CN110796584A - Motion blurred image modeling method and device, storage medium and inspection robot - Google Patents
Motion blurred image modeling method and device, storage medium and inspection robot Download PDFInfo
- Publication number
- CN110796584A CN110796584A CN201911031388.0A CN201911031388A CN110796584A CN 110796584 A CN110796584 A CN 110796584A CN 201911031388 A CN201911031388 A CN 201911031388A CN 110796584 A CN110796584 A CN 110796584A
- Authority
- CN
- China
- Prior art keywords
- image data
- motion
- current image
- solving
- blurred image
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000013178 mathematical model Methods 0.000 claims abstract description 27
- 238000005457 optimization Methods 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 abstract description 9
- 230000005540 biological transmission Effects 0.000 description 17
- 230000006870 function Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000006731 degradation reaction Methods 0.000 description 5
- 230000015556 catabolic process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000764238 Isis Species 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/251—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving models
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Robotics (AREA)
- Manipulator (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a motion blur image modeling method, a motion blur image modeling device, a storage medium and a server, and relates to the technical field of inspection robots. The motion blurred image modeling method comprises the following steps: acquiring current image data; inputting the current image data into a motion blurred image mathematical model; and solving the motion blurred image mathematical model, and obtaining actual image data corresponding to the current image data. The motion blur image modeling method, the motion blur image modeling device, the storage medium and the inspection robot provided by the invention can restore and reconstruct the acquired degraded image, and provide effective obstacle detection and original effective positioning information for autonomous navigation of the robot.
Description
Technical Field
The invention relates to the technical field of inspection robots, in particular to a motion blur image modeling method and device, a storage medium and an inspection robot.
Background
When the inspection robot performs inspection operation on an overhead line, due to the influence of factors such as disturbance of a robot body, wind power, online jitter, large air flow and the like, a camera installed on the robot is difficult to stabilize in the information acquisition process and is almost always in the jitter, so that the degradation phenomenon of a shot image due to motion blur is caused, and in a serious condition, the original effective information of the image cannot be acquired, so that the acquisition of useful information is influenced. If the current image data acquired by the camera is directly used as the information on which the inspection robot autonomously navigates, the problem of inaccurate information or navigation error can be caused, and the inspection operation of the inspection robot on the power transmission line is influenced.
Disclosure of Invention
The invention aims to provide a motion blurred image modeling method, a motion blurred image modeling device, a storage medium and an inspection robot, which provide effective obstacle detection and original effective information positioning for autonomous navigation of the robot, so that inspection of a power transmission line is facilitated.
Embodiments of the invention may be implemented as follows:
in a first aspect, an embodiment of the present invention provides a motion blur image modeling method, including:
acquiring current image data;
inputting the current image data into a motion blurred image mathematical model;
and solving the motion blurred image mathematical model, and obtaining actual image data corresponding to the current image data.
Further, in an optional embodiment, the step of solving the motion-blurred image mathematical model and obtaining the actual image data corresponding to the current image data includes:
converting the motion blurred image mathematical model into a quadratic optimization problem with boundary constraint;
and solving the quadratic optimization problem through a neural network algorithm, and obtaining the actual image data.
Further, in an optional embodiment, before the step of solving the quadratic optimization problem through a neural network algorithm and obtaining the actual image data, the method further includes:
the current image data Y is normalized to a value in the range of [ -0.5,0.5] by the following formula:
Y＝Y/255-0.5。
further, in an optional embodiment, before the step of solving the quadratic optimization problem through a neural network algorithm and obtaining the actual image data, the method further includes:
setting a value of a network convergence allowable error, wherein the network convergence allowable error is used for outputting a settlement result if an actual network convergence error is less than or equal to the network convergence allowable error, and taking the calculation result as the actual image data;
wherein the network convergence error is calculated by the following equation:
e＝(1/n)*‖X(t+1)-X(t)‖，
where e represents the network convergence error, X represents the actual image data, and n represents the number of iterations.
Further, in an optional embodiment, the method further comprises:
after the current image data is obtained, calculating the frequency domain characteristics of the current image data;
and inputting the frequency domain characteristics of the current image data into the motion blurred image mathematical model.
The embodiment of the invention provides a motion blur image modeling method, which comprises the following steps: the method is used for processing the acquired current image data to obtain the corresponding actual image data. Jitter and noise are present in the current image data due to the presence of jitter or other disturbances. If the current image data acquired by the camera is directly used as the information on which the inspection robot autonomously navigates, the problem of inaccurate information or navigation error can be caused, and the inspection operation of the inspection robot on the power transmission line is influenced. The embodiment of the application can effectively restore and reconstruct the current image data obtained by equipment such as a camera and the like, and provides effective obstacle detection and original effective positioning information for autonomous navigation of the robot, so that inspection of the power transmission line is facilitated.
In a second aspect, an embodiment of the present invention provides a motion-blurred image modeling apparatus, including:
an acquisition module: the acquisition module is used for acquiring current image data;
an input module: the input module is used for inputting the current image data into a motion blurred image mathematical model;
a solving module: and the solving module is used for solving the motion blurred image mathematical model and obtaining actual image data corresponding to the current image data.
Further, in an optional embodiment, the solving module is further configured to:
converting the motion blurred image mathematical model into a quadratic optimization problem with boundary constraint;
and solving the quadratic optimization problem through a neural network algorithm, and obtaining the actual image data.
Further, in alternative embodiments
The motion blur image modeling device provided by the embodiment of the invention comprises: the device is used for processing the acquired current image data to obtain the corresponding actual image data. Jitter and noise are present in the current image data due to the presence of jitter or other disturbances. If the current image data acquired by the camera is directly used as the information on which the inspection robot autonomously navigates, the problem of inaccurate information or navigation error can be caused, and the inspection operation of the inspection robot on the power transmission line is influenced. The embodiment of the application can effectively restore and reconstruct the current image data obtained by equipment such as a camera and the like, and provides effective obstacle detection and original effective positioning information for autonomous navigation of the robot, so that inspection of the power transmission line is facilitated.
In a third aspect, embodiments of the present invention provide a storage medium, on which a motion-blurred image modeling program is stored, which, when read and executed, is capable of implementing the above-described method.
The storage medium provided by the embodiment of the invention comprises: the acquired current image data can be processed to obtain the corresponding actual image data. Jitter and noise are present in the current image data due to the presence of jitter or other disturbances. If the current image data acquired by the camera is directly used as the information on which the inspection robot autonomously navigates, the problem of inaccurate information or navigation error can be caused, and the inspection operation of the inspection robot on the power transmission line is influenced. The embodiment of the application can effectively restore and reconstruct the current image data obtained by equipment such as a camera and the like, and provides effective obstacle detection and original effective positioning information for autonomous navigation of the robot, so that inspection of the power transmission line is facilitated.
In a fourth aspect, an embodiment of the present invention provides an inspection robot, including:
a memory; and the number of the first and second groups,
a processor;
the memory stores a motion-blurred image modeling program operable on the processor, the motion-blurred image modeling program being read and executed by the processor to implement the method.
The inspection robot provided by the embodiment of the invention comprises: the method can be used for processing the acquired current image data to obtain the corresponding actual image data. Jitter and noise are present in the current image data due to the presence of jitter or other disturbances. If the current image data acquired by the camera is directly used as the information on which the inspection robot autonomously navigates, the problem of inaccurate information or navigation error can be caused, and the inspection operation of the inspection robot on the power transmission line is influenced. The embodiment of the application can effectively restore and reconstruct the current image data obtained by equipment such as a camera and the like, and provides effective obstacle detection and original effective positioning information for autonomous navigation of the robot, so that inspection of the power transmission line is facilitated.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly described below. It is appreciated that the following drawings depict only certain embodiments of the invention and are therefore not to be considered limiting of its scope. For a person skilled in the art, it is possible to derive other relevant figures from these figures without inventive effort.
Fig. 1 is a block diagram schematically illustrating a structure of an inspection robot according to an embodiment of the present invention.
Fig. 2 is a schematic block diagram of a flow of a motion blur image modeling method according to an embodiment of the present invention.
Fig. 3 is a schematic block diagram of a flow of a motion blur image modeling method according to an embodiment of the present invention.
Fig. 4 is a block diagram schematically illustrating a flow of sub-step S510 and sub-step S520 of step S500 in fig. 2 or 3.
Fig. 5 is a block diagram schematically illustrating a structure of a motion blur image modeling apparatus according to an embodiment of the present invention.
Icon: 100-a patrol robot; 110-motion blur image modeling means; 111-an acquisition module; 112-an input module; 113-a solving module; 120-a memory; 130-a processor.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
Referring to fig. 1, the embodiment provides a motion blur image modeling method and a motion blur image modeling device 110, which are applied to an inspection robot 100, and are used for restoring and reconstructing an image acquired by the inspection robot 100, so that the acquired data is closer to a real scene, and a better running route is calculated, and the inspection effect of the inspection robot 100 is improved. The inspection robot 100 includes a memory 120, a processor 130, and a motion blur image modeling device 110.
The memory 120 and the processor 130 are electrically connected to each other, directly or indirectly, to enable transmission or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The motion-blurred image modeling apparatus 110 includes at least one software function module that may be stored in the memory 120 in the form of software or firmware (firmware) or solidified in an Operating System (OS) of a server. The processor 130 is used for executing executable modules stored in the memory 120, such as software functional modules included in the motion blur image modeling device 110, a motion blur image modeling program that can run on the processor 130, and the like.
The memory 120 is used for storing a program, and the processor 130 executes the program after receiving the execution instruction.
The Memory 120 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The Processor 130 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. The general purpose processor 130 may be a microprocessor 130. The processor 130 may also be any conventional processor 130 or the like.
Referring to fig. 2, the present embodiment provides a motion blur image modeling method, which includes the following steps.
Step S100: current image data is acquired.
It should be noted that when the inspection robot performs inspection operation on an overhead line, due to the influence of factors such as disturbance of a robot body, wind power, online jitter, and large airflow, a camera mounted on the robot is difficult to stabilize in the process of acquiring information and is almost always in the jitter, so that a degradation phenomenon occurs in a shot image due to motion blur, and in a serious case, the original effective information of the image cannot be acquired. That is, the current image data includes not only the original valid image data but also jitter and noise data. The current image data is used for providing basic data for autonomous navigation of the robot, and in the invention, the acquired current image data needs to be restored and reconstructed so as to ensure that the basic data is effective and accurate and further ensure the autonomous navigation effect of the robot.
Step S200: the current image data is input into a motion blurred image mathematical model.
If the current image data is time domain data, the current image data is converted into a frequency domain and then input into the motion blurred image mathematical model.
Referring to fig. 3, optionally, the method may further include step S300 and step 400. Step 300: after acquiring the current image data, calculating the frequency domain characteristics of the current image data; step S400: and inputting the frequency domain characteristics of the current image data into the motion blurred image mathematical model.
Step S500: and solving the motion blurred image mathematical model, and obtaining actual image data corresponding to the current image data.
The original image f (x, y) is subjected to a degradation system H (x, y) and then superimposed with noise n (x, y), thereby forming a degraded image g (x, y), i.e., the current image data in the embodiment of the present invention. An object of the embodiment of the present invention is to find an original image f (x, y), i.e., actual image data corresponding to current image data, and the image degradation process can be expressed by the following formula:
g(x,y)＝H(x,y)*f(x,y)+n(x,y)
using a two-dimensional function description, let the point spread function H (x- α, y- β) be H δ (x, y, α) to obtain:
where each dot pixel of f (α) contributes to the final image g (x, y), with the magnitude represented by the weighted function h (x- α, y- β).
Further, there are two main types of image blur models caused by the online motion of the inspection robot 100: the robot body is of a left-right pendulum type, and the robot body is of an up-down vertical shaking type.
The transfer function expression of the vertical-shake type motion blur degraded image is:
H(u,v)＝Te-jvπVTsinc(vπV)
the transfer function of a pendulum-type motion blur degraded image is:
H(u,v)＝Te-jπVT(ucosθ+vsinθ)sin c(πV(ucosθ+vsinθ))
as can be seen from the above transfer function, H (u, v) has a zero point at v ═ n/VT, and the spectrum of the motion-blurred image has some equally spaced straight lines perpendicular to the v axis. From the positions of these lines and the target-to-camera distance estimates, V can be solved. Based on this, the motion-blurred image is mathematically modeled.
Alternatively, the Hopfield neural network may be adopted to perform technical research on the image restoration inspection robot 100, and the degradation model of the motion-blurred image is rewritten into Y ═ HX + N, where H is a blurring matrix corresponding to a point spread function, N is an independent noise vector, X, Y respectively represents the original and degraded images, that is, X is actual image data in the embodiment of the present invention, and Y is current image data:
the original problem can be converted into a quadratic optimization problem with boundary constraint, and the following cost function is taken as a criterion function of image restoration:
wherein the first item seeks one
Make itSimilar to Y in the least squares sense, the second term is
Is constrained by the smoothness of the surface. λ is a constant, which is used to suppress noise and reduce abrupt changes. H is the low pass distortion and D is the high pass filter.
Referring to fig. 4, further, in an alternative embodiment, the step S500: solving the motion-blurred image mathematical model and obtaining actual image data corresponding to the current image data may comprise sub-step S510 and sub-step S520.
Substep S510: and converting the motion blurred image mathematical model into a quadratic optimization problem with boundary constraint.
Substep S520: solving a quadratic optimization problem through a neural network algorithm, and obtaining actual image data.
Further, in an optional embodiment, before the step of solving the quadratic optimization problem by the neural network algorithm and obtaining the actual image data, the method further comprises:
the current image data Y is normalized to a value in the range of [ -0.5,0.5] by the following formula:
Y＝Y/255-0.5。
further, in an optional embodiment, before the step of solving the quadratic optimization problem by the neural network algorithm and obtaining the actual image data, the method further comprises:
setting a value of a network convergence allowable error, wherein the network convergence allowable error is used for outputting a settlement result if the actual network convergence error is less than or equal to the network convergence allowable error, and taking the calculation result as actual image data;
wherein the network convergence error is calculated by the following equation:
in the formula, e represents a network convergence error, X represents actual image data, and n represents the number of iterations.
It should be noted that, in some embodiments of the present invention, the above calculation process may refer to the following steps:
1) the degraded image Y is normalized to a value of [ -0.5,0.5] by the following formula:
initial value: x (0) ═ HTY,t＝0
Network convergence allowable error value: e 10-5；
2) Determine e is satisfied with the requirement? If the network convergence allowable error is met, turning to step 6); otherwise, turning to the next step;
3) and (3) calculating: u. ofi＝∑j＝1Ti,jX(t)+Ii，ΔX＝f(ui)，X(t+1)＝g(X(t)+ΔX)；
Wherein g (u) and f (u)i) Is a state change rule function, Ti,jIs a neural network connection weight parameter, IiIs a bias input parameter
In the above formula, θiIs an empirical threshold;
4)
x (t) ═ X (t +1), where n is the total number of iterations;
5) returning to the step 2);
6) x (t) ═ x (t) +0.5, the gradation value is reduced to [0,1], x (t) ═ x (t) × 255, and the gradation value is reduced to [0,255 ].
It should be noted that the above calculation process is only a reference calculation method, and in other embodiments of the present invention, other calculation methods may be used for calculation.
The embodiment of the invention provides a motion blur image modeling method, which comprises the following steps: the method is used for processing the acquired current image data to obtain the corresponding actual image data. Jitter and noise are present in the current image data due to the presence of jitter or other disturbances. If the current image data acquired by the camera is directly used as the information on which the inspection robot 100 autonomously navigates, the problem of inaccurate information or navigation error can be caused, which affects the inspection operation of the inspection robot 100 on the power transmission line. The embodiment of the application can effectively restore and reconstruct the current image data obtained by equipment such as a camera and the like, and provides effective obstacle detection and original effective positioning information for autonomous navigation of the robot, so that inspection of the power transmission line is facilitated.
Referring to fig. 5, an embodiment of the invention provides a motion blur image modeling apparatus 110, including: an acquisition module 111, an input module 112, and a solving module 113.
The acquisition module 111: the obtaining module 111 is used for obtaining current image data.
In the embodiment of the present invention, the step S100 is executed by the obtaining module 111.
The input module 112: the input module 112 is used to input the current image data into the motion-blurred image mathematical model.
In the embodiment of the present invention, the step S200 is executed by the input module 112.
The solving module 113: the solving module 113 is configured to solve the motion blur image mathematical model and obtain actual image data corresponding to the current image data.
In the embodiment of the present invention, the above step S500 is executed by the solving module 113.
Further, in an optional embodiment, the solving module 113 is further configured to:
converting a motion blurred image mathematical model into a secondary optimization problem with boundary constraint;
solving a quadratic optimization problem through a neural network algorithm, and obtaining actual image data.
In an embodiment of the present invention, the above sub-step S510 and sub-step S520 are performed by the solving module 113.
The motion blur image modeling apparatus 110 provided in the embodiment of the present invention: the device is used for processing the acquired current image data to obtain the corresponding actual image data. Jitter and noise are present in the current image data due to the presence of jitter or other disturbances. If the current image data acquired by the camera is directly used as the information on which the inspection robot 100 autonomously navigates, the problem of inaccurate information or navigation error can be caused, and the inspection operation of the inspection robot 100 on the power transmission line is affected. The embodiment of the application can effectively restore and reconstruct the current image data obtained by equipment such as a camera and the like, and provides effective obstacle detection and original effective positioning information for autonomous navigation of the robot, so that inspection of the power transmission line is facilitated.
Embodiments of the present invention provide a storage medium, that is, a computer-readable storage medium, on which a motion blur image modeling program is stored, and when the motion blur image modeling program is read and executed, the method described above can be implemented.
The storage medium provided by the embodiment of the invention comprises: the acquired current image data can be processed to obtain the corresponding actual image data. Jitter and noise are present in the current image data due to the presence of jitter or other disturbances. If the current image data acquired by the camera is directly used as the information on which the inspection robot 100 autonomously navigates, the problem of inaccurate information or navigation error can be caused, and the inspection operation of the inspection robot 100 on the power transmission line is affected. The embodiment of the application can effectively restore and reconstruct the current image data obtained by equipment such as a camera and the like, and provides effective obstacle detection and original effective positioning information for autonomous navigation of the robot, so that inspection of the power transmission line is facilitated.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules 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: u disk, removable hard disk, read only memory, random access memory, magnetic or optical disk, etc. for storing program codes.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Although the present invention is disclosed above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (9)
1. A motion-blurred image modeling method, comprising:
acquiring current image data;
inputting the current image data into a motion blurred image mathematical model;
and solving the motion blurred image mathematical model, and obtaining actual image data corresponding to the current image data.
2. The method of claim 1, wherein the step of solving the motion-blurred image mathematical model and obtaining the actual image data corresponding to the current image data comprises:
converting the motion blurred image mathematical model into a quadratic optimization problem with boundary constraint;
and solving the quadratic optimization problem through a neural network algorithm, and obtaining the actual image data.
3. The method of modeling motion blurred images as claimed in claim 2, wherein before the step of solving the quadratic optimization problem through a neural network algorithm and obtaining the actual image data, the method further comprises:
the current image data Y is normalized to a value in the range of [ -0.5,0.5] by the following formula:
Y＝Y/255-0.5。
4. the motion-blurred image modeling method of claim 3, wherein before the step of solving the quadratic optimization problem through a neural network algorithm and obtaining the actual image data, the method further comprises:
setting a value of a network convergence allowable error, wherein the network convergence allowable error is used for outputting a settlement result if an actual network convergence error is less than or equal to the network convergence allowable error, and taking the calculation result as the actual image data;
wherein the network convergence error is calculated by the following equation:
e＝(1/n)*‖X(t+1)-X(t)‖，
where e represents the network convergence error, X represents the actual image data, and n represents the number of iterations.
5. The method of modeling a motion blurred image as claimed in claims 1 to 4, wherein said method further comprises:
after the current image data is obtained, calculating the frequency domain characteristics of the current image data;
and inputting the frequency domain characteristics of the current image data into the motion blurred image mathematical model.
6. A motion-blurred image modeling apparatus, comprising:
an acquisition module: the acquisition module is used for acquiring current image data;
an input module: the input module is used for inputting the current image data into a motion blurred image mathematical model;
a solving module: and the solving module is used for solving the motion blurred image mathematical model and obtaining actual image data corresponding to the current image data.
7. The motion-blurred image modeling apparatus of claim 6, wherein the solving module is further configured to:
converting the motion blurred image mathematical model into a quadratic optimization problem with boundary constraint;
and solving the quadratic optimization problem through a neural network algorithm, and obtaining the actual image data.
8. A storage medium having stored thereon a motion blurred image modeling program, which when read and executed is capable of implementing the method according to any of claims 1-5.
9. An inspection robot, comprising:
a memory; and the number of the first and second groups,
a processor;
the memory stores a motion blurred image modeling program executable on the processor, the motion blurred image modeling program being read and executed by the processor to implement the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911031388.0A CN110796584A (en) | 2019-10-28 | 2019-10-28 | Motion blurred image modeling method and device, storage medium and inspection robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911031388.0A CN110796584A (en) | 2019-10-28 | 2019-10-28 | Motion blurred image modeling method and device, storage medium and inspection robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110796584A true CN110796584A (en) | 2020-02-14 |
Family
ID=69441641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911031388.0A Pending CN110796584A (en) | 2019-10-28 | 2019-10-28 | Motion blurred image modeling method and device, storage medium and inspection robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796584A (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101364302A (en) * | 2008-09-28 | 2009-02-11 | 西安理工大学 | Clearness processing method for defocus blurred image |
| CN203422665U (en) * | 2013-06-04 | 2014-02-05 | 沈阳易思达智能通讯有限公司 | Inspection robot for transformer station |
| CN104156919A (en) * | 2014-08-04 | 2014-11-19 | 陕西科技大学 | Motion-blurred image restoration method based on wavelet transform and Hopfield neural network |
| CN106228512A (en) * | 2016-07-19 | 2016-12-14 | 北京工业大学 | Based on learning rate adaptive convolutional neural networks image super-resolution rebuilding method |
| CN107730469A (en) * | 2017-10-17 | 2018-02-23 | 长沙全度影像科技有限公司 | A kind of three unzoned lens image recovery methods based on convolutional neural networks CNN |
| CN108038846A (en) * | 2017-12-04 | 2018-05-15 | 国网山东省电力公司电力科学研究院 | Transmission line equipment image defect detection method and system based on multilayer convolutional neural networks |
| CN108364262A (en) * | 2018-01-11 | 2018-08-03 | 深圳大学 | A kind of restored method of blurred picture, device, equipment and storage medium |
| CN108765340A (en) * | 2018-05-29 | 2018-11-06 | Oppo（重庆）智能科技有限公司 | Fuzzy image processing method, apparatus and terminal device |
| CN109003234A (en) * | 2018-06-21 | 2018-12-14 | 东南大学 | For the fuzzy core calculation method of motion blur image restoration |
| CN109214989A (en) * | 2018-09-04 | 2019-01-15 | 四川大学 | Single image super resolution ratio reconstruction method based on Orientation Features prediction priori |
| CN109345474A (en) * | 2018-05-22 | 2019-02-15 | 南京信息工程大学 | Image motion based on gradient field and deep learning obscures blind minimizing technology |
| CN109377459A (en) * | 2018-09-30 | 2019-02-22 | 国网山东省电力公司电力科学研究院 | A kind of super-resolution deblurring method of production confrontation network |
| CN109544584A (en) * | 2018-11-30 | 2019-03-29 | 国网山东省电力公司信息通信公司 | It is a kind of to realize inspection surely as the method and system of precision measure |
| CN109903228A (en) * | 2019-02-28 | 2019-06-18 | 合肥工业大学 | A kind of image super-resolution rebuilding method based on convolutional neural networks |
| CN110148139A (en) * | 2019-04-25 | 2019-08-20 | 电信科学技术研究院有限公司 | A kind of image recovery method and device |
-
2019
- 2019-10-28 CN CN201911031388.0A patent/CN110796584A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101364302A (en) * | 2008-09-28 | 2009-02-11 | 西安理工大学 | Clearness processing method for defocus blurred image |
| CN203422665U (en) * | 2013-06-04 | 2014-02-05 | 沈阳易思达智能通讯有限公司 | Inspection robot for transformer station |
| CN104156919A (en) * | 2014-08-04 | 2014-11-19 | 陕西科技大学 | Motion-blurred image restoration method based on wavelet transform and Hopfield neural network |
| CN106228512A (en) * | 2016-07-19 | 2016-12-14 | 北京工业大学 | Based on learning rate adaptive convolutional neural networks image super-resolution rebuilding method |
| CN107730469A (en) * | 2017-10-17 | 2018-02-23 | 长沙全度影像科技有限公司 | A kind of three unzoned lens image recovery methods based on convolutional neural networks CNN |
| CN108038846A (en) * | 2017-12-04 | 2018-05-15 | 国网山东省电力公司电力科学研究院 | Transmission line equipment image defect detection method and system based on multilayer convolutional neural networks |
| CN108364262A (en) * | 2018-01-11 | 2018-08-03 | 深圳大学 | A kind of restored method of blurred picture, device, equipment and storage medium |
| CN109345474A (en) * | 2018-05-22 | 2019-02-15 | 南京信息工程大学 | Image motion based on gradient field and deep learning obscures blind minimizing technology |
| CN108765340A (en) * | 2018-05-29 | 2018-11-06 | Oppo（重庆）智能科技有限公司 | Fuzzy image processing method, apparatus and terminal device |
| CN109003234A (en) * | 2018-06-21 | 2018-12-14 | 东南大学 | For the fuzzy core calculation method of motion blur image restoration |
| CN109214989A (en) * | 2018-09-04 | 2019-01-15 | 四川大学 | Single image super resolution ratio reconstruction method based on Orientation Features prediction priori |
| CN109377459A (en) * | 2018-09-30 | 2019-02-22 | 国网山东省电力公司电力科学研究院 | A kind of super-resolution deblurring method of production confrontation network |
| CN109544584A (en) * | 2018-11-30 | 2019-03-29 | 国网山东省电力公司信息通信公司 | It is a kind of to realize inspection surely as the method and system of precision measure |
| CN109903228A (en) * | 2019-02-28 | 2019-06-18 | 合肥工业大学 | A kind of image super-resolution rebuilding method based on convolutional neural networks |
| CN110148139A (en) * | 2019-04-25 | 2019-08-20 | 电信科学技术研究院有限公司 | A kind of image recovery method and device |
Non-Patent Citations (1)
| Title |
|---|
| 金于君: ""图像去雾算法研究"", 《中国优秀硕士学位论文全文数据库》, pages 4 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3703006A1 (en) | Anti-shake method and apparatus for panoramic video, and portable terminal | |
| JP2021503134A (en) | Unsupervised learning of image depth and egomotion prediction neural networks | |
| Li et al. | Maximum likelihood stochastic gradient estimation for Hammerstein systems with colored noise based on the key term separation technique | |
| Tarel et al. | Using robust estimation algorithms for tracking explicit curves | |
| US20180032868A1 (en) | Early prediction of an intention of a user's actions | |
| US9619870B2 (en) | Scale adaptive blind deblurring | |
| CN110874827A (en) | Turbulent image restoration method and device, terminal equipment and computer readable medium | |
| CN106550187A (en) | For the apparatus and method of image stabilization | |
| CN112381868A (en) | Image depth estimation method and device, readable storage medium and electronic equipment | |
| KR102026651B1 (en) | A method and system for robust object tracking using particle filter framework | |
| CN110796584A (en) | Motion blurred image modeling method and device, storage medium and inspection robot | |
| JP4210292B2 (en) | Image change prediction method and image change prediction apparatus | |
| Kouzoupis et al. | An efficient SQP algorithm for moving horizon estimation with Huber penalties and multi-rate measurements | |
| KR101583787B1 (en) | Method of foreground detection using image decomposition and online robust principal component analysis, recording medium and device for performing the method | |
| Jia et al. | A new class of nonlinear Rauch–Tung–Striebel cubature Kalman smoothers | |
| US11958194B2 (en) | Control command based adaptive system and method for estimating motion parameters of differential drive vehicles | |
| JP5874996B2 (en) | Object motion estimation apparatus, object motion estimation method, and program | |
| Wu et al. | Attitude estimation based on robust information cubature quaternion filter | |
| de Jesus et al. | Information filtering and array algorithms for discrete-time Markovian jump linear systems subject to parametric uncertainties | |
| Zhang et al. | A high-order level-set method with enhanced stability for curvature driven flows and surface diffusion motion | |
| CN112824829B (en) | Tripod head posture adjustment method and device | |
| Gan et al. | Wiener Filter and Kalman Filter | |
| CN110543919A (en) | robot positioning control method, terminal equipment and storage medium | |
| Chen et al. | Data filtering based recursive least squares estimation algorithm for a class of Wiener nonlinear systems | |
| CN113253610B (en) | Aircraft control 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 |