CN107845110B - Method for determining proportion of visible area of window glass - Google Patents
Method for determining proportion of visible area of window glass Download PDFInfo
- Publication number
- CN107845110B CN107845110B CN201710944414.3A CN201710944414A CN107845110B CN 107845110 B CN107845110 B CN 107845110B CN 201710944414 A CN201710944414 A CN 201710944414A CN 107845110 B CN107845110 B CN 107845110B
- Authority
- CN
- China
- Prior art keywords
- area
- image
- glass
- gray
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30268—Vehicle interior
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a method for determining the proportion of the visible area of vehicle window glass, which comprises the following steps: acquiring an image containing a vehicle window glass; acquiring coordinates of each pixel point of the image corresponding to the vehicle window glass to obtain an initial pixel gray scale map of the vehicle window glass, wherein the initial gray scale value of each pixel point of the initial pixel gray scale map is a gray scale value which is not visible for representing the glass; the method can acquire the gray values of all pixel points of the image at different moments through image acquisition and image processing, and can identify the visual boundary according to the initial gray values of all the pixel points and the gray values at different moments because the gray values are related to the visibility of the glass, so that the method can determine the visual area ratio according to the area surrounded by the visual boundary and the area of the image, the visual area ratio is acquired through machine equipment according to a certain algorithm, and the efficiency, the accuracy and the repeatability of manual operation are greatly improved.
Description
Technical Field
The invention relates to the technical field of automobiles, in particular to a method for determining the proportion of the visible area of window glass.
Background
The defogging and defrosting performance of the vehicle directly affects whether the driver can drive the vehicle normally and safely in bad weather, which affects the safety and comfort of passengers.
When the outside temperature is lower than the temperature in the vehicle and the air in the vehicle is not smooth to circulate, the humidity of the air exhaled by the passengers is high, and the cold windshield can be condensed into small water drops to be attached to the inner surface of the windshield, so that the transparency of the glass is seriously reduced and the glass is not easy to clear, and the sight of a driver is also damaged. The frost on the window is opposite to the fog, and exists on the outer surface of the glass, and the frost also influences the sight of a driver.
The defogging and defrosting systems mostly adopt hot air blowing to melt frost on the outer surface of the glass or cold air blowing to blow small water drops on the inner surface, so as to achieve the effect of restoring the visual field. In small environments within the cabin, the flow of airflow is affected by a number of factors, such as: the shape and arrangement of the air supply outlet, the size of the air volume, the number and the position of passengers, different vehicle types and the like need to carry out comprehensive test and evaluation on the performance of the vehicle-mounted defogging and defrosting system.
The area calculation of fog, the frost in judging vehicle air conditioner defogging defrosting performance at present takes the marker pen by the tester, draws the region of fog, frost dissipation on car left side window glass, front windshield and right side window glass at interval equal time, then calculates the area of fog, frost dissipation at different moments, compares with preset criterion, judges vehicle air conditioner defogging defrosting performance. Because the boundary diagrams of the defogging area and the fog dissipation process on the glass are drawn manually, the method has low test efficiency, inaccurate test data and low precision.
Disclosure of Invention
The invention provides a method for determining the proportion of the visible area of window glass, and aims to solve the problems of low efficiency, inaccurate test data and low precision of an automobile glass visibility test in the prior art.
The invention provides a method for determining the proportion of the visible area of window glass, which comprises the following steps:
acquiring an image containing a vehicle window glass;
acquiring coordinates of each pixel point of the image corresponding to the vehicle window glass to obtain an initial pixel gray scale map of the vehicle window glass, wherein the initial gray scale value of each pixel point of the initial pixel gray scale map is a gray scale value which is not visible for representing the glass;
acquiring gray values of all pixel points of the image at different moments, wherein the gray values are related to the visibility of the glass;
identifying a visual boundary according to the initial gray value of each pixel point and the gray values at different moments;
and determining the visible area proportion according to the area enclosed by the visible boundary and the area of the image.
Preferably, the method further comprises:
dividing the glass into a first region, a second region and a third region before acquiring an image containing the window glass;
acquiring images of the first area, the second area and the third area, and respectively acquiring initial pixel gray-scale images of the first area, the second area and the third area;
after obtaining the visible area ratios of the first area, the second area and the third area, determining the defrosting or defogging percentages of the first area, the second area and the third area according to the visible area ratios;
and determining the defrosting or defogging performance according to the time length when the percentage of defrosting or defogging reaches the preset defrosting threshold or the preset defogging threshold.
Preferably, the dividing of the glass into a first region, a second region and a third region comprises:
determining the area enclosed by the intersection lines of 4 planes which represent the two points of the eyes of the driver and extend forwards and the glass surface according to the vertical plumb plane of the central line of the seating position of the driver, the seating reference point and the angle of the seat backrest;
taking the area as a first area;
taking the vertical center line of the glass as an axis, and taking the area of the glass symmetrical to the first area as a second area;
a minimum area at the first area and inward from the glass edge by at least a first length is a reference area;
and taking the vertical center line of the glass as an axis, taking the sum of the area of the glass symmetrical to the reference area and the reference area as a third area.
Preferably, the obtaining of the coordinates of each pixel point of the image corresponding to the window glass to obtain the initial pixel grayscale map of the window glass includes:
setting a square mark with a specified size on the vehicle window glass;
the method comprises the following steps that a camera positioned at an appointed position collects an image containing vehicle window glass, and the number of transverse pixel points and the number of longitudinal pixel points of a square mark in the image are obtained;
acquiring the area of a pixel point and the proportional coefficient of the area of the pixel point corresponding to the glass according to the number of transverse pixel points, the number of longitudinal pixel points and the actual side length of the square mark in the image;
obtaining coordinates of each pixel point of the first area image, the second area image and the third area image according to the proportion coefficient and the image of the window glass;
and setting the gray value of each pixel point of the first area image, the second area image and the third area image at the beginning of the defrosting or defogging experiment as an initial value.
Preferably, the obtaining the gray value of each pixel point of the image at different times includes:
a gray value array is set for each pixel point,
and acquiring the gray value of each pixel point of the image at each sampling time, and storing the gray value in the gray value number sequence corresponding to each pixel point, or acquiring the gray value of each pixel point of the image according to a specified sampling period, and storing the gray value in the gray value number sequence corresponding to each pixel point.
Preferably, the identifying the visual boundary according to the initial gray value of each pixel point and the gray values at different times includes:
comparing the current gray value of each pixel point with a gray value difference value, wherein the gray value difference value is the difference value between the initial gray value and the current gray value of the pixel point;
if the current gray value is greater than the gray value difference value, the glass corresponding to the pixel point is a visual area;
if the current gray value is smaller than the gray value difference value, the glass corresponding to the pixel point is an invisible area;
visual boundaries are identified based on the visual area.
Preferably, the method further comprises:
respectively acquiring visible boundaries of the window glass at a plurality of specified moments;
configuring visual boundaries at different specified moments into different colors;
the visual boundaries of different colors are superimposed in a graph to show the changing dynamics of the visual boundaries.
Preferably, the image is acquired by an image acquisition device comprising:
the camera comprises a camera supporting base, a first hollow circular tube, a seat tube clamp, a second hollow circular tube, a holder, a heat-insulating cover and a camera;
the camera supports the base with first hollow pipe compresses tightly the mode through the screw thread and fixes, first hollow pipe with pass through between the hollow pipe of second the seat pipe clamp is connected, in order to adjust keep warm cover with distance between camera and the ground, the hollow pipe of second with the cloud platform passes through threaded connection, it fixes to keep warm to cover on the cloud platform, it establishes to keep warm to cover the cover on the camera, the cloud platform is used for adjusting the gesture of camera.
Preferably, the heat preservation cover has a heating and heat preservation function and is of a sealing cover structure so as to prevent the camera from being affected by environmental moisture.
Preferably, the image acquisition apparatus further comprises: a plurality of light sources.
The invention discloses a method for determining the proportion of the visible area of window glass, which comprises the following steps: acquiring an image containing a vehicle window glass; acquiring coordinates of each pixel point of the image corresponding to the vehicle window glass to obtain an initial pixel gray scale map of the vehicle window glass, wherein the initial gray scale value of each pixel point of the initial pixel gray scale map is a gray scale value which is not visible for representing the glass; the method can acquire the gray values of all pixel points of the image at different moments through image acquisition and image processing, and can identify the visual boundary according to the initial gray values of all the pixel points and the gray values at different moments because the gray values are related to the visibility of the glass, so that the method can determine the visual area ratio according to the area surrounded by the visual boundary and the area of the image, the visual area ratio is acquired through machine equipment according to a certain algorithm, and the efficiency, the accuracy and the repeatability of manual operation are greatly improved.
Further, before the image containing the vehicle window glass is collected, the glass is divided into a first area, a second area and a third area, wherein the first area and the second area are important areas of the sight line of the driver, the importance of the visibility of the areas is higher relative to other areas, the finally obtained visibility test result can be more consistent with the actual requirement of the driver through the division, and the reference value of the test result is higher.
Further, the invention provides a specific acquisition method for obtaining the first area, the second area and the third area from the image containing the vehicle window glass, wherein the acquisition method comprises the following steps: because the first area, the second area and the third area are not the boundary area of the window glass, the method provided by the invention can accurately and efficiently extract the area which is most important for the vision of a driver from the window glass.
Furthermore, because frost, fog and the like have certain transparency, when the glass is invisible due to the frost, the fog and the like, the transparency of the glass has a large change range, and whether the glass is invisible can not be simply judged by whether the gray value exceeds a set threshold value, and the invention adopts a dynamic algorithm: the method has the advantages that whether the glass is visible or not is judged according to the size relation between the current gray value and the gray value difference, the algorithm is simple, and the method can be suitable for the condition that the glass is invisible due to frost, fog and the like.
Further, the visual boundaries of the window glass at a plurality of specified moments are respectively obtained; configuring visual boundaries at different specified moments into different colors; the visual boundaries of different colors are superimposed in a graph to show the changing dynamics of the visual boundaries. Therefore, the dynamic process of defogging and defrosting can be demonstrated in a simple and visual mode.
Drawings
In order to more clearly illustrate the embodiments of the present application or technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a first flowchart of a method for determining a visible area ratio of window glass according to an embodiment of the present invention;
fig. 2 is a second flowchart of a method for determining a visible area ratio of a window glass according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method for zoning glass according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for obtaining an initial pixel gray scale map of a vehicle glazing according to an embodiment of the invention;
fig. 5 is a schematic structural diagram of an image capturing device according to an embodiment of the present invention;
FIG. 6 is an enlarged view of FIG. 5 at A;
FIG. 7 is an enlarged view of FIG. 6 at B;
fig. 8 is an enlarged view of fig. 5 at C.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
According to the method for determining the proportion of the visible area of the window glass, the visibility of the window glass at different moments is automatically identified by acquiring the gray level image of the window glass, and the efficiency, the accuracy and the repeatability of the method are greatly improved compared with those of manual testing.
In order to better understand the technical solutions and effects of the present invention, the following detailed descriptions will be made with reference to the flowcharts and specific embodiments.
The embodiment of the invention provides a method for determining a visible area ratio of window glass, as shown in fig. 1, which is a first flowchart of the method for determining the visible area ratio of the window glass provided by the embodiment of the invention, and the method comprises the following steps:
and S01, acquiring an image containing the car window glass.
In this embodiment, the image including the window glass may be acquired by a camera, for example, the camera is mounted at a designated position inside or outside the vehicle, preferably inside the vehicle, and imitates the position of the eyes of the driver, so that the acquired image is closer to the real requirement.
And S02, acquiring coordinates of each pixel point of the image corresponding to the vehicle window glass to obtain an initial pixel gray scale image of the vehicle window glass, wherein the initial gray scale value of each pixel point of the initial pixel gray scale image is a gray scale value which is not visible for representing the glass.
In this embodiment, because not only include window glass in the image of gathering, still include other parts in addition, these parts can disturb the image processing result, consequently, need to pull out window glass's image from the image of gathering, and is concrete, can through obtain with window glass corresponds the coordinate of each pixel of image is pulled out, then obtains the grey scale map of the picture of pulling out. For defrosting, defogging, etc. tests, the initial value of the gray scale map should be the gray scale value corresponding to the invisible gray scale value, while in other tests, such as the corrosion test of acid and alkali on glass, etc., the initial gray scale value corresponding to the glass should be the gray scale value corresponding to the visible gray scale value.
And S03, acquiring the gray value of each pixel point of the image at different times, wherein the gray value is related to the visibility of the glass.
In this embodiment, the gray value of each pixel point in the image may be obtained by the prior art. Preferably, a gray value number sequence is set for each pixel, the gray value of each pixel of the image at each sampling time is acquired and stored in the gray value number sequence corresponding to each pixel, or the gray value of each pixel of the image is acquired according to a specified sampling period and stored in the gray value number sequence corresponding to each pixel.
And S04, identifying the visual boundary according to the initial gray value of each pixel point and the gray values at different moments.
In this embodiment, the grayscale image may be subjected to binarization processing to obtain a binary image, and then the visible boundary may be obtained from the binary image.
Specifically, the current gray value of each pixel point is compared with a gray value difference value, wherein the gray value difference value is the difference value between the initial gray value and the current gray value of the pixel point; if the current gray value is greater than the gray value difference value, the glass corresponding to the pixel point is a visual area; and if the current gray value is smaller than the gray value difference value, the glass corresponding to the pixel point is an invisible area. Therefore, the gray level image is actually subjected to binarization processing, and the binarization processing process is not a single threshold value but dynamic processing, so that the result after binarization processing is more in line with the distinction of visible/invisible areas under the scenes of frost, fog and the like. The visible boundary is then identified based on the visible region.
And S05, determining the visible area proportion according to the area enclosed by the visible boundary and the area of the image.
In this embodiment, the number of the pixels in the visible boundary and the number of the pixels in the non-visible boundary are obtained, and then the total number of the pixels in the visible boundary is divided by the total number of the pixels in the glass image.
The invention provides a method for determining the proportion of the visible area of window glass, which comprises the following steps: acquiring an image containing a vehicle window glass; acquiring coordinates of each pixel point of the image corresponding to the vehicle window glass to obtain an initial pixel gray scale map of the vehicle window glass, wherein the initial gray scale value of each pixel point of the initial pixel gray scale map is a gray scale value which is not visible for representing the glass; the method can acquire the gray values of all pixel points of the image at different moments through image acquisition and image processing, and can identify the visual boundary according to the initial gray values of all the pixel points and the gray values at different moments because the gray values are related to the visibility of the glass, so that the method can determine the visual area ratio according to the area surrounded by the visual boundary and the area of the image, the visual area ratio is acquired through machine equipment according to a certain algorithm, and the efficiency, the accuracy and the repeatability of manual operation are greatly improved.
As shown in fig. 2, a second flowchart of a method for determining a visible area ratio of a window glass according to an embodiment of the present invention is provided.
In this embodiment, the method further includes:
s21, before acquiring the image containing the window glass, dividing the glass to include a first region, a second region, and a third region.
In the present embodiment, it is considered that different areas of the window glass have different degrees of visual images for the driver, and therefore, when evaluating the effects of defogging, defrosting, and the like, different areas of the glass should be evaluated differently so that the evaluation result more closely conforms to the actual feeling. The first region is a visual region most important to the driver, for example, a region in front of the driver.
Specifically, as shown in fig. 3, there is a flowchart of a method for dividing a glass into regions according to an embodiment of the present invention. The method comprises the following steps:
and S31, determining the area enclosed by the intersection lines of the glass surface and 4 planes extending forwards and representing two points of the eyes of the driver according to the vertical plane of the central line of the seating position of the driver, the seating reference point and the angle of the seat back.
In one embodiment, the software is programmed to determine a first region of the front windshield by a plumb-longitudinal plane of the centerline of the driver's seating position (if an adjustable seat, the seat should be adjusted to a final position), a seating reference point, and a point representing the driver's eye position determined by the design seat back angle, the area enclosed by the intersection of the two forward extending 4 planes with the outer surface of the windshield. The 4 planes respectively refer to a vertical plane which passes through two points and forms an angle of 13 degrees with the X axis on the left side of the X axis, a plane which forms an elevation angle of 3 degrees with the X axis through a first point and is parallel to the Y axis, a plane which forms a depression angle of 1 degree with the X axis through a second point and is parallel to the Y axis, and a vertical plane which forms an angle of 13 degrees with the X axis on the right side of the X axis through the first point and the second point. Actual three-dimensional coordinates of the first region are obtained.
S32, the area is defined as a first region.
And S33, taking the vertical center line of the glass as an axis, and taking the area of the glass symmetrical to the first area as a second area.
And S34, taking the minimum area of at least a first length inward from the glass edge in the first area as a reference area.
In one embodiment, the reference area is determined based on a smaller area by defining the area of the outer surface of the windshield by 4 planes at least 25 mm inward from the edge of the area of the transparent portion of the windshield, wherein the 4 planes respectively refer to a plane parallel to the Y axis at an elevation angle of 7 ° with respect to the X axis through a first point, a plane parallel to the Y axis at a depression angle of 5 ° with respect to the X axis through a second point, a vertical plane at an angle of 17 ° with respect to the X axis on the left side of the X through the first and second points, and a plane symmetrical to a vertical plane at an angle of 17 ° with respect to the X axis on the left side of the X through the first and second points with respect to the longitudinal center plane of the vehicle.
And S35, taking the vertical center line of the glass as an axis, taking the sum of the area of the glass symmetrical to the reference area and the reference area as a third area.
The actual coordinate values of the first, second and third regions may be obtained through S31 to S35, that is, the glass is divided to include the first, second and third regions.
S22, acquiring images of the first area, the second area and the third area, and respectively acquiring initial pixel gray-scale images of the first area, the second area and the third area.
Specifically, coordinates of each pixel point of the images of the first region, the second region and the third region corresponding to the vehicle window glass are obtained, that is, the images of the regions are obtained from the collected images, and then initial pixel gray level images of the first region, the second region and the third region are obtained.
In a specific embodiment, as shown in fig. 4, there is provided a flowchart of a method for obtaining an initial pixel gray scale map of a vehicle window glass according to an embodiment of the present invention, the method including:
and S41, setting a square mark with a specified size on the window glass.
And S42, acquiring the image containing the window glass by the camera at the designated position, and acquiring the number of transverse pixels and the number of longitudinal pixels of the square mark in the image.
And S43, acquiring the area of the pixel point and the proportionality coefficient of the area of the glass corresponding to the pixel point according to the number of transverse pixel points, the number of longitudinal pixel points and the actual side length of the square mark in the image.
And S44, acquiring the coordinates of each pixel point of the first area image, the second area image and the third area image according to the proportionality coefficient and the image of the window glass. Since the actual three-dimensional coordinates of the first region, the second region and the third region of the window glass and the image of the window glass are already available, the images of the first region, the second region and the third region can be obtained from the acquired image after the scaling factor is obtained. In addition, other regional interferents can be filtered out, and only the images of the three regions are processed, so that the processing speed can be improved.
S45, the gray scale values of the pixels in the first, second, and third area images at the start of the defrosting or defogging experiment are set as initial values.
Through the steps, the initial pixel gray level images of the first area, the second area and the third area can be obtained.
And S23, after obtaining the visible area proportion of the first area, the second area and the third area, determining the percentage of defrosting or demisting of the first area, the second area and the third area according to the visible area proportion.
And S24, determining the defrosting or defogging performance according to the time length when the percentage of defrosting or defogging reaches the preset defrosting threshold or the preset defogging threshold.
In other embodiments, to demonstrate a dynamic process of defrosting and defogging, the method may further comprise the steps of: respectively acquiring visible boundaries of the window glass at a plurality of specified moments; configuring visual boundaries at different specified moments into different colors; the visual boundaries of different colors are superimposed in a graph to show the changing dynamics of the visual boundaries.
In a preferred embodiment, a front windshield is exemplified as follows: the method comprises the steps of firstly, obtaining actual three-dimensional coordinate values of a first area, a second area and a third area of the vehicle window glass.
Writing data acquisition software on the PC, attaching an identifiable mark on the front windshield, and taking square white paper with the side length of 100mm as an identification mark.
Collecting a front windshield image with an identification mark, manually selecting an effective area of the front windshield through software to obtain pixel coordinate values of the area, manually selecting an area P containing the identification mark from the effective area, filtering out interferents in other areas, processing the content in the area P only, improving the processing speed, solving the number x of marked long pixels and the number y of marked wide pixels in the area P, and taking the arithmetic mean value of the number x of the long pixels and the number y of the wide pixels as
(thus, the problem of image deformation caused by incomplete vertical relation between the front windshield and the camera can be avoided, the calibration accuracy can be improved, and the accuracy of the acquired image of each region can be improved), in the step III, the side length of the known identification mark is 100mm, and the actual value and the proportionality coefficient of the image are calculated
And converting the actual coordinate values of the first area, the third area and the second area of the test vehicle into the pixel coordinate values of the first area, the third area and the second area of the test vehicle on the image, and obtaining the pixel coordinate values of the first area, the third area and the second area on the whole imageThe three areas, namely the first area, the third area and the second area, are displayed through a front windshield process diagram acquired by test software, and the first area, the third area and the second area are front windshield demisting areas.
And storing the result graph in a fixed hard disk folder of the PC in a BMP format.
When a defogging experiment is started, acquiring an original image every second, shearing each original image according to the pixel coordinate value of the effective area of the front windshield obtained in the previous step to obtain an image only in the effective area of the front windshield, wherein the current windshield is full of fog, selecting the first fog-full image at the beginning of the experiment as a reference image, gradually dissipating fog attached to the front windshield in the experiment process, taking the fog-dissipated image on the front windshield as a process image, and calculating gray value difference C of each process image by using gray values A (A1, A2, A3 and A4 …) of the process image and gray value B of the fog-full image of the front windshield, wherein the gray value difference C is shown in formula (1):
C＝A-B (1)
in the test process, except for a reference image, each front windshield fog dissipation process image has a corresponding gray value difference value C, an original process image is firstly converted into a two-dimensional array to obtain the gray value of each point of the two-dimensional array, the gray value of each point is compared with the gray value difference value C, if the gray value is greater than the gray value difference value C, a fog-free area R is determined to be an area in which fog is dissipated, the gray value of the fog-free area R is 255, if the gray value is less than the gray value difference value C, a fog-containing area S is determined, the gray value of the fog-containing area S is 0, the two-dimensional array with the gray values of 0 and 255 is obtained, and then the two-dimensional array is converted into a result image (namely a binary image) in a BMP format with the gray.
And judging the boundary of fog and fog-free in each process map of fog dissipation on the front windshield through the gray value difference value C, wherein the fog dissipation area is arranged in the boundary, the fog dissipation area is arranged outside the boundary, and the percentage of the fog dissipation area in the boundary can be filled and calculated. Preferably, the result graph is expanded for 3 times, corroded for 2 times, noise particles are filtered, and finally a cavity part in the communicating region is filled, so that a fog dissipation process processing graph can be obtained in real time every second, a fog-containing region S and a fog-free region R on the front windshield are judged, and the total number m of pixels of the fog-free region R is obtained through calculation.
According to the pixel coordinates of the first area, the second area and the third area of the front windshield demisting area obtained in the previous step, the three areas are divided into three areas on a fog dissipation process processing diagram according to the pixel coordinates of the three areas, namely the first area, the second area and the third area, the total number of pixels of the first area is n1, the number of fog dissipation pixels of the first area is m1, the total number of pixels of the second area is n2, the number of fog dissipation pixels of the second area is m2, the total number of pixels of the third area is n3, the number of fog dissipation pixels of the third area is m3, the fog dissipation percentage of the first area is m1/n1, the fog dissipation percentage of the second area is m2/n2, and the fog dissipation percentage of the third area is m3/n 3.
According to the limited condition of demisting test time of 10min, sequentially selecting five visible boundaries of the demisting process of 2min, 4min, 6min, 8min and 10min at the beginning of the test, setting different colors for the visible boundaries, sequentially overlapping according to time to obtain a color image, and overlapping pixel coordinates of a first area, a second area and a third area of a front demisting area on the color image to obtain an effect image of the demisting test.
In addition, in order to further improve the accuracy of the judgment of the visibility, the following processing may be performed on the gray value difference value:
calculating to obtain gray value difference values C (C1, C2, C3 and C4 …) of each point in the effective area of the front windshield, sorting the gray value difference values of each point according to the order of magnitude, dividing the gray value difference values into 15 parts, wherein the x axis corresponds to the gray value difference values, the gray value difference values from left to right are sequentially from small to large, the y axis corresponds to the proportion of each gray value difference value of the effective area Q, selecting the gray value difference values Cn corresponding to 90% of the y axis proportion accumulation according to the x axis from right to left, and compensating by a coefficient k2 to obtain Cm, namely Cm is k2 × Cn.
By utilizing the method for determining the proportion of the visible area of the window glass, the first area, the second area and the third area on the window glass can be automatically identified, the defogging process maps in the areas are collected and automatically processed, a fog dissipation boundary effect map is formed, and the fog dissipation percentage is automatically calculated.
Fig. 5 is a schematic structural diagram of an image capturing device according to an embodiment of the present invention. FIG. 6 is an enlarged view of FIG. 5 at A; FIG. 7 is an enlarged view of FIG. 6 at B; fig. 8 is an enlarged view of fig. 5 at C.
In this embodiment, the image capturing apparatus includes:
the camera supports base 1, first hollow pipe 2, seat pipe clamp 3, the hollow pipe 4 of second, cloud platform 5, heat preservation cover 6 and camera 7.
The camera support base 1 with first hollow pipe 2 compresses tightly the mode through the screw thread and fixes, first hollow pipe 2 with pass through between the hollow pipe 4 of second seat pipe clamp 3 is connected, in order to adjust keep warm cover 6 with distance between camera 7 and the ground, the hollow pipe 4 of second with cloud platform 5 passes through threaded connection, it fixes to keep warm cover 6 on cloud platform 5, it establishes to keep warm cover 6 cover on camera 7, cloud platform 5 is used for the adjustment camera 7's gesture.
Specifically, because there are multiple type test cars in the air conditioner performance test, including models such as commercial car, passenger car, the position of camera 7 changes according to the test car type, so be connected through seat pipe clamp 3 between first hollow pipe 2 and the hollow pipe 4 of second, distance about can stretching out and drawing back the regulation, adjust the height of heat preservation cover 6 and camera 7, let camera 7 can shoot the front windshield region of test car completely.
The first hollow round tube 2 and the second hollow round tube 4 are made of stainless steel materials, so that the device is light in weight and convenient to carry and move. The camera supports base 1, first hollow pipe 2 and the hollow pipe 4 three zonulae occludens of second, and the three bending resistance, antitorque performance are good, can be under the test environment of low temperature, powerful cold wind, guarantee that cover 6 and camera 7 keep warm and fix stably and support at the distance above 2m from ground height, and camera 7 can not receive the shake influence. The second hollow circular tube 4 is in threaded connection with the holder 5, belongs to interference fit, and is tightly reinforced with the second hollow circular tube 4 and the holder 5. The heat preservation cover 6 is stably placed on the cloud platform 5, and the cloud platform 5 can carry out attitude adjustment on the camera 7 in the heat preservation cover 6.
Preferably, the heat insulation cover 6 has a heating and heat insulation function and is of a sealing cover structure so as to prevent the camera 7 from being affected by environmental moisture.
For example, the heat-retaining cover 6 can perform a heating function, a heat-retaining function, and an automatic power-off function. When carrying out air conditioner performance defogging test, will park the low temperature storehouse of test car and cool down, camera 7 temperature reduces thereupon, and when camera 7 temperature is less than 0 ℃, heat preservation cover 6 heats, prevents that camera 7 from breaking down because of the low temperature environment. The heat preservation cover 6 is added with the heat preservation cotton around, keeps warm to the camera simultaneously, and camera 7 can be always under low temperature environment real time monitoring and gather the image of front windshield's change process. Meanwhile, the heat-insulating cover 6 can be detached, so that the camera 7 in the heat-insulating cover 6 can be conveniently adjusted; when the defogging performance test is carried out in the low-temperature cabin, the humidity in the low-temperature cabin can be increased, so that the heat-insulating cover 6 is completely sealed, and the camera 7 is prevented from being influenced by the environment humidity. The camera 7 can be specifically selected to be at a low temperature: the industrial camera capable of keeping normal operation in the extreme environment of-40 ℃ can prevent the camera 7 from being broken down due to poor effect of the heat insulation cover 6.
In another embodiment, the image capturing apparatus further comprises: a plurality of light sources. This can affect the test results as a single light source may cause inconsistent brightness across the glazing. Preferably, 2 light sources are adopted, the first light source is fixedly arranged on a headrest of a front seat in a vehicle, and the second light source and the third light source are respectively arranged on two sides of a front windshield to improve the regional brightness of the front windshield.
The embodiments in this specification are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make numerous possible variations and modifications to the present invention, or modify equivalent embodiments, using the methods and techniques disclosed above, without departing from the scope of the present invention. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (9)
1. A method for determining the proportion of the visible area of window glass is characterized by comprising the following steps:
acquiring an image containing a vehicle window glass;
acquiring coordinates of each pixel point of the image corresponding to the vehicle window glass to obtain an initial pixel gray scale map of the vehicle window glass, wherein the initial gray scale value of each pixel point of the initial pixel gray scale map is a gray scale value which is not visible for representing the glass;
acquiring gray values of all pixel points of the image at different moments, wherein the gray values are related to the visibility of the glass;
identifying a visual boundary according to the initial gray value of each pixel point and the gray values at different moments;
determining a visible area ratio according to the area enclosed by the visible boundary and the area of the image;
the obtaining of the coordinates of each pixel point of the image corresponding to the window glass to obtain an initial pixel gray level image of the window glass comprises:
setting a square mark with a specified size on the vehicle window glass;
the method comprises the following steps that a camera positioned at an appointed position collects an image containing vehicle window glass, and the number of transverse pixel points and the number of longitudinal pixel points of a square mark in the image are obtained;
acquiring the area of a pixel point and the proportional coefficient of the area of the pixel point corresponding to the glass according to the number of transverse pixel points, the number of longitudinal pixel points and the actual side length of the square mark in the image;
obtaining coordinates of each pixel point of the first area image, the second area image and the third area image according to the proportion coefficient and the image of the window glass;
and setting the gray value of each pixel point of the first area image, the second area image and the third area image at the beginning of the defrosting or defogging experiment as an initial value.
2. The method of claim 1, further comprising:
dividing the glass into a first region, a second region and a third region before acquiring an image containing the window glass;
acquiring images of the first area, the second area and the third area, and respectively acquiring initial pixel gray-scale images of the first area, the second area and the third area;
after obtaining the visible area ratios of the first area, the second area and the third area, determining the defrosting or defogging percentages of the first area, the second area and the third area according to the visible area ratios;
and determining the defrosting or defogging performance according to the time length when the percentage of defrosting or defogging reaches the preset defrosting threshold or the preset defogging threshold.
3. The method of claim 2, wherein the dividing the glass into a first region, a second region, and a third region comprises:
determining the area enclosed by the intersection lines of 4 planes which represent the two points of the eyes of the driver and extend forwards and the glass surface according to the vertical plumb plane of the central line of the seating position of the driver, the seating reference point and the angle of the seat backrest;
taking the area as a first area;
taking the vertical center line of the glass as an axis, and taking the area of the glass symmetrical to the first area as a second area;
a minimum area at the first area and inward from the glass edge by at least a first length is a reference area;
and taking the vertical center line of the glass as an axis, taking the sum of the area of the glass symmetrical to the reference area and the reference area as a third area.
4. The method according to claim 1, wherein the obtaining the gray scale values of the pixels of the image at different times comprises:
a gray value array is set for each pixel point,
and acquiring the gray value of each pixel point of the image at each sampling time, and storing the gray value in the gray value number sequence corresponding to each pixel point, or acquiring the gray value of each pixel point of the image according to a specified sampling period, and storing the gray value in the gray value number sequence corresponding to each pixel point.
5. The method of claim 4, wherein the identifying the visual boundary according to the initial gray value of each pixel point and the gray values at different times comprises:
comparing the current gray value of each pixel point with a gray value difference value, wherein the gray value difference value is the difference value between the initial gray value and the current gray value of the pixel point;
if the current gray value is greater than the gray value difference value, the glass corresponding to the pixel point is a visual area;
if the current gray value is smaller than the gray value difference value, the glass corresponding to the pixel point is an invisible area;
visual boundaries are identified based on the visual area.
6. The method of claim 5, further comprising:
respectively acquiring visible boundaries of the window glass at a plurality of specified moments;
configuring visual boundaries at different specified moments into different colors;
the visual boundaries of different colors are superimposed in a graph to show the changing dynamics of the visual boundaries.
7. The method according to any one of claims 1 to 6, wherein the image is acquired by an image acquisition device comprising:
the camera support base (1), a first hollow round pipe (2), a base pipe clamp (3), a second hollow round pipe (4), a tripod head (5), a heat preservation cover (6) and a camera (7);
the camera support base (1) with first hollow pipe (2) compress tightly the mode through the screw thread and fix, first hollow pipe (2) with pass through between second hollow pipe (4) seat pipe clamp (3) are connected, in order to adjust keep warm cover (6) with distance between camera (7) and the ground, second hollow pipe (4) with cloud platform (5) are through threaded connection, it fixes to keep warm cover (6) on cloud platform (5), it establishes to keep warm cover (6) cover on camera (7), cloud platform (5) are used for the adjustment the gesture of camera (7).
8. The method according to claim 7, characterized in that the heat-insulating cover (6) has a heat-insulating function and is of a sealing cover structure to prevent the camera (7) from being affected by environmental moisture.
9. The method of claim 7, wherein the image acquisition device further comprises: a plurality of light sources.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710944414.3A CN107845110B (en) | 2017-09-30 | 2017-09-30 | Method for determining proportion of visible area of window glass |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710944414.3A CN107845110B (en) | 2017-09-30 | 2017-09-30 | Method for determining proportion of visible area of window glass |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107845110A CN107845110A (en) | 2018-03-27 |
| CN107845110B true CN107845110B (en) | 2020-07-24 |
Family
ID=61661293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710944414.3A Active CN107845110B (en) | 2017-09-30 | 2017-09-30 | Method for determining proportion of visible area of window glass |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107845110B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110406346B (en) * | 2018-04-26 | 2022-05-06 | 上海博泰悦臻网络技术服务有限公司 | Air conditioner control method and system based on image acquisition and vehicle |
| CN110132612A (en) * | 2019-05-31 | 2019-08-16 | 中国汽车工程研究院股份有限公司 | A kind of defrosting effect scalarization method suitable for the performance test that defrosts |
| CN111251830B (en) * | 2020-02-19 | 2021-09-03 | 陆绥平 | Intelligent blowing heating driving system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104908555A (en) * | 2015-06-29 | 2015-09-16 | 吉林大学 | Automobile glass optical defogging system and method |
| CN104908718A (en) * | 2015-06-29 | 2015-09-16 | 吉林大学 | Automobile glass automatic defogging system and method based on transmittance and relative humidity |
| CN106515369A (en) * | 2016-11-29 | 2017-03-22 | 北京汽车研究总院有限公司 | Control method and device for vehicle air conditioner |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI537984B (en) * | 2013-10-24 | 2016-06-11 | 國立清華大學 | A flexible transparent thermal conductive film |
-
2017
- 2017-09-30 CN CN201710944414.3A patent/CN107845110B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104908555A (en) * | 2015-06-29 | 2015-09-16 | 吉林大学 | Automobile glass optical defogging system and method |
| CN104908718A (en) * | 2015-06-29 | 2015-09-16 | 吉林大学 | Automobile glass automatic defogging system and method based on transmittance and relative humidity |
| CN106515369A (en) * | 2016-11-29 | 2017-03-22 | 北京汽车研究总院有限公司 | Control method and device for vehicle air conditioner |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107845110A (en) | 2018-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106503636B (en) | A kind of road sighting distance detection method and device of view-based access control model image | |
| CN107845110B (en) | Method for determining proportion of visible area of window glass | |
| CN105631853B (en) | Vehicle-mounted binocular camera demarcation and Verification method | |
| CN105722708B (en) | Driving ancillary equipment and method | |
| JP4942509B2 (en) | Vehicle position detection method and apparatus | |
| CN106651963B (en) | A kind of installation parameter scaling method of the vehicle-mounted camera for driving assistance system | |
| CN105424655A (en) | Visibility detection method based on video images | |
| CN110415544B (en) | Disaster weather early warning method and automobile AR-HUD system | |
| KR101030211B1 (en) | System and method for detecting road and object | |
| CN106218587B (en) | A kind of method and apparatus for opening defrosting function | |
| US20150178902A1 (en) | Image processing apparatus and image processing method for removing rain streaks from image data | |
| CN112339622B (en) | Seat adjusting method and device and vehicle-mounted system | |
| CN208481999U (en) | A kind of virtual reality experience system | |
| CN108151824B (en) | Water level recognition methods and system based on vehicle-mounted panoramic image | |
| TWI749030B (en) | Driving assistance system and driving assistance method | |
| CN109703465B (en) | Control method and device for vehicle-mounted image sensor | |
| CN110874559A (en) | Method and device for evaluating a vehicle driving surface | |
| WO2016091041A1 (en) | Method for performing dynamic evaluation on lighting glare of road by using imaging brightness meter | |
| DE102013204597A1 (en) | Method and apparatus for determining visibility in fog during the day | |
| CN106627416A (en) | Method, device and system for detecting road type | |
| CN110989344A (en) | Automatic adjustment method and system for preset parameters of inspection robot | |
| CN108256487B (en) | Driving state detection device and method based on reverse dual-purpose | |
| CN103954437A (en) | Vehicle headlamp irradiation angle detection method, device and system based on vertical face | |
| CN102999904B (en) | Plane-based micro-nano object image tilt correction method | |
| CN113538311B (en) | Image fusion method of vehicle-mounted redundant camera based on subjective visual effect of human eyes |
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 |