CN106846341B - Method and device for determining point cloud area growth threshold of complex outer plate of ship body - Google Patents
Method and device for determining point cloud area growth threshold of complex outer plate of ship body Download PDFInfo
- Publication number
- CN106846341B CN106846341B CN201710090974.7A CN201710090974A CN106846341B CN 106846341 B CN106846341 B CN 106846341B CN 201710090974 A CN201710090974 A CN 201710090974A CN 106846341 B CN106846341 B CN 106846341B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- area data
- data
- probability
- gray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method and a device for determining a growth threshold of a point cloud area of a complex outer plate of a ship body, which are used for solving the technical problem that a method for determining the growth threshold of the point cloud area of the complex outer plate of the ship body, which has high reasoning speed, good generalization capability and accurate reasoning result, is still lacked at present. The method provided by the embodiment of the invention comprises the following steps: extracting the gray scale of the point cloud area data of the complex hull planking; calculating the probability of each gray scale, and dividing the point cloud area data into background area data and target area data according to the probability of each gray scale; and obtaining a maximum solution meeting the inter-class variance of the background area data and the target area data by a sliding window method, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull planking.
Description
Technical Field
The invention relates to the field of hull plate processing, in particular to a method and a device for determining a point cloud area growth threshold of a complex hull plate.
Background
The line heating plate is a hull complex outer plate processing and forming process commonly adopted by shipyards at home and abroad. The process has the advantages of large technical difficulty, multiple influence factors and large difficulty of operation skills, and in order to get rid of the situation and realize accurate extraction of the board point cloud data in the process of the process, a point cloud data region growth threshold value determining and calculating method is needed in the process of realizing accurate extraction of a point cloud target, and is used for improving the precision of extracting the target region from the point cloud data.
Although domestic and foreign research institutions propose some methods for determining threshold values, mainly including point-based global threshold value methods, region-based global threshold value methods, local threshold value methods and the like, for determining the growth threshold values of the cloud region of the hull complex outer plate, the methods are some general threshold value determination methods, cannot ensure extraction accuracy when applied to determining the growth threshold values of the cloud region of the hull complex outer plate, cannot be flexibly adjusted according to an extraction target, are high in algorithm time complexity, and are slow in function convergence along with increase of cloud data volume.
Therefore, a method for determining the growth threshold of the complex hull plate point cloud area with high reasoning speed, good generalization capability and accurate reasoning result is still lacking at present.
Disclosure of Invention
The embodiment of the invention provides a method and a device for determining a growth threshold of a point cloud area of a complex outer plate of a ship body, and solves the technical problem that the method for determining the growth threshold of the point cloud area of the complex outer plate of the ship body, which has high reasoning speed, good generalization capability and accurate reasoning result, is still lacked at present.
The method for determining the point cloud area growth threshold of the complex outer plate of the ship body provided by the embodiment of the invention comprises the following steps:
extracting the gray scale of the point cloud area data of the complex hull planking;
calculating the probability of each gray scale, and dividing the point cloud area data into background area data and target area data according to the probability of each gray scale;
and obtaining a maximum solution meeting the inter-class variance of the background area data and the target area data by a sliding window method, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull planking.
Preferably, extracting the gray scale of the point cloud area data of the hull complex planking comprises:
and acquiring point cloud area data of the complex hull planking, and dividing the point cloud area data into L levels according to the gray value of the point cloud area data, wherein the L levels can be adjusted according to the growth threshold extraction precision of the point cloud area of the complex hull planking.
Preferably, the calculating the probability of occurrence of each gray scale and the dividing the point cloud area data into background area data and target area data according to the probability of occurrence of each gray scale comprises:
calculating the occurrence probability of each gray scale, and calculating the total gray average value u of the point cloud area data according to the occurrence probability of each gray scale;
and dividing the point cloud area data into background area data and target area data according to any gray level value k in the gray level set of the point cloud area data, wherein the initial value of the gray level value k is the minimum gray level.
Preferably, obtaining a maximum solution satisfying the inter-class variance of the background area data and the target area data by a sliding window method, and using the maximum solution as a growth threshold of the point cloud area of the complex hull planking comprises:
calculating the probability w of the occurrence of the background region data0And the mean gray value u0And the probability w of the occurrence of target region data1And the mean gray value u1；
Obtaining the inter-class variance of the background area data and the target area data according to a preset first formula, adjusting the gray level value k by a sliding window method, finding out the maximum solution meeting the inter-class variance of the background area data and the target area data, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull planking, wherein the preset first formula is as follows:
H2(k)＝w0(u-u0)2+w1(u-u1)2；
wherein H2Is the inter-class variance, w, of the background region data and the target region data0Is the probability of occurrence of background region data, u is the average value of the overall gray scale of point cloud region data, u0Is the mean gray value of the background region data, w1Is the probability of occurrence of data of the target area, u1For the data of the target areaAverage gray value.
Preferably, before adjusting the gray level value k by a sliding window method and finding a maximum solution satisfying the inter-class variance of the background region data and the target region data, the method comprises:
determining a feasible solution space G, and determining the size of the sliding window by presetting a second formula, wherein the preset second formula is as follows:
L1＝pG；
wherein L is1For the size of the sliding window, p is the adjustable factor, p is greater than 0 and less than or equal to 1, G is the pixel level length, and G is {0,1, …, L-1 }.
Preferably, adjusting the gray level value k by a sliding window method and finding a maximum solution satisfying the inter-class variance of the background region data and the target region data includes:
randomly generating perturbations k within a sliding window1And judging the disturbance k1Whether a preset third formula is satisfied, if so, enabling a disturbance k1Is in an initial state, otherwise, whether the state is accepted is judged according to the Metroplis criterion, and if the state is accepted, H is added2(k0) Stack S, H2(k1) Changing to an initial state, otherwise, continuing to randomly generate disturbance;
and judging whether the disturbance process is terminated according to a convergence criterion, if so, traversing the stack S, reserving the maximum solution, outputting the maximum solution when judging that the sliding window slides all gray levels, and otherwise, randomly generating disturbance again.
The invention provides a device for determining a point cloud area growth threshold of a complex hull plate, which comprises:
the extraction module is used for extracting the gray level of the point cloud area data of the complex hull planking;
the first calculation module is used for calculating the probability of each gray scale and dividing the point cloud area data into background area data and target area data according to the probability of each gray scale;
and the second calculation module is used for obtaining a maximum solution meeting the inter-class variance of the background area data and the target area data through a sliding window method, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull planking.
Preferably, the extraction module comprises:
the first dividing unit is used for acquiring point cloud area data of the complex hull planking, dividing the point cloud area data into L levels according to the gray value of the point cloud area data, and adjusting the L levels according to the growth threshold extraction precision of the point cloud area of the complex hull planking.
Preferably, the first calculation module comprises:
the first calculating unit is used for calculating the occurrence probability of each gray scale and calculating the overall gray scale average value u of the point cloud area data according to the occurrence probability of each gray scale;
and the second dividing unit is used for dividing the point cloud area data into background area data and target area data according to any gray level value k in the gray level set of the point cloud area data, and the initial value of the gray level value k is the minimum gray level.
Preferably, the second calculation module comprises:
a second calculation unit for calculating the probability w of occurrence of the background region data0And the mean gray value u0And the probability w of the occurrence of target region data1And the mean gray value u1；
The adjusting unit is used for obtaining the inter-class variance of the background area data and the target area data according to a preset first formula, adjusting the gray level value k through a sliding window method, finding a maximum solution meeting the inter-class variance of the background area data and the target area data, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull planking, wherein the preset first formula is as follows:
H2(k)＝w0(u-u0)2+w1(u-u1)2；
wherein H2Is the inter-class variance, w, of the background region data and the target region data0Is the probability of occurrence of background region data, u is the average value of the overall gray scale of point cloud region data, u0For the data of background areaMean gray value, w1Is the probability of occurrence of data of the target area, u1Is the average gray value of the target area data.
According to the technical scheme, the embodiment of the invention has the following advantages:
the embodiment of the invention provides a method and a device for determining a point cloud area growth threshold of a complex outer plate of a ship body, wherein the method comprises the following steps: extracting the gray scale of the point cloud area data of the complex hull planking; calculating the probability of each gray scale, and dividing the point cloud area data into background area data and target area data according to the probability of each gray scale; the method comprises the steps of obtaining a maximum solution meeting the inter-class variance of background area data and target area data through a sliding window method, and taking the maximum solution as a growth threshold of a point cloud area of a complex hull outer plate.
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 inventive exercise.
Fig. 1 is a schematic flowchart of an embodiment of a method for determining a point cloud area growth threshold of a complex hull planking point cloud provided by an embodiment of the invention;
fig. 2 is a schematic flowchart of another embodiment of a method for determining a point cloud area growing threshold of a complex hull planking point cloud provided by an embodiment of the present invention;
fig. 3 is a schematic flow chart of a process for determining a point cloud area growth threshold of a complex hull planking point cloud according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a device for determining a point cloud area growth threshold of a complex hull planking point cloud provided by an embodiment of the invention.
Detailed Description
The embodiment of the invention provides a method and a device for determining a growth threshold of a point cloud area of a complex outer plate of a ship body, which are used for solving the technical problem that the method for determining the growth threshold of the point cloud area of the complex outer plate of the ship body, which has high reasoning speed, good generalization capability and accurate reasoning result, is still lacked at present.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a method for determining a point cloud area growth threshold of a complex hull planking point cloud provided by an embodiment of the invention includes:
101. extracting the gray scale of the point cloud area data of the complex hull planking;
firstly, extracting the point cloud area data of the complex hull planking according to the gray scale, namely dividing the point cloud area data of the complex hull planking according to the gray scale.
102. Calculating the probability of each gray scale, and dividing the point cloud area data into background area data and target area data according to the probability of each gray scale;
and then, calculating the probability of each gray scale in the point cloud area data of the complex hull planking, and dividing the point cloud area data into background area data and target area data according to the probability of each gray scale.
103. And obtaining a maximum solution meeting the inter-class variance of the background area data and the target area data by a sliding window method, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull planking.
And finally, obtaining a maximum solution meeting the inter-class variance of the background area data and the target area data by a sliding window method, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull planking.
In order to describe the detailed description of the method for determining the point cloud area growth threshold of the complex hull plate point cloud provided by the embodiment of the invention, another embodiment of the method for determining the point cloud area growth threshold of the complex hull plate point cloud provided by the embodiment of the invention is described in detail below.
Referring to fig. 2, another embodiment of the method for determining the growth threshold of the point cloud area of the complex hull plate point cloud provided by the embodiment of the invention includes:
201. acquiring point cloud area data of the complex hull planking, and dividing the point cloud area data into L levels according to the gray value of the point cloud area data, wherein the L levels can be adjusted according to the growth threshold extraction precision of the point cloud area of the complex hull planking;
firstly, point cloud area data M of a complex hull planking are obtained, the point cloud area data are divided into L levels according to the gray value of the point cloud area data, the L levels can be adjusted according to the growing threshold extraction precision of the point cloud area of the complex hull planking, and the larger the L is, the higher the threshold extraction precision is.
202. Calculating the occurrence probability of each gray scale, and calculating the total gray average value u of the point cloud area data according to the occurrence probability of each gray scale;
then, the probability of occurrence of each gray level i is calculated, and the overall gray level average value u of the point cloud area data is calculated according to the probability of occurrence of each gray level i.
203. Dividing the point cloud area data into background area data and target area data according to any gray level value k in the gray level set of the point cloud area data, wherein the initial value of the gray level value k is the minimum gray level;
dividing the point cloud area data into background area data C according to any gray level value k in the gray level set of the point cloud area data0And target area data C1The initial value of the gray level value k is the minimum gray level, so that the point cloud data can be divided into two different types of data according to different k values.
204. Calculating the probability w of the occurrence of the background region data0And the mean gray value u0And the probability w of the occurrence of target region data1And the mean gray value u1；
Dividing point cloud area data into background area data C0And target area data C1Then, the probability w of the occurrence of the background region data is calculated0And the mean gray value u0And the probability w of the occurrence of target region data1And the mean gray value u1。
205. Obtaining the inter-class variance of the background area data and the target area data according to a preset first formula, wherein the preset first formula is as follows:
H2(k)＝w0(u-u0)2+w1(u-u1)2；
wherein H2Is the inter-class variance, w, of the background region data and the target region data0Is the probability of occurrence of background region data, u is the average value of the overall gray scale of point cloud region data, u0Is the mean gray value of the background region data, w1Is the probability of occurrence of data of the target area, u1Is the average gray value of the target area data. (ii) a
Then, the background area data C can be obtained according to a preset first formula0And target area data C1Inter-class variance of (2).
206. Determining a feasible solution space G, and determining the size of the sliding window by presetting a second formula, wherein the preset second formula is as follows:
L1＝pG；
wherein L is1Is the size of the sliding windowP is an adjustable factor, p is more than 0 and less than or equal to 1, G is the pixel level length, and G is {0,1, …, L-1 }.
Before the gray level value k is adjusted by a sliding window method, a space G of feasible solutions needs to be determined, and the size of a sliding window is determined by presetting a second formula.
207. Randomly generating perturbations k within a sliding window1And judging the disturbance k1Whether a preset third formula is satisfied, if so, enabling a disturbance k1Is in an initial state, otherwise, whether the state is accepted is judged according to the Metroplis criterion, and if the state is accepted, H is added2(k0) Stack S, H2(k1) Changing to an initial state, otherwise, continuing to randomly generate disturbance;
then, randomly generating a perturbation k within a sliding window1And judging the disturbance k1Whether a preset third formula is satisfied, if so, enabling a disturbance k1Is in an initial state, otherwise, whether the state is accepted is judged according to the Metroplis criterion, and if the state is accepted, H is added2(k0) Stack S, H2(k1) And changing to an initial state, otherwise, continuing to randomly generate disturbance.
208. And judging whether the disturbance process is terminated according to a convergence criterion, if so, traversing the stack S, reserving the maximum solution, outputting the maximum solution when judging that the sliding window slides all gray levels, and otherwise, randomly generating disturbance again.
And finally, judging whether the disturbance process is terminated according to a convergence criterion, if so, traversing the stack S, reserving the maximum solution, outputting the maximum solution when judging that the sliding window slides all gray levels, and otherwise, randomly generating disturbance again.
In the above, for the detailed description of another embodiment of the method for determining the point cloud area growth threshold of the complex hull outer plate, which is provided by the embodiment of the present invention, for the convenience of understanding, the following will describe in detail a specific process for determining the point cloud area growth threshold of the complex hull outer plate.
Referring to fig. 3, a flow of a process for determining a point cloud region growing threshold of a complex hull planking point cloud according to an embodiment of the present inventionSchematic diagram of the process. 1) Inputting a point cloud data set M, dividing M into L levels with G ═ {0,1, …, L-1} according to gray level, wherein the gray value corresponding to the pixel on the point (x, y, z) is f (x, y, z), the number of the pixels with the gray level i is niTotal number of pixels
2) Normalizing the gray level histogram, and calculating the probability of the occurrence of the gray level i as pi＝ni/M, wherein pi≥0，
Calculating the average value of the overall gray scale of the point cloud data
3) For any gray value k in G, dividing the image gray into (C)0，C1) Two types, including pixels with gray levels within |0, 1, …, k | and within | k +1, k +2, …, L-1|, respectively, corresponding to the image background and the target object, respectively; 4) calculating C0Corresponding probability of
C1Corresponding probability w1＝1-w0(ii) a Then there is
5) Note C0Has an average gray value of u, C1Has an average gray value of u1Then there is
6) Calculating the between-class variance of the background and the target object as follows: h2(k)＝w0w1(u1-u)2＝w0(u-u0)2+w1(u-u1)2(ii) a 7) Determining an optimization function H2(k)＝w0(u-u0)2+w1(u-u1)2G (k) is a state generating function, and the space of feasible solutions is G ═ 0,1, …, L-1, and the initial state k is0Taking the minimum pixel level, wherein the size of a sliding window is L ═ pG, p is more than 0 and less than or equal to 1, G is the length of the pixel level, and p is an adjustable factor; 8) randomly generating a perturbation G (k) k in G1Calculating H2(k)＝w0(u-u0)2+w1(u-u1)2(ii) a 9) Determine whether the acceptance function accepts, i.e., satisfies H2(k1)>H2(k0) If the acceptance condition is satisfied, let k1And if the state is the initial state, judging whether to accept the state according to the Metroplis criterion. If so, H2(k0) Stack S, H2(k1) Is in an initial state; 10) according to convergence criterion j>(1-m) L judges whether the disturbance process is terminated, wherein j is the number of times of disturbance generated currently, m is an adjustable factor, and different extraction accuracies can be obtained by adjusting the size of m. If the termination condition is not met, executing step 8; 11) traverse stack S, retain the largest solution H therein2(k) Judging whether the sliding window slides over all the gray levels, if so, continuing to execute the step 8 on the gray level G; 12) outputting element H reserved in stack S2(k0)，H2(k0) Corresponding k0The value is the threshold t.
Fig. 4 is a schematic structural diagram of a device for determining a point cloud area growth threshold of a complex hull planking in accordance with an embodiment of the present invention.
The extraction module 301 is used for extracting the gray scale of the point cloud area data of the complex hull planking; the extraction module comprises:
the first dividing unit 3011 is configured to obtain point cloud area data of the complex hull planking, and divide the point cloud area data into L levels according to a gray value of the point cloud area data, where the L levels may be adjusted according to a growth threshold extraction precision of the point cloud area of the complex hull planking.
A first calculating module 302, configured to calculate a probability of occurrence of each gray scale, and divide the point cloud area data into background area data and target area data according to the probability of occurrence of each gray scale; the first calculation module includes:
a first calculating unit 3021 for calculating a probability of occurrence of each gray level and calculating an overall gray average value u of the point cloud area data according to the probability of occurrence of each gray level;
a second dividing unit 3022, configured to divide the point cloud area data into background area data and target area data according to any gray scale value k in the gray scale set of the point cloud area data, where an initial value of the gray scale value k is a minimum gray scale.
The second calculation module 303 is configured to obtain a maximum solution that satisfies the inter-class variance of the background region data and the target region data by using a sliding window method, and use the maximum solution as a growth threshold of a point cloud region of the complex hull planking; the second calculation module includes:
a second calculating unit 3031 for calculating the probability w of occurrence of the background region data0And the mean gray value u0And the probability w of the occurrence of target region data1And the mean gray value u1；
An adjusting unit 3032, configured to obtain the inter-class variance between the background region data and the target region data according to a preset first formula, adjust the gray level value k by using a sliding window method, find a maximum solution that satisfies the inter-class variance between the background region data and the target region data, and use the maximum solution as a growth threshold of the point cloud region of the complex hull planking, where the preset first formula is:
H2(k)＝w0(u-u0)2+w1(u-u1)2；
wherein H2Is the inter-class variance, w, of the background region data and the target region data0Is the probability of occurrence of background region data, u is the average value of the overall gray scale of point cloud region data, u0Is the mean gray value of the background region data, w1Is the probability of occurrence of data of the target area, u1Is the average gray value of the target area data.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (5)
1. A method for determining a point cloud area growth threshold of a complex hull plate point comprises the following steps:
extracting the gray scale of the point cloud area data of the complex hull planking;
calculating the probability of each gray scale, and dividing the point cloud area data into background area data and target area data according to the probability of each gray scale;
obtaining a maximum solution meeting the inter-class variance of the background area data and the target area data by a sliding window method, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull planking;
the calculating the probability of occurrence of each gray scale and dividing the point cloud area data into background area data and target area data according to the probability of occurrence of each gray scale comprises:
calculating the probability of each gray scale, and calculating the total gray scale average value u of the point cloud area data according to the probability of each gray scale;
dividing the point cloud area data into background area data and target area data according to any gray level value k in the gray level set of the point cloud area data, wherein the initial value of the gray level value k is the minimum gray level;
the obtaining of the maximum solution which meets the inter-class variance of the background area data and the target area data through a sliding window method, and the taking of the maximum solution as the growth threshold of the point cloud area of the complex hull planking comprises the following steps:
calculating the probability w of the background region data0And the mean gray value u0And the probability w of the occurrence of target region data1And the mean gray value u1；
Solving the inter-class variance of the background area data and the target area data according to a preset first formula, adjusting the gray level value k by a sliding window method, finding a maximum solution meeting the inter-class variance of the background area data and the target area data, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull plate, wherein the preset first formula is as follows:
H2(k)＝w0(u-u0)2+w1(u-u1)2；
wherein H2Is the inter-class variance, w, of the background region data and the target region data0Is the probability of occurrence of background region data, u is the average value of the overall gray scale of point cloud region data, u0Is the mean gray value of the background region data, w1Is the probability of occurrence of data of the target area, u1The average gray value of the target area data is obtained;
the adjusting the gray level value k by a sliding window method and finding the maximum solution satisfying the inter-class variance of the background region data and the target region data includes:
randomly generating perturbations k within a sliding window1And judging the disturbance k1Whether a preset third formula is satisfied, if so, enabling the disturbance k1Is in an initial state, otherwise, whether the state is in an initial state is judged according to the Metroplis criterionAccept status, if accepted, then H2(k0) Stack S, H2(k1) Changing to an initial state, otherwise, continuing to randomly generate disturbance;
judging whether the disturbance process is terminated according to a convergence criterion, if so, traversing the stack S, reserving the maximum solution, and outputting the maximum solution when judging that the sliding window slides through all gray levels, otherwise, randomly generating disturbance again;
the preset third formula is as follows:
H2(k1)>H2(k0)。
2. the method for determining the point cloud area growing threshold value of the hull complex planking according to claim 1, wherein the extracting the gray scale of the point cloud area data of the hull complex planking comprises:
acquiring point cloud area data of the complex hull planking, and dividing the point cloud area data into L levels according to the gray value of the point cloud area data, wherein the L levels can be adjusted according to the growth threshold extraction precision of the point cloud area of the complex hull planking.
3. The hull complex planking point cloud region growing threshold determination method of claim 1, wherein said adjusting the gray level value k by a sliding window method and finding the maximum solution that satisfies the between-class variance of the background region data and the target region data comprises:
determining a feasible solution space G, and determining the size of a sliding window through a preset second formula, wherein the preset second formula is as follows:
L1＝pG；
wherein L is1For the size of the sliding window, p is an adjustable factor, p is greater than 0 and less than or equal to 1, G is the pixel level length, and G ═ 0, 1.
4. A device for determining a point cloud area growing threshold value of a complex hull outer plate is characterized by comprising:
the extraction module is used for extracting the gray level of the point cloud area data of the complex hull planking;
the first calculation module is used for calculating the probability of each gray scale and dividing the point cloud area data into background area data and target area data according to the probability of each gray scale;
the second calculation module is used for solving a maximum solution which meets the inter-class variance of the background area data and the target area data through a sliding window method, and taking the maximum solution as a growth threshold of a point cloud area of the complex hull planking;
the first computing module includes:
the first calculating unit is used for calculating the probability of each gray scale and calculating the overall gray scale average value u of the point cloud area data according to the probability of each gray scale;
the second dividing unit is used for dividing the point cloud area data into background area data and target area data according to any gray level value k in the gray level set of the point cloud area data, and the initial value of the gray level value k is the minimum gray level;
the second calculation module includes:
a second calculation unit for calculating the probability w of the background region data appearing0And the mean gray value u0And the probability w of the occurrence of target region data1And the mean gray value u1；
An adjusting unit, configured to obtain an inter-class variance between the background region data and the target region data according to a preset first formula, adjust the grayscale value k by a sliding window method, find a maximum solution that satisfies the inter-class variance between the background region data and the target region data, and use the maximum solution as a growth threshold of the point cloud region of the complex hull plate, where the preset first formula is:
H2(k)＝w0(u-u0)2+w1(u-u1)2；
wherein H2As a background regionBetween class variance of data and target area data, w0Is the probability of occurrence of background region data, u is the average value of the overall gray scale of point cloud region data, u0Is the mean gray value of the background region data, w1Is the probability of occurrence of data of the target area, u1The average gray value of the target area data is obtained;
the adjustment unit is specifically configured to randomly generate a perturbation k within a sliding window1And judging the disturbance k1Whether a preset third formula is satisfied, if so, enabling the disturbance k1Is in an initial state, otherwise, whether the state is accepted is judged according to the Metroplis criterion, and if the state is accepted, H is added2(k0) Stack S, H2(k1) Changing to an initial state, otherwise, continuing to randomly generate disturbance;
judging whether the disturbance process is terminated according to a convergence criterion, if so, traversing the stack S, reserving the maximum solution, and outputting the maximum solution when judging that the sliding window slides through all gray levels, otherwise, randomly generating disturbance again;
the preset third formula is as follows:
H2(k1)>H2(k0)。
5. the hull complex planking point cloud region growing threshold determination device of claim 4, characterized in that said extraction module comprises:
the first dividing unit is used for acquiring point cloud area data of the complex hull planking, dividing the point cloud area data into L levels according to the gray value of the point cloud area data, and adjusting the L levels according to the growth threshold extraction precision of the point cloud area of the complex hull planking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710090974.7A CN106846341B (en) | 2017-02-20 | 2017-02-20 | Method and device for determining point cloud area growth threshold of complex outer plate of ship body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710090974.7A CN106846341B (en) | 2017-02-20 | 2017-02-20 | Method and device for determining point cloud area growth threshold of complex outer plate of ship body |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106846341A CN106846341A (en) | 2017-06-13 |
| CN106846341B true CN106846341B (en) | 2020-06-09 |
Family
ID=59127988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710090974.7A Active CN106846341B (en) | 2017-02-20 | 2017-02-20 | Method and device for determining point cloud area growth threshold of complex outer plate of ship body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106846341B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112991373A (en) * | 2021-02-26 | 2021-06-18 | 成都正和德能风险管理咨询有限公司 | Flood loss assessment method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002054346A2 (en) * | 2000-12-28 | 2002-07-11 | Pitney Bowes Inc. | Determining the information capacity of a paper channel |
| CN104392208A (en) * | 2014-11-10 | 2015-03-04 | 成都信升斯科技有限公司 | Intelligent recognizing processing method for data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4396896B2 (en) * | 2005-01-07 | 2010-01-13 | 大日本スクリーン製造株式会社 | Threshold matrix generation method, threshold matrix generation apparatus, and recording medium |
| CN101699511A (en) * | 2009-10-30 | 2010-04-28 | 深圳创维数字技术股份有限公司 | Color image segmentation method and system |
| CN102842037A (en) * | 2011-06-20 | 2012-12-26 | 东南大学 | Method for removing vehicle shadow based on multi-feature fusion |
| CN104399776B (en) * | 2014-11-28 | 2017-07-07 | 广东工业大学 | It is a kind of based on Gaussian curvature difference than flame forming plate curve generating evaluation method |
| CN105205485B (en) * | 2015-09-11 | 2018-09-18 | 浙江工商大学 | Large scale image partitioning algorithm based on maximum variance algorithm between multiclass class |
-
2017
- 2017-02-20 CN CN201710090974.7A patent/CN106846341B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002054346A2 (en) * | 2000-12-28 | 2002-07-11 | Pitney Bowes Inc. | Determining the information capacity of a paper channel |
| CN104392208A (en) * | 2014-11-10 | 2015-03-04 | 成都信升斯科技有限公司 | Intelligent recognizing processing method for data |
Non-Patent Citations (4)
| Title |
|---|
| 《基于区域生长的极光图像分割方法》;王妍 等；;《计算机工程与应用》;20161231;第190-195页； * |
| 《基于随机森林的脑磁共振图像分类》;詹曙 等；;《电子测量与仪器学报》;20131130;第27卷(第11期);第3.1节 * |
| 《智能手机场景文字综合处理系统设计》;通天意;《硕士学位论文库》;20131231;第3.2.3节 * |
| 《视频图像中的文字提取技术研究》;彭媛;《硕士学位论文库》;20091231;第4.4节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106846341A (en) | 2017-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220997B (en) | Stereo matching method and system | |
| CN110147744B (en) | Face image quality assessment method, device and terminal | |
| CN111080513B (en) | Attention mechanism-based human face image super-resolution method | |
| CN105046659B (en) | A kind of simple lens based on rarefaction representation is calculated as PSF evaluation methods | |
| CN112634297B (en) | High-precision map making method, device, electronic equipment and storage medium | |
| CN110009663B (en) | Target tracking method, device, equipment and computer readable storage medium | |
| CN111784699B (en) | Method and device for carrying out target segmentation on three-dimensional point cloud data and terminal equipment | |
| CN111598796A (en) | Image processing method and device, electronic device and storage medium | |
| CN115512391B (en) | Target detection model training method, device and equipment for data self-adaptive resampling | |
| CN109658378B (en) | Pore identification method and system based on soil CT image | |
| CN107766793A (en) | MEMS gyroscope signal denoising processing method based on mixed method | |
| KR20110080246A (en) | Apparatus and method for data classification based on support vector machine | |
| CN115423870A (en) | Pupil center positioning method and device | |
| CN104091148A (en) | Facial feature point positioning method and device | |
| CN111179276A (en) | Image processing method and device | |
| CN110365404B (en) | Wavefront-free sensing self-adaptive system and method for improving convergence speed by using same | |
| CN106846341B (en) | Method and device for determining point cloud area growth threshold of complex outer plate of ship body | |
| CN114219936A (en) | Object detection method, electronic device, storage medium, and computer program product | |
| CN108846845A (en) | SAR image segmentation method based on thumbnail and hierarchical fuzzy cluster | |
| CN110580483A (en) | indoor and outdoor user distinguishing method and device | |
| CN110275895B (en) | Filling equipment, device and method for missing traffic data | |
| CN112101461A (en) | HRTF-PSO-FCM-based unmanned aerial vehicle reconnaissance visual information audibility method | |
| CN111126101B (en) | Method and device for determining key point position, electronic equipment and storage medium | |
| CN104639495B (en) | The method and apparatus of constellation soft de-mapped | |
| CN104765776A (en) | Data sample clustering method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |