CN110135260A - The determination method, apparatus and electronic equipment on the boundary of area-of-interest in image - Google Patents
The determination method, apparatus and electronic equipment on the boundary of area-of-interest in image Download PDFInfo
- Publication number
- CN110135260A CN110135260A CN201910300267.5A CN201910300267A CN110135260A CN 110135260 A CN110135260 A CN 110135260A CN 201910300267 A CN201910300267 A CN 201910300267A CN 110135260 A CN110135260 A CN 110135260A
- Authority
- CN
- China
- Prior art keywords
- image
- interest
- area
- row
- electronic equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
-
- 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
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Abstract
The invention discloses the determination method, apparatus and electronic equipment on the boundary of area-of-interest in a kind of image, this method comprises: obtaining the forward image of the vehicle for the electronic equipment acquisition being installed in the vehicle;It is handled using adjacent two frame forward image of the frame difference method to the forward image, obtains binary image;Since the first row pixel of the binary image, the quantity of each row white pixel point in the binary image is successively counted;According to the quantity of each row white pixel point, one-row pixels point is chosen from the binary image, the one-row pixels point is that the quantity of last line white pixel point in the binary image is not 0 row pixel;According to the one-row pixels point present position in the binary image selected, the lower boundary of area-of-interest is determined from the forward image.
Description
Technical field
The present invention relates to technical field of image processing, more particularly, to the boundary of area-of-interest in a kind of image
Determine method, in a kind of image the boundary of area-of-interest determining device and a kind of electronic equipment.
Background technique
Advanced driving assistance system (advanced driver assistance system, ADAS) is artificial as representing
One of field of intellectual technology is always academia and industry focus of attention.ADAS includes various early warning systems, such as lane
Deviate early warning system (lane departure warning system, LDWS), frontal collisions early warning system (forward
Collision warning system, FCWS).
Since the security requirement of ADAS is high, so that the accuracy requirement of various warning functions is higher.ADAS passes through to it
The corresponding image of the road ahead collected is analyzed, and driver's Real-time Feedback is given, to effectively avoid the hair of accident
It is raw.
ADAS is corresponding from road ahead first when the corresponding image of road ahead collected using it is analyzed
Image in intercept area-of-interest (region of interest, ROI), then ROI is analyzed, it is anti-to give driver
Feedback.
In the prior art, when intercepting ROI from the corresponding image of road ahead, usually with the corresponding image of road ahead
Lower boundary of the lower boundary as ROI.According to the preset height value of ROI and the lower boundary of ROI, the coboundary of ROI is obtained.
Due to being provided with the influence of installation site factor of the electronic equipment of ADAS in vehicle, so that it was collected
The lower half portion of the corresponding image of road ahead includes the corresponding image of vehicle headstock, i.e., its road ahead collected is corresponding
Image lower boundary be the corresponding image of vehicle headstock lower boundary so that the lower boundary of ROI be vehicle headstock correspondence
Image lower boundary.
Fig. 1 is the schematic diagram of the corresponding image of road ahead of electronic equipment acquisition.Fig. 2 is provided based on the prior art
The schematic diagram for the ROI that method intercepts.
Due to the influence of installation site factor of the electronic equipment in vehicle, according to Fig.2, the headstock of vehicle in ROI
Corresponding image proportion is excessive.Since the corresponding image of the headstock of vehicle does not include road ahead traffic information, in this way
It will affect the testing result of image, and then cause the accuracy of early warning poor.
Summary of the invention
It is an object of the present invention to provide a kind of for determining the new solution on the boundary of area-of-interest.
According to the first aspect of the invention, a kind of determination method on the boundary of area-of-interest in image is provided, comprising:
Obtain the forward image of the vehicle for the electronic equipment acquisition being installed in the vehicle;
It is handled using adjacent two frame forward image of the frame difference method to the forward image, obtains binary image;
Since the first row pixel of the binary image, each row white picture in the binary image is successively counted
The quantity of vegetarian refreshments;
According to the quantity of each row white pixel point, the selection one-row pixels point from the binary image, described one
Row pixel is the row pixel that the quantity of last line white pixel point in the binary image is not 0;
According to the one-row pixels point present position in the binary image selected, from the forward image
Determine the lower boundary of area-of-interest.
Optionally, the screen of the electronic equipment shows horizontal alignment line and vertical lubber-line, wherein the horizontal school
Directrix is overlapped with the horizontal center line of the screen, and the vertical lubber-line is overlapped with the vertical centerline of the screen, wherein
Before the forward image of the vehicle of the electronic equipment acquisition for obtaining and being installed in the vehicle, the electronics
Installation requirement of the equipment in vehicle includes: horizon and the water in the forward image of the vehicle of the electronic equipment acquisition
Flat lubber-line is overlapped, the vertical centerline of the corresponding image of headstock in the forward image of the vehicle of the electronic equipment acquisition with
The vertical lubber-line is overlapped.
Optionally, it the first row pixel since the binary image, successively counts in the binary image
Before the quantity of each row white pixel point, the method also includes:
The expansion process and corrosion treatment in Morphological scale-space are successively carried out to the binary image, obtain that treated
Binary image.
Optionally, after determining the lower boundary of area-of-interest from the forward image, the method also includes:
The fixation coboundary for obtaining setting, using the coboundary as the area-of-interest intercepted from the forward image.
Optionally, after determining the lower boundary of area-of-interest from the forward image, the method also includes:
Obtain the preset height value of area-of-interest;
The sense intercepted from the forward image is determined according to the lower boundary of the preset height value and the area-of-interest
The coboundary in interest region.
Optionally, after determining the lower boundary of area-of-interest from the forward image, the method also includes:
According to the lower boundary of the lower boundary of the area-of-interest and the forward image, vehicle in the forward image is determined
The height of corresponding image;
The height of the corresponding image of the headstock is compared with preset height, obtains comparison result;
In the case where the height that the comparison result is the corresponding image of the headstock is more than the preset height, issue
Adjust the prompt of the installation site of electronic equipment.
Optionally, the lower boundary of area-of-interest is determined from the forward image further include:
Based on the adjacent two frames forward image of multiple groups, last line white pixel is chosen respectively from corresponding binary image
One-row pixels point when the quantity of point is not 0;
One-row pixels point when quantity according to the last one each white pixel point is not 0 is in corresponding binary image
Present position determines the lower boundary of the area-of-interest.
Optionally, the quantity according to each row white pixel point chooses a line picture from the binary image
Vegetarian refreshments, the one-row pixels point are that the quantity of last line white pixel point in the binary image is not 0 row pixel
The step of include:
Histogram is generated using the quantity of each row white pixel point, wherein the abscissa of the histogram represents pixel
Locating line number, ordinate represent the quantity of the white pixel point of current line;
The histogram is handled using convex closure detection algorithm, obtains multiple convex closures, and choose and be located at the rightmost side
Convex closure;
Obtain the location information for forming the point of the rightmost side of rightmost side convex closure;
One-row pixels point when determining that the quantity of white pixel point is not 0 using the location information.
According to the second aspect of the invention, a kind of determining device on the boundary of area-of-interest in image is provided, including
Memory and processor, the memory is for storing executable instruction;The processor is used for the control in described instruction
Lower execution method according to any one of first aspect.
According to the third aspect of the invention we, a kind of electronic equipment is provided, including in the image according to second aspect
The determining device on the boundary of area-of-interest.
According to one embodiment of present invention, the corresponding image of headstock that will be located at the lower part of the forward image of vehicle is cut
It takes down, so that including no longer the corresponding image of headstock from the area-of-interest that the forward image of vehicle intercepts, avoids headstock
Interference of the corresponding image to subsequent early warning detection algorithm, and make as subsequent early warning detection zone area-of-interest more
Add precisely, improves the accuracy of subsequent early warning testing result.
By referring to the drawings to the detailed description of exemplary embodiment of the present invention, other feature of the invention and its
Advantage will become apparent.
Detailed description of the invention
It is combined in the description and the attached drawing for constituting part of specification shows the embodiment of the present invention, and even
With its explanation together principle for explaining the present invention.
Fig. 1 is the schematic diagram of the corresponding image of road ahead of electronic equipment acquisition.
Fig. 2 is the schematic diagram for the ROI that the method provided based on the prior art is intercepted.
Fig. 3 is the block diagram of the hardware configuration of electronic equipment provided in an embodiment of the present invention.
Fig. 4 is the process flow of the determination method on the boundary of area-of-interest in the image provided according to embodiments of the present invention
Figure.
Fig. 5 is the schematic diagram of the screen of the electronic equipment provided according to embodiments of the present invention.
Fig. 6 is the schematic diagram of the binary image according to an embodiment of the invention after Morphological scale-space.
Fig. 7 is the signal for the histogram that the quantity based on row white pixel point each in the binary image shown in Fig. 6 generates
Figure.
Fig. 8 is the schematic diagram handled using convex closure detection algorithm Fig. 7.
Fig. 9 is the structural representation of the determining device on the boundary of area-of-interest in image according to an embodiment of the invention
Figure.
Figure 10 is the hardware knot of the determining device on the boundary of area-of-interest in image according to an embodiment of the invention
Structure schematic diagram.
Specific embodiment
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The range of invention.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the present invention
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, without
It is as limitation.Therefore, other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
<hardware configuration>
Fig. 3 is the block diagram of the hardware configuration of electronic equipment provided in an embodiment of the present invention.
Electronic equipment can be navigator, automobile data recorder, mobile phone, any in tablet computer.
According to Fig.3, electronic equipment 3000 may include processor 3100, memory 3200, interface arrangement 3300, lead to
T unit 3400, display device 3500, input unit 3600, positioning device 3700, loudspeaker 3800, etc..Wherein, processor
3100 can be central processor CPU, Micro-processor MCV etc..Memory 3200 is for example including ROM (read-only memory), RAM
(random access memory), nonvolatile memory of hard disk etc..Interface arrangement 3300 is for example including USB interface, earphone
Interface etc..Communication device 3400 is for example able to carry out wired or wireless communication.Display device 3500 is, for example, liquid crystal display, touching
Touch display screen etc..Input unit 3600 is also possible to microphone input voice messaging such as may include touch screen, keyboard.
Positioning device 3700 is used to provide positioning function, such as can be GPS positioning module, Beidou positioning module etc..Loudspeaker 3800
For issuing voice prompting message.
Although multiple devices of electronic equipment are shown in FIG. 3, the present invention can only relate to part dress therein
It sets, for example, electronic equipment pertains only to memory 3200 and processor 3100.
In the present embodiment, for storing instruction, which is used for control processor 3100 to the memory 3200 of electronic equipment
It is operated to execute the determination method on the boundary of area-of-interest in the image of any embodiment of that present invention.Technical staff can be with
Disclosed conceptual design instruction according to the present invention.How control processor is operated for instruction, this is it is known in the art that therefore herein
It is not described in detail.
<embodiment of the method>
Fig. 4 is the process flow of the determination method on the boundary of area-of-interest in the image provided according to embodiments of the present invention
Figure.
According to Fig.4, the determination method on the boundary of area-of-interest at least includes the following steps S4100- in image
S4500。
Step S4100 obtains the forward image of the vehicle for the electronic equipment acquisition being installed in the vehicle.
The screen of electronic equipment shows horizontal alignment line and vertical lubber-line.The horizontal centre of horizontal alignment line and screen
Line is overlapped.Vertical lubber-line is overlapped with the vertical centerline of screen.
In executing image provided in an embodiment of the present invention before the determination method on the boundary of area-of-interest, electronic equipment
Installation requirement in vehicle includes: horizon and horizontal alignment line weight in the forward image of the vehicle of electronic equipment acquisition
It closes, the vertical centerline of the corresponding image of headstock in the forward image of the vehicle of electronic equipment acquisition and vertical lubber-line weight
It closes.The forward image for the vehicle for enabling electronic equipment to acquire so accurately shows the traffic information of vehicle front.
For example, vehicle parking is on open flat road surface before electronic equipment is mounted in front windshield of vehicle
On, and distant place horizon needs are high-visible.In the installation process of electronic equipment, as shown in figure 5, the screen of electronic equipment is aobvious
It is shown with horizontal alignment line and vertical lubber-line.When electronic equipment acquisition vehicle forward image in horizon and horizontal alignment
Line is overlapped, and when the vertical centerline of the corresponding image of headstock of electronic equipment acquisition is overlapped with vertical lubber-line, electronic equipment
The position being presently in is the position for meeting installation requirement.
As shown in figure 5, the screen of electronic equipment also shows two assisted calibration lines.Two assisted calibration lines it is common
Endpoint is the central point of the screen of electronic equipment.Another endpoint of two assisted calibration lines is respectively the screen of electronic equipment
The lower left corner vertex and the lower right corner vertex.By corresponding with the headstock that electronic equipment acquires using two assisted calibration lines
The relative position of image allows users to the installation site for rapidly and accurately adjusting electronic equipment, so that electronic equipment acquires
The vertical centerline of the corresponding image of headstock be overlapped with vertical lubber-line.
Installation requirement of the electronic equipment in vehicle further include: the vehicle that the corresponding image of headstock is acquired in electronic equipment
Shared ratio is less than preset ratio value in forward image, to guarantee that the forward image of vehicle of electronic equipment acquisition can satisfy
The requirement of road early warning detection, detection caused by avoiding the corresponding image of headstock proportion in the forward image of vehicle excessively high
As a result inaccurate problem.
Step S4200 is handled using adjacent two frame forward image of the frame difference method to forward image, obtains binary picture
Picture.
The principle of frame difference method is as follows: since the target in scene is moving, position of the image of target in different images frame
It sets and is different.When carrying out calculus of differences to continuous two field pictures, i.e. the gray value of the corresponding pixel of two field pictures carries out
When subtracting each other, the corresponding gray scale difference of available each pixel.The gray scale absolute value of the difference of pixel is compared with preset threshold
It is right, obtain comparison result.It, can be true in the case where the gray scale absolute value of the difference that comparison result is pixel is more than preset threshold
The fixed pixel is the pixel of moving target, i.e. pixel in prospect, and the gray value of the pixel is set as 255.?
Comparison result is that can determine that the pixel is non-fortune in the case that the absolute value of the gray value of pixel is less than preset threshold
The pixel of moving-target, i.e. pixel in background, and the gray value of the pixel is set as 0.A binaryzation is obtained in this way
Image.
Step S4300 successively counts each row white in binary image since the first row pixel of binary image
The quantity of pixel.
In one embodiment of the invention, the first row pixel since binary image, two-value is successively counted
Change in image before the quantity of each row white pixel point, binary image is successively carried out expansion process in Morphological scale-space and
Corrosion treatment, the binary image that obtains that treated.The influence that noise in binary image can be eliminated in this way, so that binaryzation
The profile of moving target is more nearly the target object in actual scene in image.
Expansion process and corrosion treatment are all based on what the pixel that the gray value in binary image is 255 carried out.It is swollen
Swollen processing is expanded to the white area in binary image, and the area bigger than the white area in binary image is obtained
Domain.Corrosion treatment is to corrode the white area after expansion process, obtains the region after white area becomes smaller.
Step S4400 chooses one-row pixels point, the row according to the quantity of each row white pixel point from binary image
Pixel is the row pixel that the quantity of last line white pixel point in binary image is not 0.
In one example, the gray value of white pixel point is 255 in binary image, and the gray value of black pixel point is
0.The quantity of each row white pixel point is to count the quantity for the pixel that each row gray value is 255 in statistics binary image.
Step S4400 further comprises step S4410-S4440.
Step S4410 generates histogram using the quantity of each row white pixel point, wherein the abscissa of histogram represents
Line number locating for pixel, ordinate represent the quantity of the white pixel point of current line.
Fig. 6 is the schematic diagram of the binary image according to an embodiment of the invention after Morphological scale-space.Fig. 7 is
The schematic diagram for the histogram that quantity based on row white pixel point each in the binary image shown in Fig. 6 generates.
According to Fig.6, upper parts of images is the sky image in scene, and lower parts of images is the corresponding image of headstock.
Step S4420 is handled histogram using convex closure detection algorithm, obtains multiple convex closures, and choose and be located at most
The convex closure on right side.
Fig. 8 is the schematic diagram handled using convex closure detection algorithm Fig. 7.According to Fig.8, it is shown from Fig. 7
Histogram in available multiple convex closures.The convex closure for being the rightmost side by the delta-shaped region that tri- points of a, b, c surround is corresponding
Region.
Step S4430 obtains the location information for forming the point of the rightmost side of rightmost side convex closure.
According to Fig.8, c point is the point to form the rightmost side of rightmost side convex closure.The location information of c point is the horizontal seat of c point
Mark information, the i.e. corresponding line number information of c point.
Step S4440 determines last line white pixel point in binary image using the location information of the point of the rightmost side
Quantity be not 0 corresponding row pixel.When determining that the quantity of white pixel point is not 0 using the corresponding line number information of c point
Corresponding row pixel.
Step S4500, according to the one-row pixels point present position in binary image selected, from vehicle image really
Determine the lower boundary of area-of-interest.
In one example, the processing that above-mentioned steps S4200-S4400 is executed to one group of adjacent two frames forward image, obtains
The quantity for the last line white pixel point chosen from binary image is not 0 row pixel, and according to the row selected
Pixel present position in binary image determines the lower boundary of area-of-interest from forward image.
In one example, two frames forward image adjacent to multiple groups executes the processing of above-mentioned steps S4200-S4400 respectively,
The quantity for obtaining the last line white pixel point chosen from corresponding binary image is not 0 row pixel.According to respectively most
One-row pixels point present position, determining sense in corresponding binary image when the quantity of the latter white pixel point is not 0
The lower boundary in interest region.One-row pixels point when not being 0 to the quantity of the last one each white pixel point is corresponding two
Locating line number carries out average value processing in value image, obtains a line number value, and using the line number value as area-of-interest
Lower boundary.
For example, three groups of adjacent two frames forward images are executed with the processing of above-mentioned steps S4200-S4400 respectively, obtain from right
The three row pictures that the quantity for the last line white pixel point that the binary image answered is chosen is not 0 row pixel, and selects
Vegetarian refreshments is respectively the 31st row, the 32nd row and the 33rd row in corresponding binary image present position.To the three row pixels selected
Point line number locating for corresponding binary image carries out average value processing, obtains line number value 32.By the of the forward image of vehicle
Lower boundary of 32 rows as area-of-interest.
In one embodiment of the invention, the coboundary of area-of-interest can be the fixation top of setting in image
Boundary, such as using the 10th row of the forward image of vehicle as the coboundary of area-of-interest in image.Alternatively, in determining image
After the lower boundary of area-of-interest, the preset height value of area-of-interest in image is obtained.According in preset height value and image
The lower boundary of area-of-interest determines the coboundary of the area-of-interest from the forward image truncated picture of vehicle.
Since installation site of the electronic equipment in vehicle is that manual operation is completed, the corresponding image of headstock is set in electronics
Ratio shared by the forward image of the vehicle of standby acquisition is by artificial subjective determining.In order to ensure the corresponding image of headstock is in electricity
Shared ratio is less than preset ratio value in the forward image of the vehicle of sub- equipment acquisition, in one embodiment, according to image
The lower boundary of the forward image of the lower boundary and vehicle of middle area-of-interest determines the corresponding figure of headstock in the forward image of vehicle
The height of picture.The height of the corresponding image of headstock is compared with preset height, obtains comparison result.According to the comparison result
Determine whether the corresponding image of headstock ratio shared in the forward image for the vehicle that electronic equipment acquires is less than preset ratio
Value.
In the case where the height that comparison result is the corresponding image of headstock is less than preset height, headstock pair can be determined
The image answered ratio shared in the forward image for the vehicle that electronic equipment acquires is less than preset ratio value, and then can determine
The installation site of electronic equipment is met the requirements.
In the case where the height that comparison result is the corresponding image of headstock is more than preset height, it can determine that headstock is corresponding
Image it is shared in the forward image for the vehicle that electronic equipment acquires ratio it is non-be less than preset ratio value, and issue adjustment electricity
The prompt of the installation site of sub- equipment.The prompt can be voice prompting, any in screen display reminding.
The determination method on the boundary of area-of-interest in image provided in an embodiment of the present invention will be located at the front figure of vehicle
The corresponding image interception of headstock of the lower part of picture falls, so that no longer wrapping from the area-of-interest that the forward image of vehicle intercepts
The corresponding image of headstock is included, avoids interference of the corresponding image of headstock to subsequent early warning detection algorithm, and make as rear
The area-of-interest of continuous early warning detection zone is more accurate, improves the accuracy of subsequent early warning testing result.
<Installation practice>
Fig. 9 is the structural representation of the determining device on the boundary of area-of-interest in image according to an embodiment of the invention
Figure.
According to Fig. 9, the determining device on the boundary of area-of-interest at least may include: acquisition module in the image
9100, image processing module 9200, statistical module 9300, selection module 9400 and area-of-interest lower boundary determining module
9500。
Obtain the forward image that module 9100 is used to obtain the vehicle for the electronic equipment acquisition being installed in the vehicle.
Image processing module 9200 be used for using frame difference method to the adjacent two frames forward image of the forward image at
Reason, obtains binary image.
Statistical module 9300 is used for since the first row pixel of the binary image, successively counts the binaryzation
The quantity of each row white pixel point in image.
Module 9400 is chosen for the quantity according to each row white pixel point, chooses one from the binary image
Row pixel, the one-row pixels point are that the quantity of last line white pixel point in the binary image is not 0 row picture
Vegetarian refreshments.
Lower boundary determining module 9500 is used for according to the one-row pixels point institute in the binary image selected
Locate position, the lower boundary of area-of-interest is determined from the forward image.
In one embodiment, the quantity for choosing module 9400 to be also used to the pixel for being 255 using each row gray value is raw
At histogram, wherein the abscissa of the histogram represents line number locating for pixel, and ordinate represents the gray value of current line
For the quantity of 255 pixel;The histogram is handled using convex closure detection algorithm, obtains multiple convex closures, and choose
Convex closure positioned at the rightmost side;Obtain the location information for forming the point of the rightmost side of rightmost side convex closure;Ash is determined using location information
The quantity for the pixel that angle value is 255 corresponding last line pixel when not being 0.
In one embodiment, the screen of electronic equipment shows horizontal alignment line and vertical lubber-line, wherein horizontal school
Directrix is overlapped with the horizontal center line of screen, and vertical lubber-line is overlapped with the vertical centerline of screen, wherein electronic equipment is in vehicle
Installation requirement in includes: that the horizon in the forward image of the vehicle of electronic equipment acquisition is overlapped with horizontal alignment line, electricity
The vertical centerline of the corresponding image of headstock in the forward image of the vehicle of sub- equipment acquisition is overlapped with vertical lubber-line.
In one embodiment, the determining device on the boundary of area-of-interest further includes Morphological scale-space module in image.
The Morphological scale-space module is used to successively carry out the binary image expansion process and corrosion treatment in Morphological scale-space,
The binary image that obtains that treated.
In one embodiment, the determining device on the boundary of area-of-interest further includes coboundary determining module in image.
The coboundary determining module is used to obtain the fixation coboundary set, using as intercepting from the forward image of vehicle
The coboundary of area-of-interest.Alternatively, coboundary determining module is used to obtain the preset height value of area-of-interest;According to default
The lower boundary of height value and area-of-interest determines the coboundary of the area-of-interest intercepted from the forward image of vehicle.
In one embodiment, the determining device on the boundary of area-of-interest further includes electronic equipment installation site in image
Determining module.The electronic equipment installation site determining module is used for according to the following of the lower boundary of area-of-interest and forward image
Boundary determines the height of the corresponding image of headstock in forward image;The height of the corresponding image of headstock is compared with preset height
It is right, obtain comparison result;In the case where the height that comparison result is the corresponding image of headstock is more than preset height, adjustment is issued
The prompt of the installation site of electronic equipment.
Figure 10 is the hardware knot of the determining device on the boundary of area-of-interest in image according to an embodiment of the invention
Structure schematic diagram.
According to Fig.10, the determining device on the boundary of area-of-interest may include memory in the image of the present embodiment
1020 and processor 1010.For storing instruction, which is operated for control processor 1010 to hold memory 1020
The determination method on the boundary of area-of-interest in the image of row any embodiment of that present invention.Technical staff can institute according to the present invention
Open conceptual design instruction.How control processor is operated for instruction, this is it is known in the art that therefore no longer retouching in detail herein
It states.
The present invention can be system, method and/or computer program product.Computer program product may include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the invention.
Computer readable storage medium, which can be, can keep and store the tangible of the instruction used by instruction execution equipment
Equipment.Computer readable storage medium for example can be-- but it is not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer readable storage medium
More specific example (non exhaustive list) includes: portable computer diskette, hard disk, random access memory (RAM), read-only deposits
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), portable
Compact disk read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above
Machine readable storage medium storing program for executing is not interpreted that instantaneous signal itself, the electromagnetic wave of such as radio wave or other Free propagations lead to
It crosses the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or is transmitted by electric wire
Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing operation of the present invention can be assembly instruction, instruction set architecture (ISA) instructs,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
The source code or object code that any combination is write, the programming language include the programming language-of object-oriented such as
Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions can be executed fully on the user computer, partly execute on the user computer, be only as one
Vertical software package executes, part executes on the remote computer or completely in remote computer on the user computer for part
Or it is executed on server.In situations involving remote computers, remote computer can pass through network-packet of any kind
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).In some embodiments, by utilizing computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can execute computer-readable program instructions, to realize each side of the invention
Face.
Referring herein to according to the method for the embodiment of the present invention, the flow chart of device (system) and computer program product and/
Or block diagram describes various aspects of the invention.It should be appreciated that flowchart and or block diagram each box and flow chart and/
Or in block diagram each box combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to general purpose computer, special purpose computer or other programmable datas
The processor of processing unit, so that a kind of machine is produced, so that these instructions are passing through computer or other programmable datas
When the processor of processing unit executes, function specified in one or more boxes in implementation flow chart and/or block diagram is produced
The device of energy/movement.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
It enables so that computer, programmable data processing unit and/or other equipment work in a specific way, thus, it is stored with instruction
Computer-readable medium then includes a manufacture comprising in one or more boxes in implementation flow chart and/or block diagram
The instruction of the various aspects of defined function action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, to produce
Raw computer implemented process, so that executed in computer, other programmable data processing units or other equipment
Instruct function action specified in one or more boxes in implementation flow chart and/or block diagram.
The flow chart and block diagram in the drawings show the system of multiple embodiments according to the present invention, method and computer journeys
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
One module of table, program segment or a part of instruction, the module, program segment or a part of instruction include one or more use
The executable instruction of the logic function as defined in realizing.In some implementations as replacements, function marked in the box
It can occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually be held substantially in parallel
Row, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that block diagram and/or
The combination of each box in flow chart and the box in block diagram and or flow chart, can the function as defined in executing or dynamic
The dedicated hardware based system made is realized, or can be realized using a combination of dedicated hardware and computer instructions.It is right
For those skilled in the art it is well known that, by hardware mode realize, by software mode realize and pass through software and
It is all of equal value that the mode of combination of hardware, which is realized,.
Various embodiments of the present invention are described above, above description is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport
In the principle, practical application or technological improvement to the technology in market for best explaining each embodiment, or lead this technology
Other those of ordinary skill in domain can understand each embodiment disclosed herein.The scope of the present invention is limited by appended claims
It is fixed.
Claims (10)
1. a kind of determination method on the boundary of area-of-interest in image characterized by comprising
Obtain the forward image of the vehicle for the electronic equipment acquisition being installed in the vehicle;
It is handled using adjacent two frame forward image of the frame difference method to the forward image, obtains binary image;
Since the first row pixel of the binary image, each row white pixel point in the binary image is successively counted
Quantity;
According to the quantity of each row white pixel point, one-row pixels point, a line picture are chosen from the binary image
Vegetarian refreshments is the row pixel that the quantity of last line white pixel point in the binary image is not 0;
According to the one-row pixels point present position in the binary image selected, determined from the forward image
The lower boundary of area-of-interest.
2. the method according to claim 1, wherein the screen of the electronic equipment show horizontal alignment line and
Vertical lubber-line, wherein the horizontal alignment line is overlapped with the horizontal center line of the screen, the vertical lubber-line with it is described
The vertical centerline of screen is overlapped, wherein
Before the forward image of the vehicle of the electronic equipment acquisition for obtaining and being installed in the vehicle, the electronic equipment
Installation requirement in vehicle includes: the horizon and the horizontal school in the forward image of the vehicle of the electronic equipment acquisition
Directrix is overlapped, the vertical centerline of the corresponding image of headstock in the forward image of the vehicle of electronic equipment acquisition with it is described
Vertical lubber-line is overlapped.
3. the method according to claim 1, wherein being opened from the first row pixel of the binary image
Begin, successively counts in the binary image before the quantity of each row white pixel point, the method also includes:
The expansion process and corrosion treatment in Morphological scale-space are successively carried out to the binary image, the two-value that obtains that treated
Change image.
4. the method according to claim 1, wherein determining the following of area-of-interest from the forward image
After boundary, the method also includes:
The fixation coboundary for obtaining setting, using the coboundary as the area-of-interest intercepted from the forward image.
5. the method according to claim 1, wherein determining the following of area-of-interest from the forward image
After boundary, the method also includes:
Obtain the preset height value of area-of-interest;
Determined according to the lower boundary of the preset height value and the area-of-interest intercept from the forward image it is interested
The coboundary in region.
6. according to the method described in claim 2, it is characterized in that, determining the following of area-of-interest from the forward image
After boundary, the method also includes:
According to the lower boundary of the lower boundary of the area-of-interest and the forward image, headstock pair in the forward image is determined
The height for the image answered;
The height of the corresponding image of the headstock is compared with preset height, obtains comparison result;
In the case where the height that the comparison result is the corresponding image of the headstock is more than the preset height, adjustment is issued
The prompt of the installation site of electronic equipment.
7. the method according to claim 1, wherein determining the lower boundary of area-of-interest from the forward image
Further include:
Based on the adjacent two frames forward image of multiple groups, last line white pixel point is chosen respectively from corresponding binary image
One-row pixels point when quantity is not 0;
One-row pixels point when quantity according to the last one each white pixel point is not 0 is locating in corresponding binary image
Position determines the lower boundary of the area-of-interest.
8. the method according to claim 1, wherein the quantity according to each row white pixel point, from
One-row pixels point is chosen in the binary image, the one-row pixels point is last line white picture in the binary image
The step of quantity of vegetarian refreshments is not 0 row pixel include:
Histogram is generated using the quantity of each row white pixel point, wherein the abscissa of the histogram represents locating for pixel
Line number, ordinate represents the quantity of the white pixel point of current line;
The histogram is handled using convex closure detection algorithm, obtains multiple convex closures, and choose the convex closure for being located at the rightmost side;
Obtain the location information for forming the point of the rightmost side of rightmost side convex closure;
One-row pixels point when determining that the quantity of white pixel point is not 0 using the location information.
9. the determining device on the boundary of area-of-interest in a kind of image, which is characterized in that described including memory and processor
Memory is for storing executable instruction;The processor for executed under the control of described instruction according to claim 1-
Method described in any one of 8.
10. a kind of electronic equipment, which is characterized in that including memory and processor, the memory is executable for storing
Instruction;The processor under the control of described instruction for executing method according to claim 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910300267.5A CN110135260A (en) | 2019-04-15 | 2019-04-15 | The determination method, apparatus and electronic equipment on the boundary of area-of-interest in image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910300267.5A CN110135260A (en) | 2019-04-15 | 2019-04-15 | The determination method, apparatus and electronic equipment on the boundary of area-of-interest in image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110135260A true CN110135260A (en) | 2019-08-16 |
Family
ID=67569950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910300267.5A Pending CN110135260A (en) | 2019-04-15 | 2019-04-15 | The determination method, apparatus and electronic equipment on the boundary of area-of-interest in image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110135260A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112631312A (en) * | 2021-03-08 | 2021-04-09 | 北京三快在线科技有限公司 | Unmanned equipment control method and device, storage medium and electronic equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104156704A (en) * | 2014-08-04 | 2014-11-19 | 胡艳艳 | Novel license plate identification method and system |
CN104915944A (en) * | 2014-03-14 | 2015-09-16 | 北京风行在线技术有限公司 | Method and device for determining black margin position information of video |
-
2019
- 2019-04-15 CN CN201910300267.5A patent/CN110135260A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104915944A (en) * | 2014-03-14 | 2015-09-16 | 北京风行在线技术有限公司 | Method and device for determining black margin position information of video |
CN104156704A (en) * | 2014-08-04 | 2014-11-19 | 胡艳艳 | Novel license plate identification method and system |
Non-Patent Citations (2)
Title |
---|
刘同焰: "车牌识别系统的相关算法研究与实现", 《中国优秀硕士学位论文全文数据库》 * |
饶云波: "夜间视频增强的关键技术研究", 《中国博士学位论文全文数据库》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112631312A (en) * | 2021-03-08 | 2021-04-09 | 北京三快在线科技有限公司 | Unmanned equipment control method and device, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109117831B (en) | Training method and device of object detection network | |
JP7110502B2 (en) | Image Background Subtraction Using Depth | |
CN107154030B (en) | Image processing method and device, electronic equipment and storage medium | |
US20230075270A1 (en) | Image processing method and apparatus, electronic device, and computer-readable storage medium | |
CN110705583B (en) | Cell detection model training method, device, computer equipment and storage medium | |
US9495601B2 (en) | Detecting and reporting improper activity involving a vehicle | |
CN110675407B (en) | Image instance segmentation method and device, electronic equipment and storage medium | |
CN111259878A (en) | Method and equipment for detecting text | |
CN108550258B (en) | Vehicle queuing length detection method and device, storage medium and electronic equipment | |
CN109118532B (en) | Visual field depth estimation method, device, equipment and storage medium | |
CN110827244A (en) | Method and equipment for detecting appearance flaws of electronic equipment | |
WO2020098506A1 (en) | Intersection state detection method and apparatus, electronic device and vehicle | |
EP3710993B1 (en) | Image segmentation using neural networks | |
CN104735435A (en) | Image processing method and electronic device | |
US11036967B2 (en) | Method and device for face selection, recognition and comparison | |
CN112257605A (en) | Three-dimensional target detection method, system and device based on self-labeling training sample | |
TW201947455A (en) | Processing method and processing equipment for vehicle damage identification, client and server | |
CN109544516B (en) | Image detection method and device | |
CN112258610B (en) | Image labeling method and device, storage medium and electronic equipment | |
CN115019273A (en) | Target detection method and device, automobile and storage medium | |
CN113033715B (en) | Target detection model training method and target vehicle detection information generation method | |
CN110135260A (en) | The determination method, apparatus and electronic equipment on the boundary of area-of-interest in image | |
CN112529006B (en) | Panoramic picture detection method, device, terminal and storage medium | |
JP7143931B2 (en) | Control method, learning device, identification device and program | |
CN114998897B (en) | Method for generating sample image and training method of character recognition model |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190816 |