with robustness to illumination, and calculating the second order moment, entropy and marginal distribution second order moment of the eye region as a feature vector;
step S233: and finally, classifying the feature vectors by using an SVM (support vector machine) to achieve the purpose of opening and closing detection.
As a further description of the above technical solution:
the step S3 includes:
step S31: the central controller controls the light transmission intensity in the corresponding area of the automobile front windshield according to the received information about tracking the eyes of the automobile driver, the head-on illumination intensity of the front windshield and the detection result of the opening angle of the eyes of the automobile driver;
step S32: the central controller also automatically controls the light transmittance of the control area according to the voice command of receiving light or dark input.
As a further description of the above technical solution:
the step S3 specifically includes: the central controller finds out the closest environment brightness value in the automobile driver comfort level lookup table according to the received automobile driver eye tracking information, the front windshield head-on illumination intensity and the automobile driver eye opening angle detection result, takes the driving signal under the working scene corresponding to the closest environment brightness value as the lookup result, and sends the lookup result to the driving device, and the driving device drives the PDLC dimming glass according to the driving signal.
A cabin self-adaptive real-time intelligent regulation and control system applied to an automobile comprises:
the illumination intensity detection module is used for detecting the head-on illumination intensity of the front windshield of the automobile;
the automobile driver eye tracking module is used for tracking the eyes of the automobile driver;
the eye opening angle detection module is used for detecting the opening angle of the eyes of the automobile driver;
the voice instruction receiving module is used for identifying the voice instruction;
the self-adaptive real-time intelligent control module is used for self-adaptive real-time intelligent control of the transmittance of the front windshield for the automobile.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
the illumination intensity detection system has stable performance, can accurately detect the value of the illumination intensity, is suitable for the front windshield of the automobile with higher requirement on illumination, and the Kalman filtering is a filtering processing method taking minimum mean square error as a criterion, which estimates the state of a current frame by using the information obtained from the previous frame, so the tracking speed and the accuracy are both higher, can accurately track the positions of the eyes of the automobile driver without a large amount of iteration, achieves the real-time effect, has higher detection accuracy, the system can completely meet the real-time requirement, has multiple detection technologies, has strong anti-interference capability, does not need a driver to pull the shading plate to shade the sun by separating the palm from a steering wheel, can carry out self-adaptive control according to the actual condition of the driver, and can automatically regulate and control the shading effect according to voice control.
Drawings
FIG. 1 is a flow chart of the adaptive real-time intelligent control of the illumination intensity applied to the cabin adaptive real-time intelligent regulation and control method and system of the automobile according to the present invention;
fig. 2 is a schematic block structure diagram of a cabin adaptive real-time intelligent regulation and control method and system applied to an automobile according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides a technical solution:
a cabin self-adaptive real-time intelligent regulation and control method applied to an automobile comprises the following steps:
step S1: splicing the small-sized liquid crystal film units to form a large-sized liquid crystal film splicing structure, and compounding to form the multi-site front windshield for the automobile;
step S21: detecting the head-on illumination intensity of the front windshield of the automobile, establishing a characteristic curve between the output illumination intensity and the input illumination intensity of BH1750FVI by adopting a least square method, and processing an optical signal by the micro singlechip according to the characteristic curve;
step S22: tracking the eyes of the automobile driver, positioning the eyes based on rules, filtering the skin color to obtain a face area, and tracking the eyes of the automobile driver by using a Kalman filtering method;
step S23: detecting the opening angle of eyes of a driver, detecting the texture of an eye region by using an LBP texture detection operator with robustness to illumination, calculating second moments, entropy and marginal distribution second moments of the eye region as characteristic vectors, and classifying the characteristic vectors by using an SVM (support vector machine) to achieve the purpose of opening and closing detection;
step S24: recognizing the voice command;
step S3: the method comprises the steps of self-adaptive real-time intelligent regulation and control of the transmittance of the front windshield for the automobile, finding out the closest environment brightness value in a comfort level lookup table of an automobile driver, taking a driving signal under a working scene corresponding to the closest environment brightness value as a lookup result, sending the lookup result to a driving device, and driving PDLC dimming glass by the driving device according to the driving signal.
Specifically, as shown in fig. 1, the step S1 specifically includes:
step S11: flatly paving a plurality of small-sized liquid crystal film units on a dust-free working platform according to a certain rule;
step S12: electrically connecting the two adjacent small-size liquid crystal film units to form a large-size liquid crystal film splicing structure;
step S13: and compounding the large-size liquid crystal film splicing structure into the middle of two layers of front windshield glass for the automobile, and gluing the two layers of front windshield glass at high temperature and high pressure to integrally form an automobile front windshield glass product.
Specifically, as shown in fig. 1, the step S21 specifically includes:
step S211: when external light rays at a position, corresponding to a main driving position, of the front windshield of the automobile irradiate on the photosensitive diode PD, photocurrent is generated;
step S212: converting the photocurrent to a PD voltage by an operational amplifier AMP;
step S213: the PD voltage is converted into digital data which can be identified by the micro single chip microcomputer by the A/D converter.
Specifically, as shown in fig. 1, the step S213 further includes: the micro single chip microcomputer automatically collects data required by calibration of the illumination intensity characteristic curve, calculates unknown illumination intensity data processing work according to the characteristic curve, establishes a characteristic curve between output and input illumination intensities of BH1750FVI by the micro single chip microcomputer through a least square method, and processes optical signals according to the characteristic curve.
Specifically, as shown in fig. 1, the step S22 specifically includes:
step S221: segmenting the face complexion of the driver, and obtaining the YCbCr for the color space through nonlinear segmentation color transformation according to the nonlinear relation of the face complexion of the driver in the YCbCr space 2 To YChCr coordinate space to YCbCr 2 The transformation formula of the coordinate space is as follows:
Figure DEST_PATH_IMAGE001
wherein:
Figure 760654DEST_PATH_IMAGE002
in the formula (I), the compound is shown in the specification,
Figure DEST_PATH_IMAGE003
and
Figure 763245DEST_PATH_IMAGE004
for the segment value range of the non-linear segment color transform,
Figure 286631DEST_PATH_IMAGE005
and
Figure 982054DEST_PATH_IMAGE006
the minimum value and the maximum value of the Y component in the skin color clustering region.
And converting each pixel point R, G, B in the skin area into Y, Cb and Cr to represent, and obtaining the chromatic value (Cb and Cr) of each pixel point.
Each pixel point in the skin area is converted to YCbCr through nonlinear piecewise conversion 2 Coordinate space, statistical chrominance of CbCr 2 Obtaining a chromaticity distribution diagram, and dividing the value of the chromaticity distribution diagram by the maximum value of the chromaticity distribution diagram to obtain a normalized chromaticity distribution diagram, namely the skin color distribution can be represented by a Gaussian model N (m, C), wherein m is a mean value, and C is a covariance matrix:
Figure DEST_PATH_IMAGE007
Figure 223680DEST_PATH_IMAGE008
step S222: by previously established skin color gaussiansThe distribution can obtain the probability that any pixel point in the face image of the automobile driver belongs to the skin, and for a certain pixel point s, the pixel point s is firstly converted into YCbCr space from RGB space and then is converted into YCbCr space 2 The color space, resulting in chrominance values (Cb ', Cr'), then the skin color probability density, i.e. skin color likelihood, for this pixel can be calculated by the following equation:
Figure DEST_PATH_IMAGE009
step S223: calculating the skin color likelihood of each pixel point of the detected color image, obtaining the maximum skin color likelihood of the whole image, dividing the skin color likelihood of each pixel point by the maximum skin color likelihood to obtain a value, representing the probability of the pixel point belonging to the skin as the gray value of the pixel point, thereby obtaining the skin color likelihood image, and then obtaining a segmentation image of the skin color through threshold value setting;
step S224: the input face image of the automobile driver is divided by skin color to obtain a binary image containing a face region, the image is corroded to remove existing isolated noise, X is set as a corrosion operator, M is set as an image before corrosion operation,
Figure 764382DEST_PATH_IMAGE010
in order to etch the image after the operation,
Figure DEST_PATH_IMAGE011
is to corrode a structural element, wherein
Figure 673433DEST_PATH_IMAGE012
The structure is described in the following formula:
Figure DEST_PATH_IMAGE013
；
step S225: segmenting the face image by using an 8-connectivity algorithm, and calculating the size of each connectivity domain to filter out regions with relatively small areas;
step S226: based on regular human eye positioning, the human face area after skin color filtering contains a certain number of holes, because the nostrils of eyebrow eyes and the mouth position of a human are not skin colors, the holes in the binary image are easy to form, if no holes exist in a certain area or the number of the holes is less than a certain number, the area can be excluded;
step S227: calculating the area of each hole, and excluding holes with too small areas;
step S228: and tracking the eyes of the automobile driver by using a Kalman filtering method.
Specifically, as shown in fig. 1, the step S221 further includes: firstly, each pixel point R, G, B in the skin area is converted into Y, Cb and Cr to be expressed, so as to obtain the chromatic value (Cb, Cr) of each pixel point, and then each pixel point in the skin area is converted into YCbCr through nonlinear piecewise conversion 2 Coordinate space, statistical chrominance of CbCr 2 The chroma distribution diagram is obtained, and the value of the chroma distribution diagram is divided by the maximum value of the chroma distribution diagram to obtain the normalized chroma distribution diagram, namely the skin color distribution can be represented by a Gaussian model N (m, C), wherein m is a mean value, and C is a covariance matrix.
Specifically, as shown in fig. 1, the step S23 specifically includes:
step S231: firstly, accurately extracting an eye region;
step S232: then, detecting the texture of the eye region by using an LBP texture detection operator with robustness to illumination, and calculating the second order moment, entropy and marginal distribution second order moment of the eye region as a feature vector;
step S233: and finally, classifying the feature vectors by using the SVM to achieve the purpose of opening and closing detection.
Specifically, as shown in fig. 1, the step S3 includes:
step S31: the central controller controls the light transmission intensity in the corresponding area of the automobile front windshield according to the received information about tracking the eyes of the automobile driver, the head-on illumination intensity of the front windshield and the detection result of the opening angle of the eyes of the automobile driver;
step S32: the central controller also automatically controls the light transmittance of the control area according to the voice command of receiving light or dark input.
Specifically, as shown in fig. 1, the step S3 specifically includes: the central controller finds out the closest environment brightness value in the automobile driver comfort level lookup table according to the received automobile driver eye tracking information, the front windshield head-on illumination intensity and the automobile driver eye opening angle detection result, takes the driving signal under the working scene corresponding to the closest environment brightness value as the lookup result, and sends the lookup result to the driving device, and the driving device drives the PDLC dimming glass according to the driving signal.
A cabin self-adaptive real-time intelligent regulation and control system applied to an automobile comprises:
the illumination intensity detection module is used for detecting the head-on illumination intensity of the front windshield of the automobile;
the automobile driver eye tracking module is used for tracking the eyes of the automobile driver;
the eye opening angle detection module is used for detecting the opening angle of the eyes of the automobile driver;
the voice instruction receiving module is used for identifying the voice instruction;
the self-adaptive real-time intelligent control module is used for self-adaptive real-time intelligent control of the transmittance of the front windshield for the automobile.
The working principle is as follows: when in use, the utility model is used,
step S1: splicing the small-sized liquid crystal film units to form a large-sized liquid crystal film splicing structure, and compounding to form the multi-site front windshield for the automobile;
step S11: flatly paving a plurality of small-sized liquid crystal film units on a dust-free working platform according to a certain rule;
step S12: electrically connecting the two adjacent small-size liquid crystal film units to form a large-size liquid crystal film splicing structure;
step S13: compounding a large-size liquid crystal film splicing structure into the middle of two layers of front windshields for automobiles, and integrally forming an automobile front windshield product after high-temperature and high-pressure gluing;
step S21: detecting the head-on illumination intensity of the front windshield of the automobile;
step S211: when external light rays at a position, corresponding to a main driving position, of the front windshield of the automobile irradiate on the photosensitive diode PD, photocurrent is generated;
step S212: converting the photocurrent to a PD voltage by an operational amplifier AMP;
step S213: the A/D converter converts the PD voltage into digital data which can be identified by the micro single chip microcomputer, the micro single chip microcomputer automatically collects data required by calibration of an illumination intensity characteristic curve and calculates unknown illumination intensity data processing work according to the characteristic curve, the micro single chip microcomputer establishes the characteristic curve between the output and input illumination intensities of BH1750FVI by adopting a least square method, and the micro single chip microcomputer processes optical signals according to the characteristic curve;
step S22: tracking the eyes of the automobile driver;
step S221: segmenting the face complexion of the driver, and obtaining the YCbCr for the color space through nonlinear segmentation color transformation according to the nonlinear relation of the face complexion of the driver in the YCbCr space 2 The method comprises the steps of firstly converting each pixel point R, G, B in a skin area into Y, Cb and Cr representations to obtain the chromatic value (Cb and Cr) of each pixel point, and then converting each pixel point in the skin area into YCbCr through nonlinear piecewise conversion 2 Coordinate space, statistical chrominance of CbCr 2 Obtaining a chroma distribution diagram, and dividing the value of the chroma distribution diagram by the maximum value of the chroma distribution diagram to obtain a normalized chroma distribution diagram, namely the skin color distribution can be represented by a Gaussian model N (m, C), wherein m is a mean value, and C is a covariance matrix;
step S222: the probability that any pixel point in the human face image of the automobile driver belongs to the skin can be obtained through the skin color Gaussian distribution established in the front, and for a certain pixel point s, the pixel point s is firstly converted into a YCbCr space from an RGB space and then is converted into the YCbCr space 2 Color space, obtaining colorimetric values (Cb ', Cr');
step S223: calculating the skin color likelihood of each pixel point of the detected color image, obtaining the maximum skin color likelihood of the whole image, dividing the skin color likelihood of each pixel point by the maximum skin color likelihood to obtain a value, representing the probability of the pixel point belonging to the skin as the gray value of the pixel point, thereby obtaining the skin color likelihood image, and then obtaining a segmentation image of the skin color through threshold value setting;
step S231: firstly, accurately extracting an eye area;
step S232: then, detecting the eye region texture by using an LBP texture detection operator with robustness to illumination, and calculating the second moment, the entropy and the marginal distribution second moment as feature vectors;
step S233: finally, the SVM is used for classifying the feature vectors so as to achieve the purpose of opening and closing detection;
step S224: after the input face image of the automobile driver is subjected to skin color segmentation, a binary image containing a face region is obtained, and the image is subjected to corrosion operation to remove existing isolated noise;
step S225: carrying out segmentation processing on the face image by using an 8-connectivity algorithm, and calculating the size of each connected domain to filter out a region with a relatively small area;
step S226: based on regular human eye positioning, the human face area after skin color filtering contains a certain number of holes, because the nostrils of eyebrow eyes and the mouth position of a human are not skin colors, the holes in the binary image are easy to form, if no holes exist in a certain area or the number of the holes is less than a certain number, the area can be excluded;
step S227: calculating the area of each hole, and excluding holes with too small area;
step S228: tracking the eyes of the automobile driver by using a Kalman filtering method;
step S23: detecting the opening angle of eyes of a driver of the automobile;
step S24: recognizing the voice command;
step S3: the transmittance of the front windshield for the automobile is self-adaptive, real-time and intelligent controlled;
step S31: the central controller controls the light transmission intensity in the corresponding area of the automobile front windshield according to the received information about tracking of human eyes of an automobile driver, the head-on illumination intensity of the front windshield and the detection result of the opening angle of the eyes of the automobile driver;
step S32: the central controller can automatically control the light transmittance of the control area according to a received bright or dark input voice instruction, finds out the closest environment brightness value in a comfort look-up table of the automobile driver according to the received tracking information of the human eyes of the automobile driver, the head-on illumination intensity of the front windshield and the detection result of the opening angle of the eyes of the automobile driver, takes a driving signal under a working scene corresponding to the closest environment brightness value as the look-up result, and sends the look-up result to the driving device, and the driving device drives the PDLC dimming glass according to the driving signal.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.

Claims (8)

1. The self-adaptive real-time intelligent regulation and control method for the cabin of the automobile is characterized by comprising the following steps of:
step S1: splicing the small-sized liquid crystal film units to form a large-sized liquid crystal film splicing structure, and compounding to form the multi-site front windshield for the automobile;
step S21: detecting the head-on illumination intensity of the front windshield of the automobile, establishing a characteristic curve between the output illumination intensity and the input illumination intensity of BH1750FVI by adopting a least square method, and processing an optical signal by the micro singlechip according to the characteristic curve;
step S22: tracking the eyes of the automobile driver, positioning the eyes based on rules, filtering the skin color to obtain a face area, and tracking the eyes of the automobile driver by using a Kalman filtering method;
step S23: detecting the eye opening angle of a driver, detecting the eye region texture by using an LBP texture detection operator with robustness to illumination, calculating the second moment, entropy and marginal distribution second moment of the eye region texture as a characteristic vector, and classifying the characteristic vector by using an SVM (support vector machine) to achieve the purpose of opening and closing detection;
step S24: recognizing the voice command;
step S3: the method comprises the steps that the transmittance of the front windshield for the automobile is adaptively and intelligently regulated in real time, the closest environment brightness value in a comfort look-up table of an automobile driver is found out, a driving signal under a working scene corresponding to the closest environment brightness value is used as a look-up result, the look-up result is sent to a driving device, and the driving device drives PDLC dimming glass according to the driving signal;
the step S3 specifically includes: the central controller finds out the closest environment brightness value in a comfort level lookup table of an automobile driver according to received human eye tracking information of the automobile driver, the head-on illumination intensity of the front windshield and the eye opening angle detection result of the automobile driver, takes a driving signal under a working scene corresponding to the closest environment brightness value as a lookup result, and sends the lookup result to the driving device, and the driving device drives the PDLC dimming glass according to the driving signal;
the step S1 specifically includes:
step S11: flatly paving a plurality of small-sized liquid crystal film units on a dust-free working platform according to a certain rule;
step S12: electrically connecting two small-size liquid crystal film units which are adjacently arranged to form a large-size liquid crystal film splicing structure;
step S13: and compounding the large-size liquid crystal film splicing structure into the middle of two layers of front windshield glass for the automobile, and gluing the two layers of front windshield glass at high temperature and high pressure to integrally form an automobile front windshield glass product.
2. The cabin adaptive real-time intelligent regulation and control method applied to the automobile according to claim 1, wherein the step S21 specifically comprises:
step S211: when external light rays at a position, corresponding to a main driving position, of the front windshield of the automobile irradiate on the photosensitive diode PD, photocurrent is generated;
step S212: converting the photocurrent to a PD voltage by an operational amplifier AMP;
step S213: the PD voltage is converted into digital data which can be identified by the micro single chip microcomputer by the A/D converter.
3. The cabin adaptive real-time intelligent regulation and control method applied to automobiles of claim 2, wherein said step S213 further comprises: the micro single chip microcomputer automatically collects data required by calibration of the illumination intensity characteristic curve, calculates unknown illumination intensity data processing work according to the characteristic curve, establishes a characteristic curve between output and input illumination intensities of BH1750FVI by the micro single chip microcomputer through a least square method, and processes optical signals according to the characteristic curve.
4. The cabin adaptive real-time intelligent regulation and control method applied to the automobile according to claim 3, wherein the step S22 is specifically as follows:
step S221: segmenting the facial complexion of the vehicle driver, and representing a color space obtained through nonlinear segmented color transformation by YCbCr2 according to the nonlinear relation of the facial complexion of the vehicle driver in the YCbCr space;
step S222: the probability that any pixel point in the face image of the automobile driver belongs to the skin can be obtained through the established skin color Gaussian distribution, for a certain pixel point s, the pixel point s is firstly converted from an RGB space to a YCbCr space, and then is converted to the YCbCr2 color space, so that chromatic values (Cb ', Cr') are obtained;
step S223: calculating the skin color likelihood of each pixel point of the detected color image, obtaining the maximum skin color likelihood of the whole image, dividing the skin color likelihood of each pixel point by the maximum skin color likelihood to obtain a value, representing the probability of the pixel point belonging to the skin as the gray value of the pixel point, thereby obtaining a skin color likelihood image, and then obtaining a skin color segmentation image through threshold value setting;
step S224: after the input face image of the automobile driver is subjected to skin color segmentation, a binary image containing a face area is obtained, and the image is subjected to corrosion operation to remove existing isolated noise;
step S225: carrying out segmentation processing on the face image by using an 8-connectivity algorithm, and calculating the size of each connected domain to filter out a region with a relatively small area;
step S226: based on regular human eye positioning, the human face area after skin color filtering contains a certain number of holes, because the nostrils of eyebrow eyes and the mouth position of a human are not skin colors, the holes in the binary image are easy to form, if no holes exist in a certain area or the number of the holes is less than a certain number, the area can be excluded;
step S227: calculating the area of each hole, and excluding holes with too small areas;
step S228: and tracking the eyes of the automobile driver by using a Kalman filtering method.
5. The cabin adaptive real-time intelligent regulation and control method applied to automobiles according to claim 4, wherein said step S221 further comprises: converting R, G, B of each pixel point in a skin area into Y, Cb and Cr for representation to obtain a chromatic value (Cb and Cr) of each pixel point, converting each pixel point in the skin area into YCbCr2 through nonlinear piecewise conversion, calculating the number of the pixel points with the chromaticity of CbCr2 to obtain a chromaticity distribution diagram, and dividing the numerical value of the chromaticity distribution diagram by the maximum value to obtain a normalized chromaticity distribution diagram, namely the skin color distribution can be represented by a Gaussian model N (m, C), wherein m is a mean value, and C is a covariance matrix.
6. The cabin adaptive real-time intelligent regulation and control method applied to the automobile according to claim 5, wherein the step S23 is specifically as follows:
step S231: firstly, accurately extracting an eye region;
step S232: then, detecting the texture of the eye region by using an LBP texture detection operator with robustness to illumination, and calculating the second order moment, entropy and marginal distribution second order moment of the eye region as a feature vector;
step S233: and finally, classifying the feature vectors by using an SVM (support vector machine) to achieve the purpose of opening and closing detection.
7. The cabin adaptive real-time intelligent regulation and control method applied to automobiles according to claim 6, wherein the step S3 comprises:
step S31: the central controller controls the light transmission intensity in the corresponding area of the automobile front windshield according to the received information about tracking the eyes of the automobile driver, the head-on illumination intensity of the front windshield and the detection result of the opening angle of the eyes of the automobile driver;
step S32: the central controller can also automatically control the light transmittance of the corresponding area of the front windshield of the automobile according to the received bright or dark input voice instruction.
8. A cabin adaptive real-time intelligent regulation and control system applied to an automobile, which is used for implementing the cabin adaptive real-time intelligent regulation and control method applied to the automobile of claim 1, and is characterized by comprising the following steps:
the illumination intensity detection module is used for detecting the head-on illumination intensity of the front windshield of the automobile;
the automobile driver eye tracking module is used for tracking the eyes of the automobile driver;
the eye opening angle detection module is used for detecting the opening angle of the eyes of the automobile driver;
the voice instruction receiving module is used for identifying the voice instruction;
the self-adaptive real-time intelligent control module is used for self-adaptive real-time intelligent control of the transmittance of the front windshield for the automobile.
CN202110668111.XA 2021-06-16 2021-06-16 Cabin self-adaptive real-time intelligent regulation and control method and system applied to automobile Active CN113212126B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110668111.XA CN113212126B (en) 2021-06-16 2021-06-16 Cabin self-adaptive real-time intelligent regulation and control method and system applied to automobile

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110668111.XA CN113212126B (en) 2021-06-16 2021-06-16 Cabin self-adaptive real-time intelligent regulation and control method and system applied to automobile

Publications (2)

Publication Number Publication Date
CN113212126A CN113212126A (en) 2021-08-06
CN113212126B true CN113212126B (en) 2022-09-30

Family

ID=77080759

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110668111.XA Active CN113212126B (en) 2021-06-16 2021-06-16 Cabin self-adaptive real-time intelligent regulation and control method and system applied to automobile

Country Status (1)

Country Link
CN (1) CN113212126B (en)

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104013414B (en) * 2014-04-30 2015-12-30 深圳佑驾创新科技有限公司 A kind of Study in Driver Fatigue State Surveillance System based on intelligent movable mobile phone
CN109808464B (en) * 2019-01-24 2020-09-25 北京梧桐车联科技有限责任公司 Method and device for adjusting light transmittance of front windshield
CN109878304B (en) * 2019-03-29 2021-04-09 合肥京东方光电科技有限公司 Sun visor, sun visor control method and automobile

Also Published As

Publication number Publication date
CN113212126A (en) 2021-08-06

Similar Documents

Publication Publication Date Title
US9180756B2 (en) Apparatus and method for detecting driver's dazzling and system and method for blocking dazzling using the same
CN101783076B (en) Method for quick vehicle type recognition under video monitoring mode
WO2021129059A1 (en) Sun visor control method, sun visor control system and apparatus
CN106548463A (en) Based on dark and the sea fog image automatic defogging method and system of Retinex
US20160334546A1 (en) Weather recognition method and device based on image information detection
CN110837800A (en) Port severe weather-oriented target detection and identification method
CN109460715A (en) A kind of traffic lights automatic identification implementation method based on machine learning
JP2020064583A (en) Vehicle detection method, nighttime vehicle detection method based on dynamic light intensity, and system for the same
CN109466286A (en) A kind of intelligent anti-glare method and device in automobile disengaging low-light (level) region
CN112287861A (en) Road information enhancement and driving early warning method based on night environment perception
CN113212126B (en) Cabin self-adaptive real-time intelligent regulation and control method and system applied to automobile
CN103465825A (en) Vehicle-mounted system and control method thereof
CN107220613B (en) Multifunctional control method based on image procossing
CN112758046A (en) Windshield definition control method and system based on intelligent identification
CN109519077B (en) Vehicle window control system for detecting rainwater based on image processing
CN106248635B (en) A kind of visibility detecting method based on digital camera
CN110435534A (en) A kind of driving assisted reaction method and system based on the identification of front speed
CN107886033A (en) Identify the method, apparatus and vehicle of circular traffic lights
CN206278024U (en) A kind of automobile rear view mirror device of automatic regulating lightness
CN105931193A (en) Night traffic block port image enhancement method based on dark channel prior
CN110979156B (en) Automobile headlamp brightness self-adaptive adjusting device and method based on ambient light detection
Ishak et al. A speed limit sign recognition system using artificial neural network
US11851003B2 (en) Driving assistance system and method for driver
CN109986938B (en) Light adjusting system and method, and vehicle comprising light adjusting system
CN107023243B (en) Vehicle window multifunction control system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant