CN112091992B - Path planning method and device of egg brushing liquid manipulator - Google Patents
Path planning method and device of egg brushing liquid manipulator Download PDFInfo
- Publication number
- CN112091992B CN112091992B CN202011090929.XA CN202011090929A CN112091992B CN 112091992 B CN112091992 B CN 112091992B CN 202011090929 A CN202011090929 A CN 202011090929A CN 112091992 B CN112091992 B CN 112091992B
- Authority
- CN
- China
- Prior art keywords
- image
- numerical value
- gray
- biscuit
- path planning
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/0045—Manipulators used in the food industry
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
- B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
Abstract
The application discloses a path planning method and a device for an egg brushing liquid manipulator, wherein the method comprises the following steps: acquiring a three-dimensional image of a cake blank to be processed on a conveyor belt through a three-dimensional scanner, wherein the three-dimensional image comprises a gray level image and a depth image; extracting a target biscuit region image from the gray-scale image, and calculating a plane coordinate of a biscuit to be processed according to the target biscuit region image; calculating the height information of the cake blank to be processed according to the depth map after filtering; acquiring a current coding numerical value of a transmission shaft of the conveyor belt through an encoder; performing path planning according to the plane coordinates, the height information and the current coding numerical value to obtain a target motion track; and carrying out egg liquid brushing operation according to the target motion track. The application can solve prior art and can't accurately hold cake base position on the conveyer belt, leads to the manipulator to be difficult to guarantee the technical problem of egg liquid brush the precision of operation.
Description
Technical Field
The application relates to the technical field of food processing, in particular to a path planning method and device for an egg brushing liquid manipulator.
Background
The moon cake is eaten in mid-autumn festival, which is a tradition of China for hundreds of thousands of years, and the surface of the moon cake needs to be coated with a layer of egg liquid in the middle baking period, so that the baked moon cake is golden in color. Because the traditional Cantonese moon cake has a well-defined angle and a waist-drum-shaped expanded cake body, the baked moon cake is required to have golden color, consistent depth and clear patterns. Therefore, the egg liquid is not simply smeared on the surface of the moon cake, but the skill is required, the egg liquid needs to be evenly brushed on the patterns on the surface of the moon cake in a light and thin manner, the conventional egg liquid brushing process is still mostly manually completed, but the working section for brushing the egg liquid needs to be arranged in the middle section of a tunnel oven, the room temperature is above 40 ℃, and the working environment is hard; and the efficiency of manually brushing the egg liquid is low.
However, in recent years, with the increasing sales of moon cakes, the production efficiency of the moon cakes needs to be improved, and in order to improve the efficiency of the egg brushing process, a plurality of devices for brushing the egg liquid quickly appear to brush the egg liquid on the cake blanks on the conveyor belt automatically and efficiently. However, the egg brushing device in the prior art usually only focuses on solving the problem of production efficiency, and neglects many detailed problems in production, such as uneven trays, errors in automatic tray arrangement or small differences among moon cake individuals. The existing equipment can not accurately acquire the position of a cake blank on a conveyor belt, the accuracy of brushing egg liquid on the cake blank by a manipulator is influenced, the egg liquid can be accurately and uniformly coated on the surface of each pattern of a moon cake, the baked moon cake is uneven in color, the pattern is not clear, or the outer surface of the pattern is prevented from being excessively colored, and the quality of the finished moon cake is further influenced.
Disclosure of Invention
The application provides a path planning method and a path planning device for an egg liquid brushing manipulator, which are used for solving the technical problem that the manipulator is difficult to ensure the accuracy of egg liquid brushing operation due to the fact that the position of a cake blank on a conveyor belt cannot be accurately grasped in the prior art.
In view of this, the first aspect of the present application provides a path planning method for an egg brushing robot, including:
acquiring a three-dimensional image of a cake blank to be processed on a conveyor belt through a three-dimensional scanner, wherein the three-dimensional image comprises a gray level image and a depth image;
extracting a target biscuit area image from the gray-scale image, and calculating the plane coordinate of the biscuit to be processed according to the target biscuit area image;
calculating the height information of the cake blank to be processed according to the depth map after filtering processing;
acquiring a current coding numerical value of a transmission shaft of the conveyor belt through an encoder;
performing path planning according to the plane coordinates, the height information and the current coding numerical value to obtain a target motion track;
and carrying out egg liquid brushing operation according to the target motion track.
Optionally, the extracting a target biscuit region image from the grayscale image, and calculating a plane coordinate of the biscuit to be processed according to the target biscuit region image, further includes:
carrying out preprocessing operation of corrosion and expansion on the gray-scale image to obtain a preprocessed gray-scale image;
correspondingly, the extracting of the target biscuit region image in the gray-scale image specifically comprises:
and extracting an image of a target biscuit area from the preprocessing gray-scale image.
Optionally, the filtering process includes:
and carrying out mean filtering processing on the depth map by adopting a mask with a preset size to obtain the depth map after filtering processing.
Optionally, the obtaining, by an encoder, a current encoded value of a transmission shaft of the conveyor belt, and then further includes:
adopting a preset code value to carry out error code detection on the current code value;
and when the current coding numerical value is an error code, performing coding prediction according to the preset coding numerical value, and taking a prediction result as the current coding numerical value.
Optionally, the performing error code detection on the current coding value by using a preset coding value includes:
performing difference calculation according to the obtained previous-time coding numerical value and the current coding numerical value to obtain a coding numerical value increment, and performing differential calculation on the coding numerical value increment to obtain a coding numerical value acceleration;
and judging whether the acceleration of the coding numerical value is in a preset range, if so, judging that the current coding numerical value is not an error code, and if not, judging that the current coding numerical value is the error code.
This application second aspect provides a path planning device of brush egg liquid manipulator, includes:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a three-dimensional image of a cake blank to be processed on a conveyor belt through a three-dimensional scanner, and the three-dimensional image comprises a gray scale image and a depth image;
the coordinate calculation module is used for extracting a target biscuit region image from the gray-scale image and calculating the plane coordinate of the biscuit to be processed according to the target biscuit region image;
the height calculating module is used for calculating the height information of the cake blank to be processed according to the depth map after filtering processing;
the second acquisition module is used for acquiring the current coding numerical value of the transmission shaft of the conveyor belt through the coder;
the path planning module is used for planning a path according to the plane coordinate, the height information and the current coding numerical value to obtain a target motion track;
and the egg liquid brushing module is used for brushing egg liquid according to the target motion track.
Optionally, the method further includes:
the preprocessing module is used for carrying out preprocessing operation of corrosion and expansion on the gray-scale image to obtain a preprocessed gray-scale image;
correspondingly, the extracting of the target biscuit region image in the gray-scale image specifically comprises:
and extracting an image of a target biscuit area from the preprocessing gray-scale image.
Optionally, the filtering process includes:
and carrying out mean filtering processing on the depth map by adopting a mask with a preset size to obtain the depth map after filtering processing.
Optionally, the method further includes:
the error code detection module is used for carrying out error code detection on the current coding value by adopting a preset coding value;
and the coding prediction module is used for performing coding prediction according to the preset coding numerical value when the current coding numerical value is an error code, and taking a prediction result as the current coding numerical value.
Optionally, the error code detection module specifically includes:
the calculation submodule is used for performing difference calculation according to the obtained coded value at the previous moment and the current coded value to obtain a coded value increment, and performing differential calculation on the coded value increment to obtain a coded value acceleration;
and the judgment submodule is used for judging whether the acceleration of the coded numerical value is within a preset range, if so, the current coded numerical value is not an error code, and otherwise, the current coded numerical value is the error code.
According to the technical scheme, the embodiment of the application has the following advantages:
in the application, a path planning method for an egg brushing liquid manipulator is provided, which comprises the following steps: acquiring a three-dimensional image of a cake blank to be processed on a conveyor belt through a three-dimensional scanner, wherein the three-dimensional image comprises a gray level image and a depth image; extracting a target biscuit region image from the gray-scale image, and calculating a plane coordinate of a biscuit to be processed according to the target biscuit region image; calculating the height information of the cake blank to be processed according to the depth map after filtering; acquiring a current coding numerical value of a transmission shaft of the conveyor belt through an encoder; performing path planning according to the plane coordinates, the height information and the current coding numerical value to obtain a target motion track; and carrying out egg liquid brushing operation according to the target motion track.
The application provides a path planning method of brush egg liquid manipulator, acquire the three-dimensional image of cake base on the conveyer belt through three-dimensional scanner, thereby can obtain the plane information of cake base, grey map promptly, and depth information, depth map promptly, can acquire the plane coordinate and the height information of cake base on the conveyer belt respectively from these two kinds of images, can acquire the relative position information of cake base and conveyer belt again through the current code numerical value of encoder, can carry out accurate path planning according to plane coordinate, height information and current code numerical value, the manipulator can be from the plane accurate cake base of applying paint with a brush, the height of the cake base that can also accurate grasp, guarantee the quality of applying paint with a brush. Therefore, the technical problem that in the prior art, the position of a cake blank on a conveyor belt cannot be accurately grasped, and the manipulator is difficult to guarantee the accuracy of egg liquid brushing operation can be solved.
Drawings
Fig. 1 is a schematic flowchart of a path planning method of an egg brushing robot according to an embodiment of the present disclosure;
fig. 2 is another schematic flow chart of a path planning method of an egg brushing robot according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a path planning device of an egg brushing robot according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an application system for path planning of an egg brushing robot according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
For easy understanding, referring to fig. 1, a first embodiment of a path planning method for an egg brushing robot provided by the present application includes:
It should be noted that a three-dimensional scanner (3D scanner) is a scientific instrument for detecting and analyzing the shape (geometric structure) and appearance data (such as color, surface albedo, etc.) of an object or environment in the real world; the collected data is often used to perform three-dimensional reconstruction calculations to create a digital model of the actual object in the virtual world. In this embodiment, a three-dimensional scanner is used to obtain a three-dimensional image of a biscuit on a conveyor belt, and the image is converted into a plane grayscale image and a depth image. The specific acquisition mode can be that a sensor is arranged at the feeding end of the conveyor belt, and when the sensor detects that the cake blank enters a target working area, the three-dimensional scanner is triggered to acquire images.
And 102, extracting a target biscuit area image from the gray-scale image, and calculating the plane coordinate of the biscuit to be processed according to the target biscuit area image.
It should be noted that the gray-scale image may directly extract the target biscuit region image, or may perform certain preprocessing to extract the target biscuit region image, where the purpose of the preprocessing is mainly to perform denoising and repairing on the image to obtain a higher-quality gray-scale image, thereby ensuring the image extraction effect. The specific method for calculating the plane coordinates of the biscuit from the target biscuit region image can be to construct a coordinate system for conversion or template matching. The specific coordinate determination method is not limited, and finally the coordinates and the conveyor belt are subjected to fusion conversion to obtain the relative coordinates of the cake blank relative to the conveyor belt.
And 103, calculating height information of the cake blank to be processed according to the depth map after filtering processing.
It should be noted that many technical means of filtering processing are available, and the purpose of filtering processing is to eliminate noise in the depth map, thereby facilitating extraction of height information. Specific filtering techniques include mean filtering, gaussian filtering, median filtering, and the like, which can be selected according to actual situations and are not limited herein. The height information calculated in the embodiment is the height of the cake blank; accurate cake blank height information can help a manipulator to realize accurate coating of egg liquid. The height of the cake blank also needs to be converted into the relative position with the conveyor belt to obtain the relative height.
And 104, acquiring a current coding value of a transmission shaft of the conveyor belt through an encoder.
It should be noted that, the encoder is the device of direct subsides on the conveyer belt, can record the coding numerical value of conveyer belt transmission shaft, and can avoid receiving the transmission shaft slip influence of conveyer belt, and the encoder can reflect the operation progress of conveyer belt through the coding numerical value of record to obtain the relative displacement condition of cake blank on the conveyer belt.
And 105, planning a path according to the plane coordinates, the height information and the current coding numerical value to obtain a target motion track.
It should be noted that the coordinate information of each biscuit can be accurately obtained according to the plane coordinate and the height information, the running rule of the conveyor belt can be calculated through the current coding numerical value, one or more key points are selected for each biscuit based on the coordinate information, and a target motion track can be formed by connecting the key points, so that path planning is realized.
And 106, carrying out egg liquid brushing operation according to the target motion track.
The egg liquid layer can be coated on the cake blank by clamping the brush on the manipulator, so that the manipulator can carry out egg liquid coating operation according to the target motion track, the running path length of the machine can be reduced, the position of the cake blank can be accurately grasped, and accurate coating is realized.
According to the path planning method of the egg brushing liquid manipulator provided by the embodiment of the application, the three-dimensional image of the cake blank on the conveyor belt is obtained through the three-dimensional scanner, so that the plane information of the cake blank, namely a gray level image, and the depth information, namely a depth image can be obtained, the plane coordinate and the height information of the cake blank on the conveyor belt can be obtained from the two images respectively, the relative position information of the cake blank and the conveyor belt can be obtained through the current coding numerical value of the encoder, accurate path planning can be carried out according to the plane coordinate, the height information and the current coding numerical value, the manipulator can accurately brush the cake blank from the plane, the height of the cake blank can be accurately grasped, and the brushing quality is ensured. Therefore, the technical problem that in the prior art, the position of a cake blank on a conveyor belt cannot be accurately grasped, and the manipulator is difficult to guarantee the accuracy of egg liquid brushing operation can be solved.
For easy understanding, referring to fig. 2, the present application provides a second embodiment of a path planning method for an egg brushing robot, including:
It should be noted that the process of acquiring a three-dimensional image of a cake blank by using a three-dimensional scanner and integrating the three-dimensional image into a gray scale map and a depth map is not repeated here, and is specifically similar to step 101.
It should be noted that the process of performing corrosion processing on the grayscale map is to perform corrosion operation on the grayscale map, and the corrosion operation can eliminate the bright regions smaller than the structural elements, thereby effectively removing the isolated noise points and the protruding portions with unsmooth boundaries in the grayscale map. The expansion processing is to perform expansion operation on the gray-scale image, the expansion operation is dual operation of corrosion operation, and the expansion operation can fill the hollow area in the gray-scale image, so that a connected domain is formed, and the concave part with unsmooth boundary is filled. The gray-scale image can be repaired through corrosion treatment and expansion treatment, so that a high-quality gray-scale image is obtained, and the extraction of a target area is facilitated.
And 203, extracting a target biscuit region image from the preprocessed gray level image, and calculating the plane coordinate of the biscuit to be processed according to the target biscuit region image.
It should be noted that the image of the target biscuit region obtained from the preprocessed image is clearer and more accurate. The method for acquiring the image of the target biscuit region may be an objective detection method, or may be acquired by other effective technical means, which is not limited herein. The plane coordinates are calculated in a manner similar to that of step 102.
And 204, carrying out mean filtering processing on the depth map by adopting a mask with a preset size to obtain the filtered depth map.
It should be noted that the mean filtering process is an effective means in the filtering operation technique, and the preset size mask may be set to 3 × 3, and the specific calculation process is as follows:
t(u,v)＝1/9f(u,v)；
where f (u, v) is the pixel value of a certain point in the depth map, and t (u, v) is the pixel value of the corresponding point after mask calculation. The mean filtering adopts a convolution mask to carry out filtering processing on the depth map, and can distinguish noise points from surrounding pixel points, thereby achieving the purpose of eliminating the noise points in the map; moreover, the average filtering calculation method is simple and easy to execute, has high calculation speed and strong inhibition force on periodic interference.
Except for processing the depth map by adopting mean filtering, Gaussian filtering can be adopted, wherein the Gaussian filtering is to carry out convolution calculation on the depth map by adopting a sliding window, and the calculation process is as follows:
wherein m and n are depth map pixel points, S is a pixel point neighborhood range, (m)x,my) Is the coordinate of m pixel points, (n)x,ny) Is the coordinate of n pixel points, FmIs the original value of pixel point m, G is the weighted average calculation function, GσIs a Gaussian function, InIs the pixel value of pixel point n, sigma is the parameter of the Gaussian function, DnIs the pixel point area range. The Gaussian filtering is a linear smooth filtering processing method, and has a good suppression effect on Gaussian noise; the gaussian filtering is to apply the weighted average to image processing, so that the weighted average is calculated for the pixel itself and other pixel values in the neighborhood, and a new pixel value is obtained.
In addition, the depth map can be preprocessed through a median filter, and the specific calculation process is as follows:
t(x,y)＝mid{f(x-m,y-n),(m,n∈w)}；
wherein f (x, y) is the depth image before median filtering, t (x, y) is the image after median filtering, (m, n) is the filtering window, and w is the size of the filtering window. The median filtering is a nonlinear filtering means, has a good protection effect on the edge and the sharpness of the depth map, and can effectively remove detail noise. The selection of the three processing means may be selected according to actual conditions, and the quality of the depth map may be improved by denoising the depth map by some other means, which is not limited herein.
And step 205, calculating the height information of the cake blank to be processed according to the depth map after filtering processing.
And step 206, acquiring the current coding value of the transmission shaft of the conveyor belt through the encoder.
And step 207, calculating a difference value between the obtained previous-time encoding numerical value and the current encoding numerical value to obtain an encoding numerical value increment, and performing differential calculation on the encoding numerical value increment to obtain an encoding numerical value acceleration.
And 208, judging whether the acceleration of the coded numerical value is in a preset range, if so, judging that the current coded numerical value is not an error code, and otherwise, judging that the current coded numerical value is the error code.
And 209, when the current coding numerical value is an error code, performing coding prediction according to a preset coding numerical value, and taking a prediction result as the current coding numerical value.
It should be noted that the encoder outputs an n-bit binary code, and the distribution of the encoded values has a time characteristic when the encoder rotates. The obtained current coding value needs to be further verified for accuracy, namely error code detection, the encoder can record the coding values at all times before the current time, and then difference processing is carried out on the coding value at the current time and the coding value at the previous time to obtain a coding value increment:
g(t)＝y(t)-y(t-Δt)；
wherein, y (t) is the current coding value, y (t-delta t) is the coding value at the previous moment, and g (t) is the coding value increment obtained by calculation at the current moment. And g (t) is subjected to primary differential processing, so that the encoded numerical acceleration can be obtained:
wherein
To encode numerical acceleration.
The preset range is set according to the actual situation, and is set to (-alpha, alpha) in the embodiment, if the acceleration of the coding numerical value is within the preset range, the current coding numerical value is not mutated, so the current coding numerical value is not an error code; if the acceleration of the coding numerical value is not in the preset range, the current coding numerical value is shown to have mutation, and the error code is judged. And if the current coding numerical value is an error code, the next path planning cannot be carried out by adopting the value, the current coding numerical value is directly discarded, then coding prediction is carried out according to the preset coding numerical value to obtain a new coding numerical value, and the coding numerical value is taken as the current coding numerical value to carry out subsequent path planning. The preset coding value is obtained by integrating the coding values recorded by the encoder at a plurality of moments and has certain representativeness, so that a new coding value obtained by adopting the preset coding value for prediction is more reliable.
And step 210, planning a path according to the plane coordinates, the height information and the current coding numerical value to obtain a target motion track.
And step 211, performing egg liquid brushing operation according to the target motion track.
It should be noted that the specific path planning and egg brushing process are similar to those in step 105-106, and are not described herein again.
For convenience of understanding, the present application also provides an application system adopting the egg brushing liquid manipulator path planning method in the embodiment of the present application, please refer to fig. 4, and the system mainly includes a conveyor belt, a three-dimensional scanner, an encoder, a computer, a robot with a manipulator, a controller for controlling the robot, and the like. In the specific working process, the conveyor belt is used for conveying a cake blank to be processed; the three-dimensional scanner is used for scanning a cake blank to be processed on the conveyor belt, acquiring a three-dimensional image, namely a gray level image and a depth image, of the cake blank to be processed, feeding the acquired image back to the computer, processing the image through the computer, calculating and the like to obtain plane coordinates and height information, and the encoder is installed on the conveyor belt and used for recording the current encoding numerical value of a transmission shaft of the conveyor belt and also needs to send the current encoding numerical value to the computer for error code detection and processing to obtain a more accurate current encoding numerical value; the computer can plan according to the plane coordinate, the height information and the current coding numerical value to obtain a target motion track, and the target motion track is sent to the robot controller, so that the robot controller controls the robot with the manipulator to conduct egg liquid painting work according to the target motion track, and the task of automatically painting egg liquid by the whole robot is completed.
For easy understanding, referring to fig. 3, the present application further provides an embodiment of a path planning apparatus for an egg brushing robot, including:
the first acquisition module 301 is configured to acquire a three-dimensional image of a cake blank to be processed on a conveyor belt through a three-dimensional scanner, where the three-dimensional image includes a grayscale image and a depth image;
a coordinate calculation module 302, configured to extract a target biscuit region image from the grayscale image, and calculate a planar coordinate of a biscuit to be processed according to the target biscuit region image;
a height calculating module 303, configured to calculate height information of the cake blank to be processed according to the filtered depth map;
a second obtaining module 304, configured to obtain, through an encoder, a current encoded value of a transmission shaft of the conveyor belt;
a path planning module 305, configured to perform path planning according to the plane coordinate, the height information, and the current coding value to obtain a target motion trajectory;
and the egg liquid brushing module 306 is used for performing egg liquid brushing operation according to the target motion track.
As a further improvement, the method further comprises the following steps:
a preprocessing module 307, configured to perform preprocessing operations of corrosion and expansion on the grayscale map to obtain a preprocessed grayscale map;
correspondingly, extracting the target biscuit region image from the gray-scale image specifically comprises the following steps:
and extracting an image of the target biscuit area from the preprocessed gray-scale image.
As a further improvement, the filtering process includes:
and carrying out mean filtering processing on the depth map by adopting a mask with a preset size to obtain the filtered depth map.
As a further improvement, the method further comprises the following steps:
the error code detection module 308 is configured to perform error code detection on the current coding value by using a preset coding value;
and the coding prediction module 309 is configured to perform coding prediction according to a preset coding value when the current coding value is an error code, and use a prediction result as the current coding value.
As a further improvement, the error detection module 308 specifically includes:
the calculation submodule 3081 is used for performing difference calculation according to the obtained previous-time encoding numerical value and the current encoding numerical value to obtain an encoding numerical value increment, and performing differential calculation on the encoding numerical value increment to obtain an encoding numerical value acceleration;
the judging submodule 3082 is configured to judge whether the acceleration of the encoded numerical value is within a preset range, if so, the current encoded numerical value is not an error code, otherwise, the current encoded numerical value is an error code.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. 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 application 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 application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). 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 embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should 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 in the embodiments of the present application.
Claims (8)
1. A path planning method of an egg brushing manipulator is characterized by comprising the following steps:
acquiring a three-dimensional image of a cake blank to be processed on a conveyor belt through a three-dimensional scanner, wherein the three-dimensional image comprises a gray level image and a depth image;
extracting a target biscuit area image from the gray-scale image, and calculating the plane coordinate of the biscuit to be processed according to the target biscuit area image;
calculating the height information of the cake blank to be processed according to the depth map after filtering processing;
acquiring a current coding numerical value of a transmission shaft of the conveyor belt through an encoder;
adopting a preset code value to carry out error code detection on the current code value;
when the current coding numerical value is an error code, performing coding prediction according to the preset coding numerical value, and taking a prediction result as the current coding numerical value;
performing path planning according to the plane coordinates, the height information and the current coding numerical value to obtain a target motion track;
and carrying out egg liquid brushing operation according to the target motion track.
2. The path planning method of the egg brushing liquid manipulator according to claim 1, wherein the extracting a target biscuit region image from the gray scale image and calculating the plane coordinates of the biscuit to be processed according to the target biscuit region image further comprise:
carrying out preprocessing operation of corrosion and expansion on the gray-scale image to obtain a preprocessed gray-scale image;
correspondingly, the extracting of the target biscuit region image in the gray-scale image specifically comprises:
and extracting an image of a target biscuit area from the preprocessing gray-scale image.
3. The path planning method of the egg brushing liquid manipulator according to claim 1, wherein the filtering process comprises:
and carrying out mean filtering processing on the depth map by adopting a mask with a preset size to obtain the depth map after filtering processing.
4. The path planning method of the egg brushing manipulator according to claim 1, wherein the performing error code detection on the current code value by using the preset code value comprises:
performing difference calculation according to the obtained previous-time coding numerical value and the current coding numerical value to obtain a coding numerical value increment, and performing differential calculation on the coding numerical value increment to obtain a coding numerical value acceleration;
and judging whether the acceleration of the coding numerical value is in a preset range, if so, judging that the current coding numerical value is not an error code, and if not, judging that the current coding numerical value is the error code.
5. The utility model provides a path planning device of brush egg liquid manipulator which characterized in that includes:
the device comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a three-dimensional image of a cake blank to be processed on a conveyor belt through a three-dimensional scanner, and the three-dimensional image comprises a gray scale image and a depth image;
the coordinate calculation module is used for extracting a target biscuit region image from the gray-scale image and calculating the plane coordinate of the biscuit to be processed according to the target biscuit region image;
the height calculating module is used for calculating the height information of the cake blank to be processed according to the depth map after filtering processing;
the second acquisition module is used for acquiring the current coding numerical value of the transmission shaft of the conveyor belt through the coder;
the error code detection module is used for carrying out error code detection on the current coding value by adopting a preset coding value;
the coding prediction module is used for carrying out coding prediction according to the preset coding numerical value when the current coding numerical value is an error code, and taking a prediction result as the current coding numerical value;
the path planning module is used for planning a path according to the plane coordinate, the height information and the current coding numerical value to obtain a target motion track;
and the egg liquid brushing module is used for brushing egg liquid according to the target motion track.
6. The path planning device of the egg brushing manipulator according to claim 5, further comprising:
the preprocessing module is used for carrying out preprocessing operation of corrosion and expansion on the gray-scale image to obtain a preprocessed gray-scale image;
correspondingly, the extracting of the target biscuit region image in the gray-scale image specifically comprises:
and extracting an image of a target biscuit area from the preprocessing gray-scale image.
7. The path planning device of the egg brushing liquid manipulator according to claim 5, wherein the filtering process comprises:
and carrying out mean filtering processing on the depth map by adopting a mask with a preset size to obtain the depth map after filtering processing.
8. The path planning device of the egg brushing liquid manipulator of claim 5, wherein the error code detection module specifically comprises:
the calculation submodule is used for performing difference calculation according to the obtained coded value at the previous moment and the current coded value to obtain a coded value increment, and performing differential calculation on the coded value increment to obtain a coded value acceleration;
and the judgment submodule is used for judging whether the acceleration of the coded numerical value is within a preset range, if so, the current coded numerical value is not an error code, and otherwise, the current coded numerical value is the error code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011090929.XA CN112091992B (en) | 2020-10-13 | 2020-10-13 | Path planning method and device of egg brushing liquid manipulator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011090929.XA CN112091992B (en) | 2020-10-13 | 2020-10-13 | Path planning method and device of egg brushing liquid manipulator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112091992A CN112091992A (en) | 2020-12-18 |
| CN112091992B true CN112091992B (en) | 2022-03-01 |
Family
ID=73783622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011090929.XA Active CN112091992B (en) | 2020-10-13 | 2020-10-13 | Path planning method and device of egg brushing liquid manipulator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112091992B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101619076B1 (en) * | 2009-08-25 | 2016-05-10 | 삼성전자 주식회사 | Method of detecting and tracking moving object for mobile platform |
| CN106826815B (en) * | 2016-12-21 | 2019-05-31 | 江苏物联网研究发展中心 | The method with positioning is identified based on the target object of color image and depth image |
| CN106733686B (en) * | 2016-12-22 | 2018-09-25 | 北京理工大学 | A kind of assembly line object positioning method of view-based access control model and code-disc data fusion |
| CN109874821A (en) * | 2017-12-06 | 2019-06-14 | 西安仁科电子科技有限公司 | The automatic brush egg liquid device baked for moon cake |
| CN209850931U (en) * | 2019-03-15 | 2019-12-27 | 长沙智能机器人研究院有限公司 | Automatic grabbing robot |
| CN111311621B (en) * | 2020-01-20 | 2023-12-29 | 北京中科核安科技有限公司 | Image processing method and device for radioactive source imaging and electronic equipment |
| CN111483803B (en) * | 2020-04-17 | 2022-03-04 | 湖南视比特机器人有限公司 | Control method, capture system and storage medium |
-
2020
- 2020-10-13 CN CN202011090929.XA patent/CN112091992B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112091992A (en) | 2020-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109596634B (en) | Cable defect detection method and device, storage medium and processor | |
| AU2015284524B2 (en) | Detecting tooth wear using intra-oral 3D scans | |
| CN110286124B (en) | Machine vision-based refractory brick measuring system | |
| CN109580630B (en) | Visual inspection method for defects of mechanical parts | |
| CN111721259A (en) | Underwater robot recovery positioning method based on binocular vision | |
| CN112651968A (en) | Wood board deformation and pit detection method based on depth information | |
| CN108921813A (en) | Unmanned aerial vehicle detection bridge structure crack identification method based on machine vision | |
| JP2014228357A (en) | Crack detecting method | |
| CN112085651B (en) | Automatic shock wave detection and tracking algorithm based on image self-adaptive threshold and feature extraction | |
| CN111311618A (en) | Circular arc workpiece matching and positioning method based on high-precision geometric primitive extraction | |
| CN115035050A (en) | Method, device, equipment and product for detecting surface defects of battery pole piece | |
| CN115131444A (en) | Calibration method based on monocular vision dispensing platform | |
| CN112085675A (en) | Depth image denoising method, foreground segmentation method and human motion monitoring method | |
| CN116704209B (en) | Quick flange contour extraction method and system | |
| CN111523611A (en) | Gluing detection method | |
| CN112884746A (en) | Character defect intelligent detection algorithm based on edge shape matching | |
| CN114266768B (en) | Method for generating surface scratch defect image | |
| CN110047146B (en) | Error correction method based on single revolving body image 3D restoration | |
| CN110288517B (en) | Projection matching group-based skeleton line extraction method | |
| CN112091992B (en) | Path planning method and device of egg brushing liquid manipulator | |
| CN114820656A (en) | Coronary artery extraction method and system based on spatial sorting self-supervision learning | |
| CN108182707B (en) | Chessboard grid calibration template under incomplete collection condition and automatic identification method thereof | |
| CN112338898B (en) | Image processing method and device of object sorting system and object sorting system | |
| CN110853097A (en) | Biscuit identification and positioning method applied to biscuit surface pattern printing equipment | |
| CN113160313A (en) | Transparent object grabbing control method and device, terminal and storage medium |
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 |