CN118032661A

CN118032661A - Object defect detection and calibration method, device and system

Info

Publication number: CN118032661A
Application number: CN202410445803.1A
Authority: CN
Inventors: 魏锦启; 许晋诚
Original assignee: Parsini Perception Technology Zhangjiagang Co ltd
Current assignee: Parsini Perception Technology Zhangjiagang Co ltd
Priority date: 2024-04-15
Filing date: 2024-04-15
Publication date: 2024-05-14
Anticipated expiration: 2044-04-15
Also published as: CN118032661B

Abstract

The embodiment of the application belongs to the technical field of defect detection of objects, and relates to a defect detection method of an object, which comprises the following steps: after the object is calibrated, a second shadow image of each light source on the surface of the object is obtained; based on the second shadow image, second normal information of the surface of the object is obtained; comparing the difference between the first normal information and the second normal information of the object surface before the object calibration; and generating a defect detection result of the calibrated object surface based on the difference. The application also provides a related object calibration method, an object defect detection and calibration device, an object processing system and the like. The technical scheme adopted by the application can reduce the cost on the basis of detecting the identification degree of the defect detection of the object.

Description

Object defect detection and calibration method, device and system

Technical Field

The present application relates to the field of object defect detection technologies, and in particular, to a method, an apparatus, and a system for detecting and calibrating an object defect.

Background

Existing defect detection techniques for objects (e.g., force/touch sensors including curved surfaces) mainly employ machine vision methods, which have the disadvantage of requiring a large number of negative samples (defect samples) as training data/recognition data to train a model or adjust a recognition strategy. However, in the actual industrial production scene, the negative samples are few, so that the detection rate is low and the generalization is poor. In addition, the existing device for detecting the defects of the object is mainly used for detecting the defects based on images acquired by RGBD cameras, and has the defects of low identification precision and strict requirements on illumination environment (such as no interference of infrared light sources), and the detected object has strict requirements (such as no high reflectivity and absorption rate of visible light and infrared light of the detected object).

Disclosure of Invention

The embodiment of the application aims to provide a method, a device and a system for detecting and calibrating defects of an object so as to reduce cost on the basis of detecting and identifying the defects of the object.

In a first aspect, an embodiment of the present application provides a method for detecting a defect of an object, including the following technical solutions:

a defect detection method of an object, the defect detection method comprising the steps of:

after the object is calibrated, a second shadow image of each light source on the surface of the object is obtained;

based on the second shadow image, second normal information of the surface of the object is obtained;

Comparing the difference between the first normal information and the second normal information of the object surface before the object calibration;

And generating a defect detection result of the calibrated object surface based on the difference.

Further, in one embodiment, the light sources are at least three different color light sources, and the optical axes of any two light sources are not parallel; the step of obtaining second normal information of the object surface based on the second shadow image comprises the following steps:

Based on the second shadow image, solving the second normal information by combining formula (1);

（1）

Wherein E represents the light source intensity, L represents the light source direction vector, N represents the second normal information, and P represents the reflectivity of the object surface; m represents the pixel light intensity of the second shadow image.

Further, in one embodiment, the difference between the first normal information and the second normal information of the object surface before the calibration of the comparison object includes the following steps:

calculating average differences AD between the first normal information and the corresponding second normal information of a plurality of detection points based on a formula (2);

（2）

Wherein, First normal information representing an ith detection point; second normal information representing an ith detection point; n represents the total number of detection points;

Solving a single-point difference between the first normal information and the second normal information of each detection point based on a formula (3);

（3）

Wherein, Representing a single point difference; first normal information representing a single detection point; And second normal information representing a single detection point.

Further, in one embodiment, the generating the defect detection result of the calibrated object surface based on the difference includes the following steps:

The average difference and the single difference are combined to generate the defect detection result of the object.

Further, in one embodiment, after the calibration of the object, before the second shadow image of each light source on the surface of the object is acquired, the defect detection method further includes the following steps:

Before the object calibration, acquiring a first shadow image of each light source on the surface of the object;

And obtaining first normal information of the surface of the object based on the first shadow image.

Further, in one embodiment, after the first normal information of the object surface is obtained based on the first shadow image; after the object is calibrated, before the second shadow image of each light source on the surface of the object is acquired, the defect detection method further comprises the following steps:

And generating a motion instruction based on the first normal information to instruct an actuator to apply a calibration acting force to the surface of the object so as to finish the object calibration.

In a second aspect, an embodiment of the present application provides a method for calibrating an object, including the following technical solutions:

a method of calibrating an object, the method comprising the steps of:

Obtaining first normal information of the surface of the object based on the first shadow image;

In a third aspect, an embodiment of the present application provides a processing system for an object, including the following technical solutions:

a system for processing an object, the system comprising: an image acquisition device, an actuator and a controller;

The image acquisition device includes: an image sensor and at least three different color light sources; the at least three different-color light sources are arranged around the object, and the optical axes of any two light sources are not parallel;

the actuator includes: an actuator body and an end effector;

The controller is respectively in communication connection with the image acquisition device and the actuator;

The controller for implementing the steps of the defect detection method of an object as described in any one of the above; and/or the steps of the method of calibrating an object described above.

In a fourth aspect, an embodiment of the present application provides a defect detection apparatus for an object, the defect detection apparatus including:

the second acquisition module is used for acquiring a second shadow image of each light source on the surface of the object after the object is calibrated;

The second solving module is used for solving second normal information of the surface of the object based on the second shadow image;

The difference comparison module is used for comparing the difference between the first normal information and the second normal information of the object surface before the object calibration;

And the defect detection module is used for generating a defect detection result of the calibrated object surface based on the difference.

In a fifth aspect, an embodiment of the present application provides an apparatus for calibrating an object, where the apparatus includes:

the first acquisition module is used for acquiring a first shadow image of each light source on the surface of the object before the object is calibrated;

The first solving module is used for solving first normal information of the object surface based on the first shadow image;

And the object calibration module is used for generating a motion instruction based on the first normal information so as to instruct the actuator to apply a calibration acting force to the surface of the object, thereby completing the object calibration.

In a sixth aspect, an embodiment of the present application provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements defect detection of an object described above when the computer program is executed; and/or, a calibration method of the object.

In a seventh aspect, the present examples provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements defect detection of an object as described above; and/or, a calibration method of the object.

Compared with the prior art, the embodiment of the application has the following main beneficial effects:

The embodiment of the application compares the difference between the first normal information before the object calibration and the second normal information after the calibration; the defect detection result of the object surface is calculated based on the difference, the accuracy requirements of a real acquisition light source and vision acquisition equipment can be reduced, and negative samples are not required to be acquired for training, so that the cost of hardware, software and the like is reduced on the basis of detecting the defect detection recognition degree.

In addition, the embodiment of the application can realize the functions of object calibration and/or object defect detection based on the same system, thereby effectively reducing the overall hardware cost.

In addition, in the embodiment of the application, the force applied during the calibration of the object is not a vector predefined according to the design drawing, but a proper force vector sequence distribution is given according to the individual difference of the detected object in production, so that the quantification of the difference between the manufacturing result of the hardware of the object and the design parameter is realized, and the calibration accuracy is improved.

Drawings

In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.

FIG. 1 is a system architecture diagram of one embodiment of a processing system for objects of the present application;

FIG. 2 is a schematic representation of one embodiment of normal information of an object surface of the present application;

FIG. 3 is a flow chart of one embodiment of a method of defect detection of an object of the present application;

FIG. 4 is a flow chart of one embodiment of a method of calibrating an object of the present application;

FIG. 5 is a block diagram of one embodiment of a defect detection apparatus for objects of the present application;

FIG. 6 is a block diagram of one embodiment of a calibration device for an object of the present application;

FIG. 7 is a schematic diagram of an embodiment of a computer device of the present application.

Detailed Description

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.

As shown in fig. 1, fig. 1 is a system architecture diagram of one embodiment of a processing system for objects of the present application.

The embodiment of the application provides an object processing system 100, which can complete object calibration and object defect detection based on the same processing system.

For convenience of understanding, the embodiment of the present application will be described in detail with reference to the force/touch sensor 200 including a curved surface as an example, and in addition, the object of the embodiment of the present application may be set to other objects with similar performance according to needs. The surface of the object may be any of various shapes such as a curved surface and a plane surface, and the present application is not limited thereto.

Wherein the force/tactile sensor 200 refers to a force sensor and/or a tactile sensor.

The force sensor may be, but is not limited to: a two-dimensional or multi-dimensional force sensor for measuring data of a two-dimensional or multi-dimensional force.

Tactile sensors are a type of sensing device that can be placed on an end effector or the like to measure contact force information. Implementations of the tactile sensor include flexible contact surfaces, sensing circuitry, computing devices, and contact force information parsing algorithms.

In particular, the force/touch sensor may comprise one integral sensing unit or a plurality of sensing units arranged in an array, etc., all falling within the scope of the present application.

An embodiment of the present application provides a processing system 100 for an object, the system comprising: an image acquisition device 110, an actuator 120, and a controller 130.

Image acquisition device

The image pickup device 110 includes: an image sensor 111 and at least three different color light sources; at least three different colored light sources are disposed around the object with the optical axes of any two light sources not being parallel.

As shown in fig. 1, in one embodiment, the three different color light sources include: a red light source 112, a blue light source 113, and a green light source 114. By using three primary colors of light, the object shadow corresponding to each color of light can be obtained by capturing an object image at one time in the latter embodiment. In addition, light sources with other colors can be adopted according to the requirement, if light with other colors is adopted, multiple shooting may be required to obtain shadows of corresponding objects under each light source. Three monochromatic light sources are disposed around the force/touch sensor 200.

The number of the light sources is at least 3, and any of 3 or more light sources may be used as needed. The plurality of light sources ensures at least three different colors.

In one embodiment, three different color light sources are substantially equidistantly encircling the object under test, which can improve the accuracy of the calculation result. In addition, three light sources can be arranged at other angles and positions as required, and as long as the axial directions of any two light sources are not parallel, the light sources belong to the protection scope of the application, wherein the axial directions of the light sources refer to the light propagation directions.

Actuator

The effector 120 may include an effector body 121 and an end effector 122.

Specifically, the actuator may be, but is not limited to: robots (e.g., robotic arms or humanoid robots); an XYZ stage or an actuator comprising an XYZ stage. For convenience of understanding, the embodiment of the application mainly uses an actuator as an example of a mechanical arm for detailed description.

The actuating end of the actuator body 121 is provided with an end effector 122 to apply a force for object calibration to the surface of the object through the end effector.

Controller for controlling a power supply

The controller 130 is connected to the image sensor 111, the actuator 121, and the like by wired or wireless communication. For limitations on the controller, reference is made to the description of the object surface defect detection method in the following embodiments.

It should be noted that the wireless connection may include, but is not limited to, 3G/4G/5G connection, wiFi connection, bluetooth connection, wiMAX connection, zigbee connection, UWB (ultra wideband) connection, and other now known or later developed wireless connection.

The controller in the embodiment of the application can be, but is not limited to: a computer terminal (Personal Computer, PC); an industrial control computer terminal (Industrial Personal Computer, IPC); a mobile terminal; a server; the system comprises a terminal and a server, and is realized through interaction between the terminal and the server; a programmable logic controller (Programmable Logic Controller, PLC); a Field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA); a Digital signal processor (Digital SignalProcesser, DSP) or a micro-control unit (Microcontroller unit, MCU). The controller generates program instructions in accordance with a program fixed in advance in conjunction with data output from the image sensor, the actuator, and the like. By way of example, may be applied to a computer device as shown in fig. 7.

The controller 130 according to the embodiment of the present application may be an independent controller, or may be fully or partially integrated in the image capturing device 110, the actuator 120, etc., which is not limited by the present application.

It should be noted that, the image acquisition device, the actuator, the object and the like mentioned in the embodiment of the application can be a real object in a real environment or a virtual object in a simulation platform, so as to achieve the effect of connecting the real object through the simulation environment. The controller which depends on the virtual environment to complete training can be transplanted to the real environment to control or retrain the real object, and resources and time of the training process can be saved.

In one embodiment, the method for detecting defects of an object provided by the embodiments of the present application is generally performed by the controller 130 of the processing system of an object described in fig. 1 of the above embodiments, and accordingly, the defect detecting device for an object is generally disposed in the controller 130 of the processing system of an object.

As shown in fig. 3, fig. 3 is a flow chart illustrating an embodiment of a defect detection method of an object of the present application. The embodiment of the application provides a defect detection method of an object, which comprises the following method steps:

Step 210 obtains a second shadow image of each light source on the surface of the object after the object is calibrated.

Step 220 obtains second normal information of the object surface based on the second shadow image.

Step 230 compares the difference between the first normal information and the second normal information of the object surface before the object calibration.

Step 240 generates a calibrated object surface defect detection result based on the difference.

For ease of understanding, the method steps described above are described in further detail below.

In one embodiment, after the object is calibrated, the controller acquires a second shadow image of the object under the irradiation of at least three monochromatic light sources or the second shadow image after some preprocessing, which is acquired based on the image sensor, from the memory or the server according to a preset address. Specifically, the calibration method can be calibrated by adopting various existing or future developed method steps.

It should be noted that, based on the foregoing embodiment, the second shadow image may be an image including a plurality of shadows formed by a plurality of light sources; in addition, a plurality of images may be provided, each of which includes a shadow formed by a corresponding one of the light sources.

In the embodiment of the application, the force/touch sensor is taken as an example, and the force/touch sensor is possibly damaged in the calibration process (for example, the surface of the force/touch sensor is damaged and sunken in the process of controlling the actuator to press the force/touch sensor), so that the defect detection method disclosed by the embodiment of the application is used for detecting the defects of the calibrated force/touch sensor.

In one embodiment, step 220 may comprise the following method steps:

step 221 obtains second normal information of the object surface based on the second shadow image in combination with equation (1).

（1）

Wherein E represents the light source intensity, L represents the light source direction vector, N represents the second normal information, P represents the reflectivity of the object surface, and M is the pixel light intensity of the second shadow image.

In the embodiment of the application, under the condition that three different color light sources are provided and the optical axes of any two light sources are not parallel, the normal vector N (namely second normal information) of the surface of the measured object can be solved based on the formula (1).

As shown in fig. 2, fig. 2 is a schematic diagram of one embodiment of model normal information of an object surface of the present application. By way of example, the second normal information N of the object surface as shown in fig. 2 can be obtained based on the formula (1).

In the embodiment of the application, as each variable in the formula (1) is a matrix, vectors of all directions on the surface of the object can be solved at one time.

In one embodiment, step 230 may include the following method steps:

Step 231 obtains an average difference AD (AerageDistance) between the first normal information and the corresponding second normal information of the plurality of detection points based on formula (2).

（2）

Wherein,First normal information representing an ith detection point; Second normal information representing an ith detection point; n represents the total number of detection points.

Specifically, the mathematical meaning of the above formula (2) is the Average Difference (AD) between the two vector sets, which can reflect the average difference across the surface.

Step 232 obtains a single point difference Dj between the first normal information and the corresponding second normal information of each detection point based on formula (3).

（3）

Wherein,Representing a single point difference; first normal information representing a single detection point; And second normal information representing a single detection point.

In one embodiment, step 240 may comprise the following method steps:

step 241 combines the average difference and the individual differences to generate a defect detection result for the object.

In one embodiment, it may be assumed that the average difference threshold is t_1 and the single point difference threshold is t_2.

When AD is greater than t_1 or Dj is greater than t_2, it is considered to be unacceptable (the actual surface is too different from the design surface).

According to the embodiment of the application, the average difference between the first normal information and the second normal information corresponding to the detection points and the single-point difference between the first normal information and the second normal information corresponding to each detection point can be respectively obtained through the method steps. In practical application, not only the individual with overlarge average error but also the individual with overlarge partial point error are detected, and defect evaluation is respectively carried out from two angles, and any evaluation result is considered to be defective if error exists, so that the recognition precision of final defect detection can be improved overall.

In addition, defect detection is performed based on the normal information difference, the shape of the object surface is not limited, the defect detection can be performed on the object surface with various shapes including curved surfaces, planes and the like, and the application range of the object surface defect detection is improved.

In an embodiment, before step 210, the method for detecting a defect of an object according to the embodiment of the present application may further include the following method steps:

step 240 acquires a first shadow image of each light source on the surface of the object prior to object calibration.

In one embodiment, the controller acquires a first shadow image of the object under the irradiation of at least three monochromatic light sources or the first shadow image after some preprocessing from the memory or the server according to a preset address before the object is calibrated.

For other descriptions of the first shadow image, reference may be made to the second shadow image, and no further description is repeated here.

Step 250 finds first normal information of the object surface based on the first shadow image.

In one embodiment, step 250 may comprise the following method steps:

Step 251 obtains first normal information of the object surface based on the first shadow image in combination with equation (4).

（4）

Wherein E represents the light source intensity, L represents the light source direction vector, N 'represents the first normal information, P represents the reflectivity of the object surface, and M' represents the pixel light intensity of the first shadow image.

According to the embodiment of the application, through the method steps, the first normal information detection is carried out on the object before the object calibration.

In one embodiment, after step 250 and before step 210, the method for detecting defects of an object according to the embodiment of the present application may further include the following method steps:

step 260 generates a motion command based on the first normal information to instruct the actuator to apply a calibration force to the surface of the object to complete the calibration of the object.

Specifically, the motion command may be generated based on the first normal information in various existing or future developed manners to instruct the actuator to apply the calibration force to the surface of the object so as to complete the calibration of the object.

In one embodiment, the direction vector of the calibration force is the same as the vector direction of the first normal information.

In the embodiment of the application, the force applied during the object calibration is not a vector predefined according to the design drawing, but a proper force vector sequence distribution is given according to the individual difference of the detected object in production, so that the quantification of the difference between the manufacturing result of the hardware of the object and the design parameter is realized, and the calibration accuracy is improved.

It should be noted that, the contact points of the actuator applying the contact force to the surface of the object may be uniformly or randomly generated on the surface of the object to be measured according to the need. The abundance of data distributed on the surface of the object at the contact point may depend on the structure of the object to be measured and the accuracy of each region, for example, when the measured object is a matrix load cell, the accuracy of the region with more calibration detection points after calibration may be higher than that of other regions, so that denser contact points may be required.

In one implementation, the calibration detection points of the object surface are usually multiple, so that the processing system according to the previous embodiment can enable the structures such as the protrusions provided on the end effector in the effector to apply the contact force at one or more contact points of the object surface based on the motion command, so as to achieve the point contact with the object surface.

In one embodiment, the method for calibrating an object provided by the embodiments of the present application is generally performed by the controller 130 of the object handling system described in the above embodiment fig. 1, and accordingly, the calibration device for an object is generally disposed in the controller 130 of the object handling system.

FIG. 3 is a flow chart of one embodiment of the calibration method of the object of the present application, as shown in FIG. 3. The embodiment of the application provides a method for calibrating an object, which comprises the following method steps:

step 310 acquires a first shadow image of each light source at the surface of the object.

Step 320 finds first normal information of the object surface based on the first shadow image.

In one embodiment, step 320 may include the following method steps:

step 321 obtains first normal information of the object surface based on the first shadow image in combination with equation (4).

（4）

Step 330 generates a motion command based on the first normal information to instruct the actuator to apply a calibration force to the surface of the object to complete the calibration of the object.

For further description of steps 310 to 330, refer to the above embodiments, and are not repeated here.

Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored in a computer-readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

With further reference to fig. 5, as an implementation of the method shown in fig. 3, the present application provides an embodiment of an apparatus for detecting defects of an object, which corresponds to the embodiment of the method for detecting defects of an object shown in fig. 3, and which is particularly applicable to various controllers.

As shown in fig. 3, the defect detecting apparatus 200 of an object according to an embodiment of the present application may include:

a second obtaining module 210, configured to obtain a second shadow image of each light source on the surface of the object after the calibration of the object;

A second calculating module 220, configured to calculate second normal information of the object surface based on the second shadow image;

The difference comparison module 230 is configured to compare a difference between the first normal information and the second normal information of the object surface before the object calibration;

The defect detection module 240 is configured to generate a defect detection result of the calibrated object surface based on the difference.

In one embodiment, the light sources are at least three different color light sources, and the optical axes of any two light sources are not parallel; the second solving module 220 may include:

the first solving sub-module is used for solving second normal information based on the second shadow image by combining the formula (1);

（1）

In one embodiment, the difference contrast module 230 may include:

the average calculating sub-module is used for calculating average difference AD between the first normal information and the corresponding second normal information of the plurality of detection points based on the formula (2);

（2）

The single-point calculating sub-module is used for calculating the single-point difference between the first normal information and the corresponding second normal information of each detection point based on the formula (3);

（3）

In one embodiment, the defect detection module 240 may include:

The result generation sub-module 241 is configured to generate a defect detection result of the object by combining the average difference and the single difference.

In one embodiment, after the calibration of the object, before the second shadow image of each light source on the surface of the object is acquired, the defect detecting device 200 may further include:

the first solving module is used for solving first normal information of the object surface based on the first shadow image.

Further, in one embodiment, the first solving module may include:

The first solving sub-module is used for solving the first normal information of the object surface based on the first shadow image and in combination with the formula (4).

（4）

In one embodiment, after obtaining the first normal information of the surface of the object based on the first shadow image, after the calibration of the object, before obtaining the second shadow image of each light source on the surface of the object, the defect detecting apparatus 200 may further include:

And the sensor calibration module is used for generating a motion instruction based on the first normal information so as to instruct the actuator to apply a calibration acting force to the surface of the object, thereby completing the object calibration.

With further reference to fig. 6, as an implementation of the method shown in fig. 4, the present application provides an embodiment of an apparatus for calibrating an object, which corresponds to the embodiment of the method for calibrating an object shown in fig. 4, and which is particularly applicable to various controllers.

As shown in fig. 3, the calibration device 300 of the object according to the embodiment of the present application includes:

A first acquiring module 310, configured to acquire a first shadow image of each light source on the surface of the object before the calibration of the object;

A first obtaining module 320, configured to obtain first normal information of the object surface based on the first shadow image;

The object calibration module 330 is configured to generate a motion instruction based on the first normal information, so as to instruct the actuator to apply a calibration force to the surface of the object, thereby completing the object calibration.

In one embodiment, the first solving module 320 may include:

（4）

Referring specifically to fig. 7, in order to solve the above technical problem, an embodiment of the present application further provides a controller (taking the computer device 6 as an example).

The computer device 6 comprises a memory 61, a processor 62, a network interface 63 communicatively connected to each other via a system bus. It is noted that only computer device 6 having components 61-63 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a Programmable gate array (Field-Programmable GATE ARRAY, FPGA), a digital Processor (DIGITAL SIGNAL Processor, DSP), an embedded device, and the like.

The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.

The memory 61 includes at least one type of readable storage media including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 61 may be an internal storage unit of the computer device 6, such as a hard disk or a memory of the computer device 6. In other embodiments, the memory 61 may also be an external storage device of the computer device 6, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the computer device 6. Of course, the memory 61 may also comprise both an internal memory unit of the computer device 6 and an external memory device. In this embodiment, the memory 61 is typically used to store an operating system and various application software installed on the computer device 6, such as program codes of a defect detection and/or calibration method of an object, and the like. Further, the memory 61 may be used to temporarily store various types of data that have been output or are to be output.

The processor 62 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 62 is typically used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is configured to execute the program code stored in the memory 61 or process data, such as program code of a defect detection and/or calibration method for an object.

The network interface 63 may comprise a wireless network interface or a wired network interface, which network interface 63 is typically used for establishing a communication connection between the computer device 6 and other electronic devices.

The present application also provides another embodiment, namely, a computer readable storage medium storing a defect detection and/or calibration program of an object, where the defect detection and/or calibration program of the object is executable by at least one processor, so that the at least one processor performs the steps of the defect detection and/or calibration method of the object as described above.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.

It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.

Claims

1. A method of detecting a defect in an object, the method comprising the steps of:

2. The defect detection method of an object according to claim 1, wherein the light sources are at least three different-color light sources, and optical axes of any two light sources are not parallel; the step of obtaining second normal information of the object surface based on the second shadow image comprises the following steps:

（1）

3. The method for detecting defects of an object according to claim 1 or 2, wherein the difference between the first normal information and the second normal information of the object surface before the calibration of the comparison object comprises the steps of:

（2）

Wherein, First normal information representing an ith detection point; /(I)Second normal information representing an ith detection point; n represents the total number of detection points;

（3）

Wherein, Representing a single point difference; /(I)First normal information representing a single detection point; /(I)And second normal information representing a single detection point.

4. A method of detecting defects in an object according to claim 3, wherein said generating a result of detecting defects in the surface of the object after calibration based on said difference comprises the steps of:

5. The method for detecting defects of an object according to claim 1 or 2, wherein after the object is calibrated, before the second shadow image of each light source on the surface of the object is obtained, the method for detecting defects further comprises the steps of:

6. The method according to claim 5, wherein after the first normal information of the object surface is obtained based on the first shadow image; after the object is calibrated, before the second shadow image of each light source on the surface of the object is acquired, the defect detection method further comprises the following steps:

7. A method of calibrating an object, the method comprising the steps of:

8. A system for processing an object, the system comprising: an image acquisition device, an actuator and a controller;

the actuator includes: an actuator body and an end effector;

The controller for implementing the steps of the defect detection method of an object according to any one of claims 1 to 6; and/or the steps of the method for calibrating an object according to claim 7.

9. A defect detection apparatus for an object, the defect detection apparatus comprising:

10. An apparatus for calibrating an object, the apparatus comprising: