CN116026837A - White household appliance appearance detection method and system and electronic equipment thereof - Google Patents
White household appliance appearance detection method and system and electronic equipment thereof Download PDFInfo
- Publication number
- CN116026837A CN116026837A CN202211613773.8A CN202211613773A CN116026837A CN 116026837 A CN116026837 A CN 116026837A CN 202211613773 A CN202211613773 A CN 202211613773A CN 116026837 A CN116026837 A CN 116026837A
- Authority
- CN
- China
- Prior art keywords
- detected
- standard
- household appliance
- white household
- depth
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a white household appliance appearance detection method, a system and electronic equipment thereof, which comprise the steps of setting a rectangular detection area on a conveyor belt, placing a standard white household appliance on the rectangular detection area of the conveyor belt, when a light detection module detects that the rectangular detection area coincides with a to-be-detected station, controlling the conveyor belt to stop, acquiring standard depth images of all sides of the standard white household appliance except the bottom surface through depth cameras arranged at preset positions, placing the to-be-detected white household appliance on the rectangular detection area of the conveyor belt, when the light detection module detects that the rectangular detection area coincides with the to-be-detected station, controlling the conveyor belt to stop, acquiring to-be-detected depth images of all sides of the standard white household appliance except the bottom surface through depth cameras arranged at preset positions, analyzing the standard depth images and the to-be-detected depth images of all sides of the to-be-detected white household appliance, and judging whether flaws exist in the appearance of the to-be-detected white household appliance or not based on analysis results. The detection efficiency and the detection precision are greatly improved.
Description
Technical Field
The invention relates to the technical field of appearance detection of household appliances, in particular to a white household appliance appearance detection method, a white household appliance appearance detection system and electronic equipment.
Background
The white household appliances such as refrigerators and washing machines are more in appearance defect types in the production process, risks of increasing appearance defects exist in each production link, such as a plurality of defects including relatively large depressions, greasy dirt, powder points in the spraying process, scratches in the assembling process, hairlines and the like are accompanied with the process, the defects are difficult to remove one by one under the condition of human vision, meanwhile, the defects are input by a plurality of manpower, the resource waste of enterprises can be caused, and defective products flow into the market to bring adverse effects to consumer satisfaction and brand image. In the existing household appliance detection method, household appliances are required to be placed on a conveying mechanism for conveying, household appliances are positioned on a detection station through a positioning device, a driving mechanism is utilized to drive a detection assembly to move along the height direction of the conveying mechanism, so that a plurality of cameras installed on a frame are driven to automatically detect the appearance of the products, and due to the limitation of resolution of the traditional cameras and the influence of ambient light, the detection accuracy is low, and the detection assembly needs to move back and forth, so that the detection efficiency is low.
Accordingly, the prior art is subject to further development.
Disclosure of Invention
The invention aims to overcome the technical defects and provide a white household appliance appearance detection method, a white household appliance appearance detection system and electronic equipment, so as to solve the problems in the prior art.
To achieve the above object, according to a first aspect of the present invention, there is provided a white appliance appearance detection method, the method comprising:
setting a rectangular detection area on a conveyor belt, placing a standard white household appliance on the rectangular detection area of the conveyor belt, when the light detection module detects that the rectangular detection area coincides with a to-be-detected station, controlling the conveyor belt to stop, acquiring standard depth images of all sides of the standard white household appliance except the bottom surface through depth cameras arranged at preset positions, placing the to-be-detected white household appliance on the rectangular detection area of the conveyor belt, when the light detection module detects that the rectangular detection area coincides with the to-be-detected station, controlling the conveyor belt to stop, acquiring to-be-detected depth images of all sides of the standard white household appliance except the bottom surface through depth cameras arranged at preset positions, analyzing the standard depth images and the to-be-detected depth images of all sides of the standard white household appliance except the bottom surface, and judging whether flaws exist in the appearance of the to-be-detected white household appliance based on analysis results.
Specifically, set up the rectangle detection zone on the conveyer belt, place standard white household electrical appliances on the rectangle detection zone of conveyer belt, when detecting rectangle detection zone and waiting to detect the station coincidence, control conveyer belt stop specifically does:
the utility model provides a white household electrical appliances, including conveyer belt, rectangle detection zone, light detection point, light sensor, light detection point, conveyer belt, light detection point and light detection point, the rectangle detection zone on the conveyer belt is the rectangle for showing the position that should place before waiting to detect white household electrical appliances detects the outward appearance, wait to detect the station and be the rectangle, set up subaerial, whether through detecting rectangle detection zone and wait to detect the station and coincide and realize the position of waiting to detect white household electrical appliances for each depth camera before detecting, rectangle detection zone sets up a plurality of, sets up to follow the direction interval of conveyer belt and sets up to a plurality of, the lower surface of conveyer belt is provided with the pointolite corresponding to the center of every rectangle detection zone, the conveyer belt sets up on the mount, be provided with light sensor on the mount, when light detection point detects the light signal that the light detection point sent, the conveyer belt stops, at this moment, rectangle detection zone on the conveyer belt coincides with waiting to detect the station, places standard white household electrical appliances on the rectangle detection zone, and the left side of light sensor is provided with first depth camera and first depth camera is first preset height, and the right side of light sensor is provided with second depth camera and second depth camera is high to the first preset.
Specifically, the standard depth images of all sides except the bottom surface of the standard white household appliance are obtained by the depth cameras arranged at all preset positions, and specifically:
when the standard white household appliance is placed on the forefront rectangular detection area of the conveyor belt, the standard depth images on the left side and the right side of the standard white household appliance are acquired through the first depth camera arranged on the left side and the second depth camera arranged on the right side of the light sensor, and the standard depth images on the front side, the rear side and the upper side of the standard white household appliance are acquired through the depth camera groups which are arranged above the light sensor and distributed at intervals.
Specifically, the standard depth images of the front side, the rear side and the upper side of the standard white household appliance are obtained through the depth camera set arranged above the light sensor at intervals, and specifically are:
the depth camera set comprises a third depth camera, a fourth depth camera and a fifth depth camera which are distributed along the same straight line at intervals according to a preset distance, so that the third depth camera can acquire standard depth images of the front side and the upper side of the standard white household appliance, and the fifth depth camera can acquire standard depth images of the upper side and the rear side of the standard white household appliance.
Specifically, the analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface and judging whether the appearance of the white household appliance to be detected has flaws based on the analysis result comprises the following steps:
firstly, analyzing a standard depth image to obtain a set of standard depth arrays in standard depth image data, counting points with the distance within the range of d1+/-dsigma in the image, storing coordinates in the array Ad1, counting to obtain the maximum value, the minimum value and the maximum value and the minimum value of the abscissa in the array Ad1, establishing a target search frame M1 according to the maximum value, the minimum value and the maximum value and the minimum value of the ordinate in the Ad1, establishing a standard mark lattice in the target search frame, and obtaining standard distance data of each standard mark point in the standard mark lattice and a depth camera of the currently analyzed depth image.
Specifically, the analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface, and judging whether the appearance of the white household appliance to be detected has flaws based on the analysis result further comprises:
analyzing a depth image to be detected to obtain a set of depth arrays to be detected in the depth image data, counting points with the distance within the range of d1+/-dsigma in the image, storing coordinates in the array Ad1, counting to obtain the maximum value, the minimum value and the maximum value and the minimum value of the abscissa in the array Ad1, establishing a target search frame M1 according to the maximum value, the minimum value and the maximum value and the minimum value of the ordinate in the abscissa Ad1, establishing a mark lattice to be detected in the target search frame, and obtaining the distance data to be detected between each mark point to be detected in the mark lattice to be detected and a depth camera shooting the current analyzed depth image.
Specifically, the analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface, and judging whether the appearance of the white household appliance to be detected has flaws based on the analysis result further comprises:
and carrying out one-to-one correspondence on the to-be-detected mark lattices of each surface of the to-be-detected white household appliance except the bottom surface and the standard mark lattices, calculating to-be-detected distance data of each to-be-detected mark point in the to-be-detected mark lattices and standard distance data corresponding to the to-be-detected mark points one by one, and finishing to obtain an actual distance difference value set, and outputting an alarm signal related to the appearance defect of the current to-be-detected white household appliance if the data quantity of the actual distance difference value which is larger than or equal to the first preset threshold value in the actual distance difference value set is larger than or equal to the second preset threshold value.
Specifically, if the data amount of the actual distance difference value greater than or equal to the first preset threshold value in the actual distance difference value set is smaller than the second preset threshold value, the detection conveyor belt is controlled to continue to move, and detection of the next white household appliance to be detected is continued.
According to a second aspect of the present invention, there is provided a white goods appearance detection system comprising:
the acquisition module is used for acquiring standard depth images of all sides of the standard white household appliance except the bottom surface; or the depth image to be detected of each surface except the bottom surface of the white household appliance to be detected is obtained;
the control module is used for analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface and judging whether the appearance of the white household appliance to be detected has flaws or not based on the analysis result; or the alarm module is used for controlling the alarm module to output an alarm signal related to the appearance defect of the white household appliance to be detected currently; or for controlling the conveyor belt to stop;
the alarm module is used for outputting an alarm signal related to the appearance defect of the white household appliance to be detected currently;
the conveyor belt is used for conveying the standard white household appliances and the white household appliances to be detected;
and the light detection module is used for detecting whether the rectangular detection area on the conveyor belt coincides with the station to be detected.
According to a third aspect of the present invention, there is provided an electronic device comprising:
a memory; and a processor having stored thereon computer readable instructions which when executed by the processor implement the white appliance appearance detection method according to any one of claims 1 to 8.
The beneficial effects of the invention are as follows:
1. according to the invention, whether the appearance of the white household appliance has flaws or not is judged by utilizing the depth images acquired by the multiple depth cameras arranged at multiple angles, the analysis result is affected by visible light, fine appearance flaws can be found, and the accuracy of the analysis result is greatly improved.
2. According to the method, the actual distance difference value is obtained through calculation of the standard distance data and the distance data to be detected, whether the data amount of the actual distance difference value which is larger than or equal to the first preset threshold value in the actual distance difference value set is larger than or equal to the second preset threshold value is judged, the abstract appearance detection problem is visualized and simplified, and complex algorithm modeling is not needed.
3. In the technical scheme of the invention, when the data amount of the actual distance difference value which is larger than or equal to the first preset threshold value in the actual distance difference value set is larger than or equal to the second preset threshold value, the fact that the to-be-detected household appliance has larger appearance flaws is proved, at the moment, an alarm signal about the appearance flaws of the to-be-detected white household appliance is output to inform a worker to carry out subsequent processing, if the to-be-detected white household appliance has no larger appearance flaws, the conveyor belt is controlled to continue to convey until the next rectangular detection area coincides with the to-be-detected station, the to-be-detected white household appliance does not need to be frequently conveyed or a depth camera is not required to be frequently moved, and the detection efficiency and the reliability of detection results are greatly improved.
4. The algorithm designed by the invention realizes that the white household appliances to be detected and the standard white household appliances are not required to be accurately positioned and placed before detection, and only the white household appliances to be detected and the standard white household appliances are required to be placed in the rectangular detection area on the conveyor belt, so that the directions of the standard white household appliances and the white household appliances to be detected are consistent, the working flow is further simplified, and the practicability of the invention is greatly improved.
5. According to the invention, the white household appliance to be detected is placed on the conveyor belt, the depth camera for detection is fixed, and the white household appliance to be detected is detected, and as the depth camera is adopted, the floodlight illuminator in the depth camera can emit unstructured infrared light to be projected onto the surface of the white household appliance to be detected, and then the infrared camera receives the light and then detects whether the white household appliance to be detected is the white household appliance to be detected, if yes, the lattice projector can project tens of thousands of structured light patterns invisible to the naked eyes onto the surface of the white household appliance to be detected, the infrared lens receives the reflected lattice patterns, and the distances of different positions of the white household appliance to be detected are obtained by calculating the deformation condition of the patterns, so that the accuracy of analysis results is greatly improved.
Drawings
Fig. 1 is a flowchart of a method for detecting the appearance of a white household appliance according to an embodiment of the present invention;
fig. 2 is a block diagram of a white household appliance appearance detection system according to an embodiment of the present invention.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings, and based on the embodiments in the present application, other similar embodiments obtained by those skilled in the art without making creative efforts should fall within the scope of protection of the present application. In addition, directional words such as "upper", "lower", "left", "right", and the like, as used in the following embodiments are merely directions with reference to the drawings, and thus, the directional words used are intended to illustrate, not to limit, the invention.
The invention will be further described with reference to the drawings and preferred embodiments.
Referring to fig. 1, the present embodiment provides a method for detecting the appearance of a white household appliance, where the method for detecting the appearance of the white household appliance includes:
and S100, setting a rectangular detection area on the conveyor belt, placing a standard white household appliance on the rectangular detection area of the conveyor belt, and controlling the conveyor belt to stop when the light detection module detects that the rectangular detection area coincides with a station to be detected.
Specifically, set up the rectangle detection zone on the conveyer belt, place standard white household electrical appliances on the rectangle detection zone of conveyer belt, when detecting rectangle detection zone and waiting to detect the station coincidence, control conveyer belt stop specifically does:
the utility model provides a white household electrical appliances, including conveyer belt, rectangle detection zone, light detection point, light sensor, light detection point, conveyer belt, light detection point and light detection point, the rectangle detection zone on the conveyer belt is the rectangle for showing the position that should place before waiting to detect white household electrical appliances detects the outward appearance, wait to detect the station and be the rectangle, set up subaerial, whether through detecting rectangle detection zone and wait to detect the station and coincide and realize the position of waiting to detect white household electrical appliances for each depth camera before detecting, rectangle detection zone sets up a plurality of, sets up to follow the direction interval of conveyer belt and sets up to a plurality of, the lower surface of conveyer belt is provided with the pointolite corresponding to the center of every rectangle detection zone, the conveyer belt sets up on the mount, be provided with light sensor on the mount, when light detection point detects the light signal that the light detection point sent, the conveyer belt stops, at this moment, rectangle detection zone on the conveyer belt coincides with waiting to detect the station, places standard white household electrical appliances on the rectangle detection zone, and the left side of light sensor is provided with first depth camera and first depth camera is first preset height, and the right side of light sensor is provided with second depth camera and second depth camera is high to the first preset.
The step S100 is preceded by: the method comprises the steps of presetting a first preset threshold value, a second preset threshold value, a third preset threshold value, a first preset height and a second preset height, drawing a rectangular detection area on the upper surface of a conveyor belt, setting a point light source at the center of the lower surface of the conveyor belt corresponding to each rectangular detection area, drawing a station to be detected on the ground, wherein the center of the rectangular detection area is the center position of the intersection point of two diagonal lines of the rectangular detection area, the size and the shape of the work to be detected are consistent with those of the rectangular detection area, a light sensor is arranged at the center of the fixed frame corresponding to the station to be detected, and when the light sensor detects a light signal emitted by the light detection point, the conveyor belt stops, and at the moment, the rectangular detection area on the conveyor belt coincides with the vertical projection of the station to be detected on the ground so as to realize the positioning before detection of white household appliances to be detected and standard white household appliances.
S200, acquiring standard depth images of all sides of the standard white household appliance except the bottom surface through depth cameras arranged at all preset positions.
Specifically, the standard depth images of all sides except the bottom surface of the standard white household appliance are obtained by the depth cameras arranged at all preset positions, and specifically:
when the standard white household appliance is placed on the forefront rectangular detection area of the conveyor belt, the standard depth images on the left side and the right side of the standard white household appliance are acquired through the first depth camera arranged on the left side and the second depth camera arranged on the right side of the light sensor, and the standard depth images on the front side, the rear side and the upper side of the standard white household appliance are acquired through the depth camera groups which are arranged above the light sensor and distributed at intervals.
Here, the acquiring, by the depth camera set disposed above the light sensor and spaced apart from each other, the standard depth images of the front side, the rear side and the upper side of the standard white home appliance specifically includes:
the depth camera set comprises a third depth camera, a fourth depth camera and a fifth depth camera which are distributed along the same straight line at intervals according to a preset distance, so that the third depth camera can acquire standard depth images of the front side and the upper side of the standard white household appliance, and the fifth depth camera can acquire standard depth images of the upper side and the rear side of the standard white household appliance. The heights of the third depth camera, the fourth depth camera and the fifth depth camera from the ground are second preset heights, and the standard white household appliance and the standard household appliance to be detected can be conveyed from the lower parts of the third depth camera, the fourth depth camera and the fifth depth camera through the conveying belt. It can be understood that the position of the third depth camera should make the area difference between the front side and the upper side of the standard white household appliance in the standard depth images obtained by the third depth camera not exceed a third preset threshold, the position of the fifth depth camera should make the area difference between the upper side and the rear side of the standard white household appliance in the standard depth images obtained by the fifth depth camera not exceed the third preset threshold, and the third depth camera and the fifth depth camera can better and more uniformly analyze the distance data of each point in the front side, the upper side and the rear side of the white household appliance to be detected in the following process, so that the application scene of the invention is further improved.
And S300, placing the white household appliance to be detected on a rectangular detection area of the conveyor belt, controlling the conveyor belt to stop when the light detection module detects that the rectangular detection area coincides with the station to be detected, and acquiring depth images to be detected of all sides of the standard white household appliance except the bottom surface through depth cameras arranged at all preset positions.
The method includes the steps that an actual distance difference value is obtained through calculation of standard distance data and distance data to be detected, whether the data amount of the actual distance difference value which is larger than or equal to a first preset threshold value in an actual distance difference value set is larger than or equal to a second preset threshold value is judged, abstract appearance detection problems are embodied and simplified, complex algorithm modeling is not needed, when the data amount of the actual distance difference value which is larger than or equal to the first preset threshold value in the actual distance difference value set is larger than or equal to the second preset threshold value, the fact that the household appliance to be detected has larger appearance flaws is proved, at the moment, an alarm signal which is related to the appearance flaws of the white household appliance to be detected is output to inform workers to carry out subsequent processing, if the white household appliance to be detected does not have larger appearance flaws, a next rectangular detection area is controlled to coincide with a to be detected station, the white household appliance to be detected does not need to be frequently carried, the efficiency of the detection is greatly improved, the reliability of a detection result is greatly improved, the algorithm is designed, the fact that the white household appliance to be detected and the white household appliance to be accurately positioned and placed before detection is not needed, the white household appliance to be detected is accurately positioned and placed, and the white appliance to be detected is placed on the standard household appliance is required to be detected, and the white appliance is placed on the white appliance to be detected by the standard area is greatly is further and is enabled to face to be more than the standard household appliance to be detected.
S400, analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface, and judging whether flaws exist in the appearance of the white household appliance to be detected based on the analysis result.
Specifically, the analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface and judging whether the appearance of the white household appliance to be detected has flaws based on the analysis result comprises the following steps:
firstly, analyzing a standard depth image to obtain a set of standard depth arrays in standard depth image data, counting points with the distance within the range of d1+/-dsigma in the image, storing coordinates in the array Ad1, counting to obtain the maximum value, the minimum value and the maximum value and the minimum value of the abscissa in the array Ad1, establishing a target search frame M1 according to the maximum value, the minimum value and the maximum value and the minimum value of the ordinate in the Ad1, establishing a standard mark lattice in the target search frame, and obtaining standard distance data of each standard mark point in the standard mark lattice and a depth camera of the currently analyzed depth image.
Specifically, the analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface, and judging whether the appearance of the white household appliance to be detected has flaws based on the analysis result further comprises:
analyzing a depth image to be detected to obtain a set of depth arrays to be detected in the depth image data, counting points with the distance within the range of d1+/-dsigma in the image, storing coordinates in the array Ad1, counting to obtain the maximum value, the minimum value and the maximum value and the minimum value of the abscissa in the array Ad1, establishing a target search frame M1 according to the maximum value, the minimum value and the maximum value and the minimum value of the ordinate in the abscissa Ad1, establishing a mark lattice to be detected in the target search frame, and obtaining the distance data to be detected between each mark point to be detected in the mark lattice to be detected and a depth camera shooting the current analyzed depth image.
Specifically, the analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface, and judging whether the appearance of the white household appliance to be detected has flaws based on the analysis result further comprises:
and carrying out one-to-one correspondence on the to-be-detected mark lattices of each surface of the to-be-detected white household appliance except the bottom surface and the standard mark lattices, calculating to-be-detected distance data of each to-be-detected mark point in the to-be-detected mark lattices and standard distance data corresponding to the to-be-detected mark points one by one, and finishing to obtain an actual distance difference value set, and outputting an alarm signal related to the appearance defect of the current to-be-detected white household appliance if the data quantity of the actual distance difference value which is larger than or equal to the first preset threshold value in the actual distance difference value set is larger than or equal to the second preset threshold value.
Specifically, if the data amount of the actual distance difference value greater than or equal to the first preset threshold value in the actual distance difference value set is smaller than the second preset threshold value, the detection conveyor belt is controlled to continue to move, and detection of the next white household appliance to be detected is continued.
The invention uses the depth camera, the floodlight illuminator in the depth camera can emit unstructured infrared light to project on the surface of the white household appliance to be detected, then the infrared camera receives the light to detect whether the white household appliance to be detected is the white household appliance to be detected, if yes, the lattice projector can project tens of thousands of structural light patterns invisible to eyes on the surface of the white household appliance to be detected, the infrared lens receives the reflected lattice patterns, and the distance between different positions of the white household appliance to be detected is obtained by calculating the deformation condition of the patterns, thereby greatly improving the accuracy of analysis results.
Referring to fig. 2, another embodiment of the present invention provides a white appliance appearance detection system, which includes:
the acquisition module 1 is used for acquiring standard depth images of all sides of the standard white household appliance except the bottom surface; or the depth image to be detected of each surface except the bottom surface of the white household appliance to be detected is obtained;
the control module 2 is used for analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface and judging whether the appearance of the white household appliance to be detected has flaws or not based on the analysis result; or the alarm module 3 is used for controlling the alarm module 3 to output an alarm signal related to the appearance defect of the white household electrical appliance to be detected currently; or for controlling the conveyor belt to stop;
the alarm module 3 is used for outputting an alarm signal related to the appearance defect of the white household appliance to be detected currently;
a conveyor belt 4 for conveying standard white household appliances and white household appliances to be detected;
and the light detection module 5 is used for detecting whether the rectangular detection area on the conveyor belt 4 coincides with a station to be detected on the ground.
In a preferred embodiment, the present application further provides an electronic device, including:
a memory; and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions implement the white appliance appearance detection method when executed by the processor. The computer device may be broadly a server, a terminal, or any other electronic device having the necessary computing and/or processing capabilities. In one embodiment, the computer device may include a processor, memory, network interface, communication interface, etc. connected by a system bus. The processor of the computer device may be used to provide the necessary computing, processing and/or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. The non-volatile storage medium may have an operating system, computer programs, etc. stored therein or thereon. The internal memory may provide an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface and communication interface of the computer device may be used to connect and communicate with external devices via a network. Which when executed by a processor performs the steps of the method of the invention.
The present invention may be implemented as a computer readable storage medium having stored thereon a computer program which, when executed by a processor, causes steps of a method of an embodiment of the present invention to be performed. In one embodiment, the computer program is distributed over a plurality of computer devices or processors coupled by a network such that the computer program is stored, accessed, and executed by one or more computer devices or processors in a distributed fashion. A single method step/operation, or two or more method steps/operations, may be performed by a single computer device or processor, or by two or more computer devices or processors. One or more method steps/operations may be performed by one or more computer devices or processors, and one or more other method steps/operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step/operation or two or more method steps/operations.
Those of ordinary skill in the art will appreciate that the method steps of the present invention may be implemented by a computer program, which may be stored on a non-transitory computer readable storage medium, to instruct related hardware such as a computer device or a processor, which when executed causes the steps of the present invention to be performed. Any reference herein to memory, storage, database, or other medium may include non-volatile and/or volatile memory, as the case may be. Examples of nonvolatile memory include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage, hard disk, solid state disk, and the like. Examples of volatile memory include Random Access Memory (RAM), external cache memory, and the like.
The technical features described above may be arbitrarily combined. Although not all possible combinations of features are described, any combination of features should be considered to be covered by the description provided that such combinations are not inconsistent.
The above-described embodiments of the present invention do not limit the scope of the present invention. Any other corresponding changes and modifications made in accordance with the technical idea of the present invention shall be included in the scope of the claims of the present invention.
Claims (10)
1. A white household appliance appearance detection method is characterized in that a rectangular detection area is arranged on a conveyor belt, standard white household appliances are placed on the rectangular detection area of the conveyor belt, when a light detection module detects that the rectangular detection area coincides with a to-be-detected station, the conveyor belt is controlled to stop, standard depth images of all sides of the standard white household appliances except the bottom surface are obtained through depth cameras arranged at preset positions, the to-be-detected white household appliances are placed on the rectangular detection area of the conveyor belt, when the light detection module detects that the rectangular detection area coincides with the to-be-detected station, the conveyor belt is controlled to stop, to-be-detected depth images of all sides of the standard white household appliances except the bottom surface are obtained through depth cameras arranged at preset positions, the standard depth images and the to-be-detected depth images of all sides of the to-be-detected white household appliances except the bottom surface are analyzed, and whether flaws exist in the appearance of the to-be-detected white household appliances is judged based on analysis results.
2. The method for detecting the appearance of a white household appliance according to claim 1, wherein a rectangular detection area is arranged on the conveyor belt, a standard white household appliance is placed on the rectangular detection area of the conveyor belt, and when the rectangular detection area is detected to coincide with a station to be detected, the conveyor belt is controlled to stop specifically:
the utility model provides a white household electrical appliances, including conveyer belt, rectangle detection zone, light detection point, light sensor, light detection point, conveyer belt, light detection point and light detection point, the rectangle detection zone on the conveyer belt is the rectangle for showing the position that should place before waiting to detect white household electrical appliances detects the outward appearance, wait to detect the station and be the rectangle, set up subaerial, whether through detecting rectangle detection zone and wait to detect the station and coincide and realize the position of waiting to detect white household electrical appliances for each depth camera before detecting, rectangle detection zone sets up a plurality of, sets up to follow the direction interval of conveyer belt and sets up to a plurality of, the lower surface of conveyer belt is provided with the pointolite corresponding to the center of every rectangle detection zone, the conveyer belt sets up on the mount, be provided with light sensor on the mount, when light detection point detects the light signal that the light detection point sent, the conveyer belt stops, at this moment, rectangle detection zone on the conveyer belt coincides with waiting to detect the station, places standard white household electrical appliances on the rectangle detection zone, and the left side of light sensor is provided with first depth camera and first depth camera is first preset height, and the right side of light sensor is provided with second depth camera and second depth camera is high to the first preset.
3. The method for detecting the appearance of a white household appliance according to claim 2, wherein the step of obtaining the standard depth image of each face of the standard white household appliance except the bottom face by the depth camera arranged at each preset position comprises the following steps:
when the standard white household appliance is placed on the forefront rectangular detection area of the conveyor belt, the standard depth images on the left side and the right side of the standard white household appliance are acquired through the first depth camera arranged on the left side and the second depth camera arranged on the right side of the light sensor, and the standard depth images on the front side, the rear side and the upper side of the standard white household appliance are acquired through the depth camera groups which are arranged above the light sensor and distributed at intervals.
4. The method for detecting the appearance of a white household appliance according to claim 2, wherein the step of acquiring the standard depth images of the front side, the rear side and the upper side of the standard white household appliance by the depth camera set arranged above the light sensor at intervals is specifically:
the depth camera set comprises a third depth camera, a fourth depth camera and a fifth depth camera which are distributed along the same straight line at intervals according to a preset distance, so that the third depth camera can acquire standard depth images of the front side and the upper side of the standard white household appliance, and the fifth depth camera can acquire standard depth images of the upper side and the rear side of the standard white household appliance.
5. The method for detecting the appearance of a white household appliance according to claim 1, wherein analyzing the standard depth image and the depth image of each surface of the white household appliance except the bottom surface, and judging whether the appearance of the white household appliance to be detected has flaws based on the analysis result comprises:
firstly, analyzing a standard depth image to obtain a set of standard depth arrays in standard depth image data, counting points with the distance within the range of d1+/-dsigma in the image, storing coordinates in the array Ad1, counting to obtain the maximum value, the minimum value and the maximum value and the minimum value of the abscissa in the array Ad1, establishing a target search frame M1 according to the maximum value, the minimum value and the maximum value and the minimum value of the ordinate in the Ad1, establishing a standard mark lattice in the target search frame, and obtaining standard distance data of each standard mark point in the standard mark lattice and a depth camera of the currently analyzed depth image.
6. The method according to claim 5, wherein analyzing the standard depth image and the depth image of each surface of the white appliance to be detected except the bottom surface and judging whether the appearance of the white appliance to be detected has flaws based on the analysis result further comprises:
analyzing a depth image to be detected to obtain a set of depth arrays to be detected in the depth image data, counting points with the distance within the range of d1+/-dsigma in the image, storing coordinates in the array Ad1, counting to obtain the maximum value, the minimum value and the maximum value and the minimum value of the abscissa in the array Ad1, establishing a target search frame M1 according to the maximum value, the minimum value and the maximum value and the minimum value of the ordinate in the abscissa Ad1, establishing a mark lattice to be detected in the target search frame, and obtaining the distance data to be detected between each mark point to be detected in the mark lattice to be detected and a depth camera shooting the current analyzed depth image.
7. The method for detecting the appearance of a white household appliance according to claim 6, wherein analyzing the standard depth image and the depth image of each surface of the white household appliance except the bottom surface, and judging whether the appearance of the white household appliance to be detected has flaws based on the analysis result, further comprises:
and carrying out one-to-one correspondence on the to-be-detected mark lattices of each surface of the to-be-detected white household appliance except the bottom surface and the standard mark lattices, calculating to-be-detected distance data of each to-be-detected mark point in the to-be-detected mark lattices and standard distance data corresponding to the to-be-detected mark points one by one, and finishing to obtain an actual distance difference value set, and outputting an alarm signal related to the appearance defect of the current to-be-detected white household appliance if the data quantity of the actual distance difference value which is larger than or equal to the first preset threshold value in the actual distance difference value set is larger than or equal to the second preset threshold value.
8. The method for detecting the appearance of a white household appliance according to claim 7, wherein,
and if the data quantity of the actual distance difference value which is larger than or equal to the first preset threshold value in the actual distance difference value set is smaller than the second preset threshold value, controlling the detection conveyor belt to continue to move, and continuing to detect the next white household appliance to be detected.
9. A white goods appearance detection system, comprising:
the acquisition module is used for acquiring standard depth images of all sides of the standard white household appliance except the bottom surface; or the depth image to be detected of each surface except the bottom surface of the white household appliance to be detected is obtained;
the control module is used for analyzing the standard depth image and the depth image of each surface of the white household appliance to be detected except the bottom surface and judging whether the appearance of the white household appliance to be detected has flaws or not based on the analysis result; or the alarm module is used for controlling the alarm module to output an alarm signal related to the appearance defect of the white household appliance to be detected currently; or for controlling the conveyor belt to stop;
the alarm module is used for outputting an alarm signal related to the appearance defect of the white household appliance to be detected currently;
the conveyor belt is used for conveying the standard white household appliances and the white household appliances to be detected;
and the light detection module is used for detecting whether the rectangular detection area on the conveyor belt coincides with the station to be detected.
10. An electronic device, comprising:
a memory; and a processor having stored thereon computer readable instructions which when executed by the processor implement the white appliance appearance detection method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211613773.8A CN116026837A (en) | 2022-12-15 | 2022-12-15 | White household appliance appearance detection method and system and electronic equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211613773.8A CN116026837A (en) | 2022-12-15 | 2022-12-15 | White household appliance appearance detection method and system and electronic equipment thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116026837A true CN116026837A (en) | 2023-04-28 |
Family
ID=86076861
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211613773.8A Pending CN116026837A (en) | 2022-12-15 | 2022-12-15 | White household appliance appearance detection method and system and electronic equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116026837A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118469993A (en) * | 2024-06-07 | 2024-08-09 | 元数仓数字科技(上海)有限公司 | Intelligent automatic picking system based on Internet of things |
-
2022
- 2022-12-15 CN CN202211613773.8A patent/CN116026837A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118469993A (en) * | 2024-06-07 | 2024-08-09 | 元数仓数字科技(上海)有限公司 | Intelligent automatic picking system based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111246204B (en) | Relative brightness deviation-based dirt detection method and device | |
| KR102022496B1 (en) | Process management and monitoring system using vision image detection and a method thereof | |
| US20190238796A1 (en) | Object Inspection System And Method For Inspecting An Object | |
| CN110132166B (en) | Product image detection method capable of automatically distributing light and comparison device | |
| US20090297020A1 (en) | Method and system for determining poses of semi-specular objects | |
| CN110336691B (en) | Management method, device, equipment and communication system of equipment in data center | |
| CN107470170A (en) | PCB detection sorting systems and method based on machine vision | |
| CN109213202B (en) | Goods placement method, device, equipment and storage medium based on optical servo | |
| CN108120353B (en) | Fire transmission hole detection device and method based on intelligent camera | |
| CN107504917B (en) | Three-dimensional size measuring method and device | |
| CN116026837A (en) | White household appliance appearance detection method and system and electronic equipment thereof | |
| CN107588777B (en) | Indoor positioning system | |
| CN114813783A (en) | Chip surface flaw detection method | |
| CN109191516B (en) | Rotation correction method and device of structured light module and readable storage medium | |
| CN109991237A (en) | Painting dressing automobiles skirt glue vision detection system and method | |
| CN105424721A (en) | Metal strain gauge defect automatic detection system | |
| US11748838B2 (en) | System and method for three-dimensional scan of moving objects longer than the field of view | |
| CN114445494A (en) | Image acquisition and processing method, image acquisition device and robot | |
| CN205333535U (en) | Metal strainometer defect automatic check out system | |
| CN117522830A (en) | Point cloud scanning system for detecting boiler corrosion | |
| CN113888408A (en) | Multi-camera image acquisition method and device | |
| EP3660452B1 (en) | Positioning system and positioning method | |
| CN116385868A (en) | Building monitoring system based on image recognition and patrol robot thereof | |
| CN114264243B (en) | Method for detecting crimping welding spots and measuring wire arc height between crimping welding spots | |
| CN111375884A (en) | Automatic welding line tool setting and tracking system based on random phase illumination |
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 |