CN112017170A - Road pavement pit slot identification method, device and equipment based on three-dimensional light and shadow model - Google Patents
Road pavement pit slot identification method, device and equipment based on three-dimensional light and shadow model Download PDFInfo
- Publication number
- CN112017170A CN112017170A CN202010872629.0A CN202010872629A CN112017170A CN 112017170 A CN112017170 A CN 112017170A CN 202010872629 A CN202010872629 A CN 202010872629A CN 112017170 A CN112017170 A CN 112017170A
- Authority
- CN
- China
- Prior art keywords
- projection
- road surface
- shadow
- area
- determining
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 49
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 239000002131 composite material Substances 0.000 claims description 12
- 201000010099 disease Diseases 0.000 claims description 8
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Abstract
The invention discloses a method, a device and equipment for identifying pits in a road pavement based on a three-dimensional light and shadow model, wherein the method comprises the following steps: acquiring three-dimensional image data of a road surface; setting a plurality of groups of bidirectional projection group light beams with different projection angles by using a three-dimensional light and shadow model, respectively projecting the bidirectional projection group light beams on a road surface, and then determining a road surface shadow area formed by the road surface under the projection of each bidirectional projection group light beam; determining a common road surface shadow region which is a shadow region under the projection of each two-way projection group light beam as a final road surface projection region according to the road surface shadow region formed by each two-way projection group; carrying out image connected domain analysis on the final pavement shadow area, and determining the independent and connected shadow area as a possible pavement pit area; determining the physical area and the average depth of each possible pavement pit slot; and determining pavement pit slots forming pavement defects according to the physical area and the average depth. The invention can accurately identify the road surface pit slot.
Description
Technical Field
The invention relates to the technical field of pavement detection, in particular to a method, a device and equipment for identifying pits in a road pavement based on a three-dimensional light and shadow model.
Background
The road surface pit is a serious road surface disease, which not only affects the comfort and stability of driving, but also affects the safety of driving; therefore, the method can find and repair the pits on the road surface as soon as possible in time, and has great significance for the driving safety of the road.
In recent years, machine learning, in particular, deep learning techniques have made a major breakthrough in the fields of image processing, object recognition, and the like, and are also widely used in the detection of road surface pits. However, machine learning techniques generally rely on learning samples and have a "black box" operation mechanism, and may generate abnormal, wrong, and difficult-to-interpret recognition results for unknown recognition samples, thereby resulting in inaccurate recognition of road pavement pits.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a road pavement pit recognition method, a road pavement pit recognition device and road pavement pit recognition equipment based on a three-dimensional light and shadow model, which can avoid the phenomenon that the road pavement pit cannot be accurately recognized due to the fact that learning samples are insufficient in the prior art.
According to one aspect of the invention, a method for identifying a pit in a road pavement based on a three-dimensional light and shadow model is provided, which comprises the following steps:
step 5, performing geometric measurement on the possible road surface pit area, and determining the physical area and the average depth of each possible road surface pit;
and 6, determining the pavement pit grooves forming the pavement diseases according to whether the physical area and the average depth of each possible pavement pit groove are within preset range values.
Further, let L andfor a set of bidirectional projection group beams, the step of determining a road surface shadow region formed by the road surface under the projection of each bidirectional projection group beam comprises:
step 201, determining each three-dimensional image pixel point (p) in three-dimensional image data under L projection beamx,py) Elevation value p ofzAnd maximum beam heightmax(P) determining the pixel value B (P) of the pixel point of the three-dimensional image according to the following formulax,py):
The pixel value "0" represents that the three-dimensional image pixel point is a shadow pixel, and the pixel value "1" represents that the three-dimensional image pixel point is a non-shadow pixel, so that a shadow image B formed by the road surface under the projection of the L projection light beam is determined;
step 202, also determined according to the above formulaPixel value of each three-dimensional image pixel point under projection of projection light beamThereby determining on the road surfaceShadow image formed under projection of projection light beam
Step 203, determining a composite shadow image B under the beam projection of the bidirectional projection group by using the following formulac:
Wherein, Bc(px,py) Finger composite shadow image BcAt a pixel point (p)x,py) To determine the projection directions L and LThe lower common shadow area is the road surface shadow area.
Further, in step 3, the final road surface projection area is determined according to the following formula:
in the formula, Bf(px,py) Is a final road shadow image BfAt a pixel point (p)x,py) The value of the pixel of (a) is,for composite shadow image under ith bidirectional projectionAt a pixel point (p)x,py) Pixel value of (a) according to Bf(px,py) Determines the final road projection area.
Furthermore, the projection angles of the light beams of the multiple groups of bidirectional projection groups are the same, and the horizontal rotation angles are different; the range of projection angles is (0 °,30 °).
Further, step 4 specifically includes:
carrying out image connected domain analysis on all three-dimensional image pixel points confirmed as a final shadow area of the road surface, and marking all connectable shadow area pixel points as an independent pixel group in an 8-adjacent mode; wherein a single independent pixel group is a possible pavement pit area.
Further, step 5 comprises the following substeps:
step 501, determining a pixel group forming each shadow area, counting the number of pixels in each pixel group, and calculating the physical area of each possible pavement pit area according to the physical area occupied by each pixel;
step 502, calculating an average elevation of each shadow area pixel group according to elevation information of pixels in the shadow area pixel group, and selecting a non-shadow area in a preset range in the neighborhood of the shadow area pixel group to determine the average elevation of the non-shadow area, wherein a difference value between the average elevation of the non-shadow area and the average elevation of the shadow area is an average depth of the shadow area.
According to another aspect of the present invention, there is provided a road surface pit recognition apparatus based on a three-dimensional light and shadow model, comprising:
the road surface data acquisition module is used for acquiring three-dimensional image data of a road surface;
the road surface shadow area determining module is used for setting a plurality of groups of bidirectional projection group light beams with different projection angles to be respectively projected on the road surface by utilizing the three-dimensional light and shadow model according to the three-dimensional image data of the road surface, and then determining a road surface shadow area formed by the road surface under the projection of each bidirectional projection group light beam; the bidirectional projection group light beam is two projection light beams with the same projection angle and different horizontal rotation angles, and the components of the two projection light beams on the horizontal plane are opposite to each other;
the final road surface projection area module is used for determining a common road surface shadow area which is a shadow area under the projection of each two-way projection group light beam as a final road surface projection area according to the road surface shadow area formed by each two-way projection group;
the possible road surface pit area determining module is used for carrying out image connected domain analysis on the final road surface shadow area and determining the independent and connected shadow area as the possible road surface pit area;
the geometric information determining module is used for performing geometric measurement on the possible road surface pit area and determining the physical area and the average depth of each possible road surface pit;
and the real pavement pit determining module is used for determining the pavement pits forming the pavement diseases according to whether the physical area and the average depth of each possible pavement pit are within preset range values.
According to still another aspect of the present invention, there is provided a road surface pit recognition apparatus based on a three-dimensional light and shadow model, comprising a processor and a memory; wherein the memory is used for storing a computer program; the processor is used for executing the road pavement pit recognition method based on the three-dimensional light and shadow model.
Compared with the prior art, the invention has the following advantages: based on the three-dimensional geometrical characteristics of the road surface pits, the invention firstly utilizes a three-dimensional light and shadow model to set a plurality of groups of bidirectional projection groups of light beams with different projection angles to search for pit-hole type low-lying areas on the road surface, and then discriminates the searched low-lying areas according to the physical area and the average depth, thereby identifying the road surface pits which really accord with engineering practice definition.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of an embodiment of a method for identifying a pit in a road pavement based on a three-dimensional light and shadow model according to the present invention;
FIG. 2 is a block diagram of a road surface pit recognition device based on a three-dimensional light and shadow model according to an embodiment of the present invention;
FIG. 3 is a schematic view of a single light source projection principle;
FIG. 4 is an exploded view of a point light source in the projection direction;
FIG. 5 is a schematic view of a multi-group bi-directional projection arrangement;
FIG. 6 is a schematic diagram of binary shadow image connected domain analysis;
FIG. 7 is a schematic illustration of an elevation reference area;
FIG. 8 is a flowchart of an embodiment of combining three-dimensional image data of a real road surface;
FIG. 9 is a three-dimensional image of an example of a typical pit;
fig. 10 is a diagram illustrating the final result of pit recognition in fig. 9;
fig. 11 is a block diagram of a road surface pit recognition device based on a three-dimensional light and shadow model according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Firstly, the road surface pit groove has the following obvious geometrical characteristics compared with the normal road surface area: (1) the elevation in the pit is lower than that of a normal road surface area around the pit, and the pit is a pit-type low-lying area on the road surface; (2) the pits have a certain area, and the pits with too small area may only fall off for pavement aggregates; (3) the pit groove should have a certain depth, and a too shallow pit groove may be a local uneven area only and should not be counted as a pavement defect. The embodiment of the invention provides an automatic identification method of the road pavement pit slot based on the pure three-dimensional geometric characteristics based on the geometric characteristics.
Referring to fig. 1 in particular, the method for identifying a pit in a road pavement based on a three-dimensional light and shadow model disclosed by the embodiment of the invention comprises the following steps:
step 5, performing geometric measurement on the possible road surface pit areas, and determining geometric information of each possible road surface pit, wherein the geometric information comprises the physical area and the average depth of each possible road surface pit area;
and 6, determining a real road surface pit slot according to the geometric information.
Referring to fig. 2, the embodiment of the present invention further discloses a road pavement pit recognition device based on the three-dimensional light and shadow model, which is characterized by comprising:
the road surface data acquisition module is used for acquiring three-dimensional image data of a road surface;
the road surface shadow area determining module is used for setting a plurality of groups of bidirectional projection group light beams with different projection angles to be respectively projected on the road surface by utilizing the three-dimensional light and shadow model according to the three-dimensional image data of the road surface, and then determining a road surface shadow area formed by the road surface under the projection of each bidirectional projection group light beam; the bidirectional projection group light beam is two projection light beams with the same projection angle and different horizontal rotation angles, and the components of the two projection light beams on the horizontal plane are opposite to each other;
the final road surface projection area module is used for determining a common road surface shadow area which is a shadow area under the projection of each two-way projection group light beam as a final road surface projection area according to the road surface shadow area formed by each two-way projection group;
the possible road surface pit area determining module is used for carrying out image connected domain analysis on the final road surface shadow area and determining the independent and connected shadow area as the possible road surface pit area;
the geometric information determining module is used for performing geometric measurement on the possible road surface pit area and determining the physical area and the average depth of each possible road surface pit;
and the real pavement pit determining module is used for determining the pavement pits forming the pavement diseases according to whether the physical area and the average depth of each possible pavement pit are within preset range values.
The method for identifying the road surface pit based on the three-dimensional light and shadow model takes a road surface pit identification device based on the three-dimensional light and shadow model as an execution object of the step, or takes a module in the road surface pit identification device based on the three-dimensional light and shadow model as an execution object of the step. Specifically, step 1 takes a road surface data acquisition module as an execution object of the step, step 2 takes a road surface shadow region determination module as an execution object of the step, step 3 takes a final road surface projection region module as an execution object of the step, step 4 takes a possible road surface pit region determination module as an execution object of the step, step 5 takes a geometric information determination module as an execution object of the step, and step 6 takes a real road surface pit determination module as an execution object of the step.
Specifically, the three-dimensional image data of the road surface in the step 1 can be acquired by using a three-dimensional road detection vehicle. Specifically, the three-dimensional road detection vehicle utilizes a laser line scanning imaging system to acquire road pavement three-dimensional image data, and the scanning width is set as the width of a single lane. The three-dimensional laser line scanning imaging system can intercept and store three-dimensional pavement images at fixed intervals along the advancing direction of the detection vehicle. Compared with a two-dimensional road detection vehicle, the three-dimensional road detection vehicle has the advantages of richer acquired information, small interference of light receiving line parts and the like, and is widely applied to road detection practice in recent years.
And 2, simulating the projection behavior of the point light source on the road surface by using the three-dimensional light and shadow model, and tracing the road surface shadow area projected by the simulated point light source. As shown in fig. 3, any one of the point light sources is assumed to originate from infinity, that is, each projection direction corresponds to one point light source from infinity, and the projection light beams of the point light sources are parallel light beams and are uniformly distributed on the road surface when reaching the road surface. Referring to fig. 4, the projection direction of the point light source is determined by a projection angle θ and a horizontal rotation angle ρ, where the projection angle θ is an angle between the projection beam and the xy plane (i.e., horizontal plane), and the horizontal rotation angle ρ is an angle between the projection component of the projection beam on the xy plane and the x axis.
Based on the input three-dimensional road surface image data, when a shadow area of a single point light source on a road surface is simulated by the three-dimensional light and shadow model, each three-dimensional image pixel is regarded as a starting tracing point of a light beam, and then the light beam height when the light beam reaches other image pixels is traced and calculated along the projection direction until a specific condition of stopping tracing is reached. And repeating the tracing process for all the three-dimensional image pixels by the three-dimensional light and shadow model until a corresponding tracing stopping condition is reached. Suppose that three-dimensional image pixel point P ═ Px,py,pzIs the initial tracing point of the light beam S, thenA series of beam sampling points along the projection direction L may be defined as:
in the formula, S(k)For the kth beam sampling point, Δ S is the pitch adopted on the xy plane. Since the minimum pitch between pixels is 1 due to the dispersion of image data, Δ S may be 1.
One beam spot S per sample, according to equation (1)(k)Then, the three-dimensional shadow model can enable the three-dimensional shadow model to be adjacent to a three-dimensional image pixel point on the xy planeBinding:
in the formula (I), the compound is shown in the specification,andare respectively S(k)The x-component and the y-component of (c),rounding the rounding operator.
Based on the binding principle of formula (2), light beam S is at three-dimensional image pixel pointBeam height (S, P)(k)) Therefore, it can be expressed as:
Since a single three-dimensional image pixel may be associated in the trace back of multiple beams, there may be multiple associated beam heights for a single three-dimensional image pixel. The three-dimensional shadow model only keeps recording the highest beam height at a single three-dimensional image pixel:
max(P)=max{(S1,P),(S2,P),…,(Sn,P)} (4)
in the formula (I), the compound is shown in the specification,max(P) refers to the highest beam height at the pixel point P of the three-dimensional image, (S)iAnd P) refers to the ith beam height associated with the three-dimensional image pixel point P.
All light beams starting from all the three-dimensional image pixel points are traced back according to the principle, and the highest light beam height corresponding to the updating is continuously recorded at the associated three-dimensional image pixel points. Wherein, the judgment condition for stopping tracing a certain light beam is as follows: 1) the strip of light has crossed the image boundary; 2) the height of the light beam at the pixel point of the currently associated three-dimensional image is lower than the self height of the pixel point of the currently associated three-dimensional image, namely the light beam cannot exceed the pixel point of the three-dimensional image and reach the next pixel point.
And the highest beam heightmaxAnd (P) is a key index for judging whether the three-dimensional image pixel point P is a shadow pixel point. Specifically, if the elevation value of the three-dimensional image pixel point P is lower than the highest light beam height, the three-dimensional image pixel point P is a shadow pixel point; otherwise, the three-dimensional image pixel point P is a non-shadow pixel point. In the embodiment of the present invention, a pixel value "0" indicates that the pixel is a shadow pixel, and a pixel value "1" indicates that the pixel is a non-shadow pixel. Let B be the shadow image in the projection direction L, the value of the shadow image B can be simply expressed as:
in the formula, B (p)x,py) Finger shadow image B at pixel point (p)x,py) The pixel value of (p)x,py) Also referred to the pixel coordinates of the three-dimensional image pixel P, and PzIn particular to the elevation value of a three-dimensional image pixel P.
The above formula sets forth the basic principle of shadow simulation under projection of a single point source. In order to avoid generating shadows in the slope region, the three-dimensional light and shadow model in the embodiment of the invention adopts a bidirectional projection mode, and the shadow regions under two projection directions with horizontal planes in opposite directions are simulated and calculated, so that a low-lying region is searched instead of the slope region, namely, two conjugate point light sources are considered to irradiate the road surface. Let L andtwo projection directions for bi-directional projection, i.e. L andfor a set of two-way projection sets of beams, and according to the decomposition principle shown in FIG. 4, then L andthe method has the following characteristic relationship:
it can be seen that L andthe projection angles are the same and the horizontal rotation angles are different, and the components of the projection angles and the horizontal rotation angles on the horizontal plane are opposite. Due to L andthe projection direction of the bidirectional projection can be expressed by (θ, ρ) alone. Likewise, the projection direction can be simulated by using equations (1) to (5)Shadow image of shadowThe composite shadow image B under the bidirectional projectioncCan be expressed as:
in the formula, Bc(px,py) Finger composite shadow image BcAt a pixel point (p)x,py) The pixel value of (c). It can be easily seen that the road shadow area under one group of bidirectional projection groups is the projection direction L andlower common shaded area.
Therefore, in step 2, in combination with the above, the step of determining the road surface shadow area formed by the road surface under the projection of each bidirectional projection group of light beams includes:
step 201, determining each three-dimensional image pixel point (p) in three-dimensional image data under L projection beamx,py) Elevation value p ofzAnd maximum beam heightmax(P), determining the pixel value B (P) of the pixel point of the three-dimensional image according to the formula (5)x,py) Determining a shadow image B formed by the road surface under the projection of the L projection light beam;
step 202, also according to formula (5) is determinedPixel value of each three-dimensional image pixel point under projection of projection light beamThereby determining on the road surfaceShadow image formed under projection of projection light beam
Step 203, determining a composite shadow image B projected by the bidirectional projection group light beams by using the formula (7)cTo determine the projection directions L and LThe lower common shadow area is the road surface shadow area.
The above is a determination process of a road surface shadow region formed under the projection of one set of bidirectional projection group light beams. In order to better utilize the geometrical characteristics of the road surface pits, the three-dimensional light and shadow model can trace shadow areas (or low-lying areas) under a plurality of bidirectional projection modes by setting a plurality of groups of bidirectional projection groups of light beams with different projection angles.
In one embodiment of the present invention, four bidirectional projection sets of light beams are used for projection, and the detailed arrangement is shown in fig. 5 and the following table.
Furthermore, the four sets of bidirectional projection light beams adopted in the embodiment of the present invention adopt the same projection angle, and the range of the projection angle is preferably (0 ° and 30 °).
Further, the method comprisesIn step 3, based on the composite shadow map obtained in step 2 and projected by each group of bidirectional projection groups, the embodiment of the invention calculates the final shadow image B of the road surface by using a logical and rulefNamely, according to the formula (8), selecting a common shadow area which is a shadow area under each group of bidirectional projections as a final road surface shadow area of the road surface:
in the formula, Bf(px,py) Means final road shadow image BfAt a pixel point (p)x,py) The value of the pixel of (a) is,refers to the composite shadow image under the ith bidirectional projectionAt a pixel point (p)x,py) Pixel value of (B) according tof(px,py) Determines the final road projection area.
In the embodiment of the invention, the final road shadow image BfMeanwhile, the composite projection behavior of the four bidirectional projection groups is considered, and the threshold condition for forming a shadow area is greatly improved, so that the method can effectively identify the hole-type low-lying area such as a road pit and can well avoid the error identification in the non-hole-type low-lying area. Moreover, the simulation of the point light source projection behavior by the three-dimensional light and shadow model is completely based on the three-dimensional geometric characteristics of the recognition object, so that the road pavement pit slot recognition method provided by the invention has good objectivity and stability, and the problems such as over-fitting and under-fitting and the like required by a machine learning method do not exist.
In addition, the road surface pit has very bright three-dimensional characteristics compared with a normal road surface area, so that the road surface pit automatic identification method based on pure geometric characteristics is more direct, simpler and more efficient than a machine learning method, and can also avoid various abnormal machine misjudgment or missed judgment cases caused by insufficient learning samples.
Further, step 4 specifically includes: carrying out image connected domain analysis on all three-dimensional image pixel points confirmed as a final shadow area of the road surface, and marking all connectable shadow area pixel points as an independent pixel group in an 8-adjacent mode; wherein a single independent pixel group is a possible pavement pit area.
By adopting a general image processing technology, the final shadow image B of the road surface is processed in an 8-adjacent modefPerforming binary image connected domain analysis, and classifying the pixel groups connected into groups into pixel groups with independent marks in sequence, specifically referring to fig. 6; the single independent pixel group is an independent road surface depression area and is also regarded as a possible road surface depression area.
Further, step 5 comprises the following substeps:
step 501, determining a pixel group forming each shadow area, counting the number of pixels in each pixel group, and calculating the physical area of each possible pavement pit area according to the physical area occupied by each pixel;
step 502, calculating an average elevation of each shadow area pixel group according to elevation information of pixels in the shadow area pixel group, and selecting a non-shadow area in a preset range in the neighborhood of the shadow area pixel group to determine the average elevation of the non-shadow area, wherein a difference value between the average elevation of the non-shadow area and the average elevation of the shadow area is an average depth of the shadow area.
In the embodiment of the present invention, based on the independent shadow pixel groups marked in step 4, each independent shadow pixel group is regarded as a possible pavement pit area, and the physical area and the average depth thereof are calculated.
Specifically, in step 501, the ith independently shaded pixel group TiCan be calculated as follows:
A(Ti)=Δα·ni (9)
in the formula, A (T)i) As a group of independently shaded pixels TiΔ α is the data accuracy of the input three-dimensional road surface image (i.e. the physical area occupied by a single pixel, e.g. 1mm or 2mm), niFinger independent shadow pixel group TiThe number of pixels.
Specifically, in step 502, for calculating the average depth, the average elevation of the entire shadow pixel group is calculated according to the elevation information of each independent shadow pixel group; and selecting a non-shadow area in a certain range in the neighborhood of the shadow pixel group as a reference, and calculating the average elevation of the non-shadow area. The difference between the average elevation of the non-shaded area and the average elevation of the shaded area is the average depth of the shaded area. As shown in FIG. 7, the dotted line frame is assumed to surround the independent shadow pixel group TiThe extended rectangular field can be obtained along the extension distance r of the minimum rectangular frame, and the extended rectangular field is the calculation of the independent shadow pixel group TiAn elevation reference area at an average depth. In the embodiment of the present invention, the recommended reference range of the extension distance r is: r is more than or equal to 10cm and less than or equal to 25 cm. Let omegaiIs the set of all non-shadow pixels in the elevation reference region, then the independent shadow pixel group TiThe average depth of (d) can be calculated as follows:
in the formula, D (T)i) Finger independent shadow pixel group TiThe average depth of the optical fiber,finger independent shadow pixel group TiThe average elevation of the air flow in the air flow,all non-shaded pixel groups omega in the reference area of the finger-corresponding elevationiAverage elevation of.
Further, in step 6, forIn the physical area A (T)i) Too small or average depth D (T)i) The present invention excludes shadow areas that are too shallow, and therefore the present invention determines the actual pavement pit according to whether the physical area and the average depth of each individual shadow pixel group are within predetermined range values. In actual engineering practice, a pit with a too small physical area may only fall off pavement aggregates, and a pit with a too shallow physical area may only be a local uneven area and should not be counted as a pavement disease, so that a real pavement pit is finally determined. Therefore, the final distinguishing condition of the pavement pit groove which constitutes the pavement disease and is identified by the invention can be expressed as follows:
in the formula, AminFor minimum definition of the area of the pit, DminFor minimum defined depth, T, of the pit i0 denotes the independently shaded pixel group TiIs a pit in the road surface, T i1 denotes an independently shaded pixel group TiNot a road pit. Wherein A isminAnd DminThe values of the method need to be considered by referring to the industry standard and combining with the engineering practical experience, and the values recommended by the invention are as follows: minimum defined area A of pitmin=25cm2Minimum defined depth D of pitmin=15mm。
As shown in fig. 8, the three-dimensional image data of the road surface of the real road is combined to illustrate the specific implementation flow of the present invention in detail. The present invention is further described below with reference to fig. 9 and 10, but the embodiments of the present invention are not limited thereto.
As shown in fig. 9, the three-dimensional image data of 4 real road surfaces includes a plurality of road surface pit grooves of different sizes and different depths. The pavement pit slots in fig. 9 are identified below with reference to the same model parameters, wherein the light and shadow model parameters are as follows:
the 4 example patterns in fig. 9 are recognized based on the unified model parameters, and the final pit recognition result shown in fig. 10 can be obtained. In fig. 10, the dark shaded area on the road surface is the finally recognized pit area. It can be seen that some small pits are not identified as pit regions because the area is too small or the average depth is too shallow, but other pit regions whose area or average depth satisfies the formula (11) can be effectively identified by the method of the present invention.
In addition, as shown in fig. 11, an embodiment of the present invention further provides a road surface pit recognition apparatus based on a three-dimensional light and shadow model, including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the above-mentioned road pavement pit recognition method based on the three-dimensional light and shadow model.
Where the memory and processor are connected by a bus, the bus may comprise any number of interconnected buses and bridges, the buses connecting together one or more of the various circuits of the processor and the memory. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver may be one element or a plurality of elements, such as a plurality of receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. The data processed by the processor is transmitted over a wireless medium via an antenna, which further receives the data and transmits the data to the processor.
The processor is responsible for managing the bus and general processing and may also provide various functions including timing, peripheral interfaces, voltage regulation, power management, and other control functions. And the memory may be used to store data used by the processor in performing operations.
In summary, based on the three-dimensional geometrical characteristics of the road surface pits, the invention firstly uses the three-dimensional light and shadow model to set a plurality of groups of bidirectional projection groups with different projection angles to search for pit-hole type low-lying areas on the road surface, and then discriminates the searched low-lying areas according to the physical area and the average depth, thereby identifying the road surface pits which really accord with the engineering practice definition.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. A road pavement pit slot identification method based on a three-dimensional light and shadow model is characterized by comprising the following steps:
step 1, acquiring three-dimensional image data of a road surface;
step 2, according to three-dimensional image data of the road surface, setting a plurality of groups of bidirectional projection group light beams with different projection angles by using a three-dimensional light and shadow model to be respectively projected on the road surface, and then determining a road surface shadow area formed by the road surface under the projection of each bidirectional projection group light beam; the bidirectional projection group light beam is two projection light beams with the same projection angle and different horizontal rotation angles, and the components of the two projection light beams on the horizontal plane are opposite to each other;
step 3, determining a common road surface shadow area which is a shadow area under the projection of each two-way projection group light beam as a final road surface projection area according to the road surface shadow area formed by each two-way projection group;
step 4, carrying out image connected domain analysis on the final pavement shadow area, and determining the independent and connected shadow area as a possible pavement pit area;
step 5, performing geometric measurement on the possible road surface pit area, and determining the physical area and the average depth of each possible road surface pit;
and 6, determining the pavement pit grooves forming the pavement diseases according to whether the physical area and the average depth of each possible pavement pit groove are within preset range values.
2. The method for identifying the pits in the road surface based on the three-dimensional light and shadow model as claimed in claim 1, wherein L and L areFor a set of bidirectional projection group beams, the step of determining a road surface shadow region formed by the road surface under the projection of each bidirectional projection group beam comprises:
step 201, determining each three-dimensional image pixel point (p) in three-dimensional image data under L projection beamx,py) Elevation value p ofzAnd maximum beam heightmax(P) determining the pixel value B (P) of the pixel point of the three-dimensional image according to the following formulax,py):
The pixel value "0" represents that the three-dimensional image pixel point is a shadow pixel, and the pixel value "1" represents that the three-dimensional image pixel point is a non-shadow pixel, so that a shadow image B formed by the road surface under the projection of the L projection light beam is determined;
step 202, also determined according to the above formulaPixel value of each three-dimensional image pixel point under projection of projection light beamThereby determining on the road surfaceShadow image formed under projection of projection light beam
Step 203, determining a composite shadow image B under the beam projection of the bidirectional projection group by using the following formulac:
3. The method for identifying the pits in the road surface based on the three-dimensional light and shadow model as claimed in claim 1, wherein in step 3, the final road surface projection area is determined according to the following formula:
4. The method for identifying the pits on the road surface based on the three-dimensional light and shadow model as claimed in claim 1, wherein the projection angles of the light beams of the plurality of bidirectional projection sets are the same, and the horizontal rotation angles are different; the range of projection angles is (0 °,30 °).
5. The method for identifying the pits in the road pavement based on the three-dimensional light and shadow model as claimed in claim 1, wherein the step 4 specifically comprises:
carrying out image connected domain analysis on all three-dimensional image pixel points confirmed as a final shadow area of the road surface, and marking all connectable shadow area pixel points as an independent pixel group in an 8-adjacent mode; wherein a single independent pixel group is a possible pavement pit area.
6. The method for identifying the pits in the road pavement based on the three-dimensional light and shadow model as claimed in claim 1, wherein the step 5 comprises the following substeps:
step 501, determining a pixel group forming each shadow area, counting the number of pixels in each pixel group, and calculating the physical area of each possible pavement pit area according to the physical area occupied by each pixel;
step 502, calculating an average elevation of each shadow area pixel group according to elevation information of pixels in the shadow area pixel group, and selecting a non-shadow area in a preset range in the neighborhood of the shadow area pixel group to determine the average elevation of the non-shadow area, wherein a difference value between the average elevation of the non-shadow area and the average elevation of the shadow area is an average depth of the shadow area.
7. A road pavement pit recognition device based on three-dimensional light and shadow model is characterized by comprising:
the road surface data acquisition module is used for acquiring three-dimensional image data of a road surface;
the road surface shadow area determining module is used for setting a plurality of groups of bidirectional projection group light beams with different projection angles to be respectively projected on the road surface by utilizing the three-dimensional light and shadow model according to the three-dimensional image data of the road surface, and then determining a road surface shadow area formed by the road surface under the projection of each bidirectional projection group light beam; the bidirectional projection group light beam is two projection light beams with the same projection angle and different horizontal rotation angles, and the components of the two projection light beams on the horizontal plane are opposite to each other;
the final road surface projection area module is used for determining a common road surface shadow area which is a shadow area under the projection of each two-way projection group light beam as a final road surface projection area according to the road surface shadow area formed by each two-way projection group;
the possible road surface pit area determining module is used for carrying out image connected domain analysis on the final road surface shadow area and determining the independent and connected shadow area as the possible road surface pit area;
the geometric information determining module is used for performing geometric measurement on the possible road surface pit area and determining the physical area and the average depth of each possible road surface pit;
and the real pavement pit determining module is used for determining the pavement pits forming the pavement diseases according to whether the physical area and the average depth of each possible pavement pit are within preset range values.
8. A road pavement pit slot recognition device based on a three-dimensional light and shadow model is characterized by comprising a processor and a memory; wherein the memory is used for storing a computer program; the processor is used for executing the computer program to realize the method for identifying the road pavement pit based on the three-dimensional light and shadow model according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010872629.0A CN112017170A (en) | 2020-08-26 | 2020-08-26 | Road pavement pit slot identification method, device and equipment based on three-dimensional light and shadow model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010872629.0A CN112017170A (en) | 2020-08-26 | 2020-08-26 | Road pavement pit slot identification method, device and equipment based on three-dimensional light and shadow model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112017170A true CN112017170A (en) | 2020-12-01 |
Family
ID=73503297
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010872629.0A Pending CN112017170A (en) | 2020-08-26 | 2020-08-26 | Road pavement pit slot identification method, device and equipment based on three-dimensional light and shadow model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112017170A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112444490A (en) * | 2021-02-01 | 2021-03-05 | 深圳宜美智科技股份有限公司 | Hole plugging defect detection method based on image detection and hole plugging defect detection equipment |
CN115424232A (en) * | 2022-11-04 | 2022-12-02 | 深圳市城市交通规划设计研究中心股份有限公司 | Method for identifying and evaluating pavement pit, electronic equipment and storage medium |
CN115830032A (en) * | 2023-02-13 | 2023-03-21 | 杭州闪马智擎科技有限公司 | Road expansion joint lesion identification method and device based on old facilities |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005033682A1 (en) * | 2003-10-02 | 2005-04-14 | Daimlerchrysler Ag | Three-dimensional reconstruction of surface profiles |
CN106023226A (en) * | 2016-05-31 | 2016-10-12 | 彭博 | Crack automatic detection method based on three-dimensional virtual pavement |
KR101785205B1 (en) * | 2016-05-17 | 2017-10-18 | 한국과학기술원 | Method and Apparatus for Multi-object Segmentation based on Shadow using Depth Sensor |
CN110414418A (en) * | 2019-07-25 | 2019-11-05 | 电子科技大学 | A kind of Approach for road detection of image-lidar image data Multiscale Fusion |
-
2020
- 2020-08-26 CN CN202010872629.0A patent/CN112017170A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005033682A1 (en) * | 2003-10-02 | 2005-04-14 | Daimlerchrysler Ag | Three-dimensional reconstruction of surface profiles |
KR101785205B1 (en) * | 2016-05-17 | 2017-10-18 | 한국과학기술원 | Method and Apparatus for Multi-object Segmentation based on Shadow using Depth Sensor |
CN106023226A (en) * | 2016-05-31 | 2016-10-12 | 彭博 | Crack automatic detection method based on three-dimensional virtual pavement |
CN110414418A (en) * | 2019-07-25 | 2019-11-05 | 电子科技大学 | A kind of Approach for road detection of image-lidar image data Multiscale Fusion |
Non-Patent Citations (2)
Title |
---|
周慧媛;邱书波;刘海英;马宏伟;: "基于对比度受限自适应直方图多种路面裂缝检测与识别", 齐鲁工业大学学报, no. 05 * |
张立华;朱庆;暴景阳;徐胜华;: "一种基于数字伴潮海岸线的潮滩淹没区仿真算法", 武汉大学学报(信息科学版), no. 07 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112444490A (en) * | 2021-02-01 | 2021-03-05 | 深圳宜美智科技股份有限公司 | Hole plugging defect detection method based on image detection and hole plugging defect detection equipment |
CN112444490B (en) * | 2021-02-01 | 2021-04-16 | 深圳宜美智科技股份有限公司 | Hole plugging defect detection method based on image detection and hole plugging defect detection equipment |
CN115424232A (en) * | 2022-11-04 | 2022-12-02 | 深圳市城市交通规划设计研究中心股份有限公司 | Method for identifying and evaluating pavement pit, electronic equipment and storage medium |
CN115830032A (en) * | 2023-02-13 | 2023-03-21 | 杭州闪马智擎科技有限公司 | Road expansion joint lesion identification method and device based on old facilities |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112017170A (en) | Road pavement pit slot identification method, device and equipment based on three-dimensional light and shadow model | |
CN101498592B (en) | Reading method and apparatus for pointer instrument | |
US8422759B2 (en) | Image processing method and image processing device | |
EP1890264B1 (en) | Vehicle, image processing system, image processing method, image processing program, image processing system configuration method, and server | |
CN111863645B (en) | Machining process parameter determination method and device, storage medium and electronic equipment | |
CN105023010A (en) | Face living body detection method and system | |
CN104899609B (en) | A kind of mechanical meter recognition methods based on image registration | |
CN110288032A (en) | A kind of vehicle driving trace type detection method and device | |
CN105006003A (en) | Random projection fern based real-time target tracking algorithm | |
US10235576B2 (en) | Analysis method of lane stripe images, image analysis device, and non-transitory computer readable medium thereof | |
CN107345789A (en) | A kind of pcb board hole location detecting device and method | |
CN104778465A (en) | Target tracking method based on feature point matching | |
CN110967014A (en) | Method for indoor navigation and equipment tracking of machine room based on augmented reality technology | |
CN105354816B (en) | A kind of electronic units fix method and device | |
CN109934851A (en) | A kind of mask method, device and machine readable storage medium | |
CN109190616A (en) | A kind of online Vision Tracking of hot rolled steel plate based on feature identification | |
CN106529548A (en) | Sub-pixel level multi-scale Harris corner point detection algorithm | |
CN107886541A (en) | Monocular movement object pose method for real-time measurement based on back projection method | |
CN112902869B (en) | Method and device for adjusting laser plane of rail profile measuring system | |
CN103150558A (en) | Machine vision-based display terminal operation response matching detection method | |
CN112434583B (en) | Lane transverse deceleration marking line detection method and system, electronic equipment and storage medium | |
CN206019585U (en) | Rail Abrasion Detection System system | |
CN114913175A (en) | Speckle image quality evaluation method, electronic device, and storage medium | |
Jiao et al. | Lce-calib: automatic lidar-frame/event camera extrinsic calibration with a globally optimal solution | |
CN110909569B (en) | Road condition information identification method and terminal equipment |
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 |