CN114399467B - Case shell detection method and device, electronic equipment and computer readable medium - Google Patents
Case shell detection method and device, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN114399467B CN114399467B CN202111534086.2A CN202111534086A CN114399467B CN 114399467 B CN114399467 B CN 114399467B CN 202111534086 A CN202111534086 A CN 202111534086A CN 114399467 B CN114399467 B CN 114399467B
- Authority
- CN
- China
- Prior art keywords
- shell
- image
- area
- result
- point cloud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the disclosure discloses a chassis shell detection method, a chassis shell detection device, electronic equipment and a medium. One embodiment of the method comprises: controlling a related camera device to shoot a shell area image of each surface of the shell of the target case to obtain a shell area image group; marking a target shell area in the shell gray area image to generate a marked shell gray area image; performing edge detection processing on a labeled target shell area in the shell gray area labeling image to obtain a shell outline corresponding to the target shell area; identifying a shell gray level profile image corresponding to the shell profile from the shell gray level area image; generating a shell point cloud contour map based on the shell gray contour map and a shell point cloud area image corresponding to the shell gray area image; and inputting the shell point cloud profile map into a shell image recognition model trained in advance to obtain a shell image recognition result. This embodiment has promoted the efficiency to chassis exterior detection, has shortened the detection duration.
Description
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a chassis shell detection method, a chassis shell detection device, electronic equipment and a computer readable medium.
Background
At present, for the detection of a computer case shell to be delivered, the general adopted method is as follows: every computer case shell that waits to leave warehouse is detected through the staff to prevent that the computer case shell of damage from flowing out.
However, the following technical problems generally exist in the above detection method:
firstly, the efficiency of detecting the computer case shell is low and the detection time is long through manual detection;
secondly, the detection mode of the computer case shell is single, so that the state of the computer case shell cannot be accurately detected, and abnormal computer case shell outflow is easily caused.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose chassis housing detection methods, apparatuses, electronic devices, and computer readable media to address one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a chassis enclosure detection method, including: controlling a related camera device to shoot a shell area image of each surface of a target case shell to obtain a shell area image group, wherein the shell area images in the shell area image group comprise a shell gray area image and a shell point cloud area image corresponding to the shell gray image; executing the following processing steps for each shell gray scale area image included in the shell area image group: marking a target shell area in the shell gray area image to generate a marked shell gray area image; performing edge detection processing on a labeled target shell area in the labeled shell gray area image to obtain a shell outline corresponding to the target shell area; identifying a shell gray level profile image corresponding to the shell profile from the shell gray level area image; generating a shell point cloud contour map based on the shell gray contour map and a shell point cloud area image corresponding to the shell gray area image; and inputting the shell point cloud profile map into a shell image recognition model trained in advance to obtain a shell image recognition result.
In a second aspect, some embodiments of the present disclosure provide a chassis enclosure detection apparatus, the apparatus comprising: the control unit is configured to control an associated camera to shoot a shell area image of each surface of a target case shell to obtain a shell area image group, wherein the shell area images in the shell area image group comprise a shell gray area image and a shell point cloud area image corresponding to the shell gray area image; an identification unit configured to execute the following processing steps for each shell gray scale region image included in the shell region image group: marking a target shell area in the shell gray area image to generate a marked shell gray area image; performing edge detection processing on a target shell area marked in the shell gray area marked image to obtain a shell outline corresponding to the target shell area; identifying a shell gray contour map corresponding to the shell contour from the shell gray area image; generating a shell point cloud contour map based on the shell gray contour map and a shell point cloud area image corresponding to the shell gray area image; and inputting the shell point cloud contour map into a shell image recognition model trained in advance to obtain a shell image recognition result.
In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method described in any of the implementations of the first aspect.
In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect.
The above embodiments of the present disclosure have the following advantages: by the case shell detection method of some embodiments of the present disclosure, the efficiency of detecting the computer case shell is improved, and the detection time is shortened. Specifically, the reasons for the low efficiency and long detection time of the detection of the computer case casing are as follows: through manual detection, the efficiency of detecting the computer case shell is lower, and the detection time is longer. Based on this, the chassis housing detection method according to some embodiments of the present disclosure first controls the associated imaging device to capture a housing area image of each surface of the target chassis housing, and obtains a housing area image group. Therefore, the target case shell can be conveniently and comprehensively detected subsequently. Then, for each shell gray scale region image included in the shell region image group, the following processing steps are performed: firstly, labeling a target shell area in the shell gray scale area image to generate a labeled shell gray scale area image. Therefore, the area to be detected in the shell gray scale area image can be marked. And secondly, carrying out edge detection processing on the labeled target shell area in the labeled shell gray area image to obtain a shell outline corresponding to the target shell area. Thereby, the shell contour of the area to be detected can be detected. And then, identifying a shell gray level outline image corresponding to the shell outline from the shell gray level area image. And then, generating an outer shell point cloud outline map based on the outer shell gray outline map and an outer shell point cloud area image corresponding to the outer shell gray outline image. Therefore, the computer case shell can be conveniently detected whether to have defects/recesses and other problems. And finally, inputting the shell point cloud profile map into a shell image recognition model trained in advance to obtain a shell image recognition result. Therefore, whether the computer case shell has defects, depressions and other problems can be quickly and accurately detected through the shell image recognition model trained in advance. Therefore, the efficiency of detecting the computer case shell is improved, and the detection time is shortened.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and components are not necessarily drawn to scale.
Fig. 1 is a schematic diagram of an application scenario of a chassis housing detection method of some embodiments of the present disclosure;
fig. 2 is a flow diagram of some embodiments of a chassis enclosure detection method according to the present disclosure;
FIG. 3 is a flow diagram of further embodiments of a chassis enclosure detection method according to the present disclosure;
FIG. 4 is a schematic block diagram view of some embodiments of a chassis housing detection apparatus according to the present disclosure;
FIG. 5 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a" or "an" in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will appreciate that references to "one or more" are intended to be exemplary and not limiting unless the context clearly indicates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a schematic diagram of an application scenario of a chassis housing detection method according to some embodiments of the present disclosure.
In the application scenario of fig. 1, first, the computing device 101 may control the associated camera to capture a shell area image of each surface of the target chassis shell, resulting in a shell area image group 102. The shell area image in the shell area image group includes a shell gray scale area image 1021 and a shell point cloud area image 1022 corresponding to the shell gray scale image. Then, the computing device 101 may perform the following processing steps for each of the shell gray-scale area images 1021 included in the above-described shell area image group: labeling a target shell area in the shell gray area image 1021 to generate a labeled shell gray area image 103; performing edge detection processing on a labeled target shell area in the labeled shell gray area image 103 to obtain a shell outline 104 corresponding to the target shell area; recognizing a shell gray outline image 105 corresponding to the shell outline 104 from the shell gray area image 1021; generating an outer shell point cloud contour map 106 based on the outer shell gray contour map 105 and an outer shell point cloud area image 1022 corresponding to the outer shell gray area image 1021; the shell point cloud contour map 107 is input into a shell image recognition model 107 trained in advance, and a shell image recognition result 108 is obtained.
The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices enumerated above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.
It should be understood that the number of computing devices in FIG. 1 is merely illustrative. There may be any number of computing devices, as implementation needs dictate.
With continued reference to fig. 2, a flow 200 of some embodiments of a chassis enclosure detection method according to the present disclosure is shown. The chassis shell detection method comprises the following steps:
In some embodiments, the performing agent (e.g., computing device 101 shown in fig. 1) of the enclosure detection method may control the associated camera to capture an enclosure area image of each surface of the target enclosure, resulting in an enclosure area image set. The shell area image in the shell area image group comprises a shell gray scale area image and a shell point cloud area image corresponding to the shell gray scale image. Here, the associated camera may be a camera having a 3D photographing function, or other image pickup devices having a 3D photographing function. Here, the target casing may refer to a computer casing to be discharged. Here, the housing area image may refer to an area image including a surface of the target chassis housing. Here, the gray scale coordinates (gray scale pixel coordinates) in the shell gray scale area image have a one-to-one correspondence relationship with the point cloud coordinates in the shell point cloud area image.
In some embodiments, the execution subject may label the target shell area in the shell gray scale area image through image labeling software to generate a labeled shell gray scale area image. Here, the target housing area may refer to an area of the chassis housing displayed in the housing gray scale area image. Here, the image annotation software may include, but is not limited to: a visual image calibration tool (Labelimg) and an image annotation tool (Labelme).
In some embodiments, the executing entity may perform edge detection processing on a target shell area labeled in the labeled shell gray scale area image to obtain a shell contour corresponding to the target shell area. Here, the execution subject may perform edge detection processing on the target shell region labeled in the shell gray scale region labeling image through a pre-trained edge detection model, so as to obtain a shell contour corresponding to the target shell region. For example, the pre-trained edge detection model may be a pre-trained VGG (Visual Geometry Group) model.
In some embodiments, the executing entity may recognize an image area included in the shell contour from the shell gray scale area image as a shell gray scale contour map.
In some embodiments, based on the shell gray scale profile map and the shell point cloud area image corresponding to the shell gray scale area image, the executing subject may generate the shell point cloud profile map by:
the first step is to carry out standardization processing on the shell point cloud area image so as to generate a standardized shell point cloud area image. Here, the normalization process may be referred to as a thinning process.
And secondly, identifying a standardized shell point cloud outline map corresponding to the shell gray outline map from the standardized shell point cloud area image as a shell point cloud outline map. Here, a normalized shell point cloud profile corresponding to the shell gray profile may be identified from the normalized shell point cloud area image as the shell point cloud profile using a correspondence between point cloud coordinates in the normalized shell point cloud area image and gray coordinates in the shell gray profile.
In some embodiments, the executing subject may input the shell point cloud profile into a shell image recognition model trained in advance, so as to obtain a shell image recognition result. Here, the pre-trained shell image recognition model may be a pre-trained image detection model. For example, the pre-trained shell image recognition model may be a VGG model or a VGG16 model.
In practice, the pre-trained shell image recognition model may be obtained by training the following steps:
the method comprises the steps of firstly, determining a network structure of an initial shell image recognition model and initializing network parameters of the initial shell image recognition model.
And secondly, acquiring a training image sample set. The training image sample set comprises a chassis shell point cloud image sample set and a labeling information set corresponding to the chassis shell point cloud image sample set. Here, the annotation information in the annotation information set may refer to description of a chassis shell state corresponding to the chassis shell point cloud image sample. For example, if the chassis shell displayed in the point cloud image sample of the chassis shell is in a rusted state, the labeling information corresponding to the point cloud image sample of the chassis shell is the case shell corrosion.
And thirdly, respectively taking the point cloud image sample set of the chassis shell in the training image sample set and the annotation information set as the input and the expected output of the initial shell image recognition model, and training the initial shell image recognition model by using a deep learning method.
And fourthly, determining the initial shell image recognition model obtained by training as the shell image recognition model trained in advance.
The above embodiments of the present disclosure have the following advantages: by the case shell detection method of some embodiments of the present disclosure, the efficiency of detecting the case shell of the computer is improved, and the detection time is shortened. Specifically, the reasons for the low efficiency and long detection time of the detection of the computer case casing are as follows: through manual detection, the efficiency of detecting the computer case shell is lower, and the detection time is longer. Based on this, the chassis housing detection method of some embodiments of the present disclosure, first, controls the associated camera to capture a housing area image of each surface of the target chassis housing, resulting in a housing area image group. Therefore, the target case shell can be conveniently and comprehensively detected subsequently. Then, for each shell gray scale region image included in the shell region image group, the following processing steps are performed: firstly, labeling a target shell area in the shell gray scale area image to generate a labeled shell gray scale area image. The region to be detected in the shell gray scale region image can be marked. And secondly, performing edge detection processing on the target shell area marked in the shell gray area marked image to obtain a shell outline corresponding to the target shell area. Thereby, the shell contour of the region to be detected can be detected. And then, identifying a shell gray level outline image corresponding to the shell outline from the shell gray level area image. And then, generating a shell point cloud outline map based on the shell gray outline map and a shell point cloud area image corresponding to the shell gray area image. Therefore, the computer case shell can be conveniently detected whether to have defects/recesses and other problems. And finally, inputting the shell point cloud profile map into a shell image recognition model trained in advance to obtain a shell image recognition result. Therefore, whether the computer case shell has defects, depressions and other problems can be quickly and accurately detected through the shell image recognition model trained in advance. Therefore, the efficiency of detecting the computer case shell is improved, and the detection time is shortened.
With further reference to fig. 3, further embodiments of chassis enclosure detection methods according to the present disclosure are illustrated. The detection method of the chassis shell comprises the following steps:
In some embodiments, the specific implementation of step 301 and the technical effect brought by the implementation may refer to step 202 in those embodiments corresponding to fig. 2, and are not described herein again.
And step 3023, identifying a shell gray-scale profile image corresponding to the shell profile from the shell gray-scale area image.
And step 3024, generating a shell point cloud outline map based on the shell gray outline map and the shell point cloud area image corresponding to the shell gray area image.
And step 3025, inputting the shell point cloud profile into a pre-trained shell image recognition model to obtain a shell image recognition result.
In some embodiments, the detailed implementation and technical effects of steps 3021 to 3025 may refer to steps 2021 to 2025 in those embodiments corresponding to fig. 2, which are not described herein again.
In some embodiments, an executing entity (e.g., the computing device 101 shown in fig. 1) of the chassis housing detection method may determine the housing image recognition result as an abnormal housing image recognition result in response to the housing image recognition result satisfying a preset abnormal condition. Here, the preset abnormal condition may be: and the shell image recognition result is a preset result. Here, the preset result may include, but is not limited to, at least one of the following: case shell corrosion, case shell sag, case shell damage, and the like.
In some embodiments, the execution body may control the associated mobile inspection apparatus to perform surface defect inspection on each surface of the target enclosure to generate a surface defect inspection result, so as to obtain a surface defect inspection result set. Here, the associated movement detection device may be a mobile device communicatively connected to the execution main body for detecting whether a defect (such as corrosion, depression, breakage, or the like) exists on the surface of the chassis. For example, the movement detection apparatus may be a mobile robot on which the surface detector is mounted.
In some embodiments, the execution body may determine whether the surface defect detection result satisfies the predetermined abnormal condition.
In some embodiments, the performing body may determine whether the surface defect detection result has a corresponding abnormal shell image recognition result in response to determining that the surface defect detection result satisfies the preset abnormal condition. In practice, the execution body may determine whether an abnormal shell image recognition result identical to the surface of the chassis corresponding to the surface defect detection result exists in each generated abnormal shell image recognition result.
In some embodiments, the performing agent may determine whether the defect result characterized by the surface defect detection result is consistent with the defect result characterized by the abnormal shell image identification result in response to determining that the surface defect detection result has a corresponding abnormal shell image identification result. In practice, the execution subject may determine whether the defect result represented by the surface defect detection result is the same as the defect result represented by the abnormal shell image recognition result.
In some embodiments, the performing agent may determine the surface defect detection result as an abnormal surface defect detection result in response to determining that the defect result characterized by the surface defect detection result is consistent with the defect result characterized by the abnormal skin image identification result.
The related contents in steps 303-304 serve as an invention point of the present disclosure, thereby solving the technical problems mentioned in the background art, i.e., "the state of the computer case housing cannot be accurately detected due to a single detection method for the computer case housing, which is likely to cause abnormal outflow of the computer case housing". The factors that easily cause abnormal outflow of the computer case casing are as follows: the detection mode of the computer case shell is single, so that the state of the computer case shell cannot be accurately detected, and the abnormal computer case shell is easy to flow out. If the above factors are solved, the effect of reducing the outflow of the abnormal computer case shell can be achieved. To achieve this effect, first, the associated mobile inspection apparatus is controlled to perform surface defect inspection on each surface of the target enclosure to generate a surface defect inspection result, so as to obtain a surface defect inspection result set. Therefore, whether defects exist on each surface of the target chassis can be further detected. Next, it may be determined whether each surface defect detection result has a corresponding abnormal shell image recognition result. Therefore, whether the surface of the target chassis is abnormal or not can be judged through two detection results. Then, it is determined whether each surface defect detection result has a corresponding abnormal shell image recognition result. Therefore, whether the defect result detected by the model is consistent with the detection result of the surface defect detection result or not can be judged, and the state of the computer case shell can be accurately detected conveniently. And finally, in response to determining that the defect result represented by the surface defect detection result is consistent with the defect result represented by the abnormal shell image identification result, determining the surface defect detection result as an abnormal surface defect detection result. Therefore, the state of the computer case shell can be detected simultaneously in two modes, so that the accuracy of detecting the computer case shell is improved, and the outflow of abnormal computer case shells is reduced.
Optionally, in response to determining that the defect result represented by the surface defect detection result is inconsistent with the defect result represented by the abnormal shell image recognition result, determining the pre-trained shell image recognition model as the shell image recognition model to be trained.
In some embodiments, the performing body may determine the pre-trained shell image recognition model as the shell image recognition model to be trained in response to determining that the defect result represented by the surface defect detection result is inconsistent with the defect result represented by the abnormal shell image recognition result.
Optionally, a training sample set of the chassis enclosure is obtained.
In some embodiments, the execution subject may obtain a training sample set of the chassis housing from the terminal device through a wired connection or a wireless connection. The training samples in the training sample set comprise sample shell images and labels corresponding to the sample shell images. Here, the sample housing image may include, but is not limited to: damaged hull image, rusted hull image, depressed hull image. Here, the label corresponding to the sample housing image may include, but is not limited to: a label corresponding to an image of a damaged housing, a label corresponding to an image of a rusted housing, and a label corresponding to an image of a sunken housing. Here, the label corresponding to the broken case image may be a character indicating that the case is broken. Here, the label corresponding to the rusted case image may be a character indicating the case rust. Here, the label corresponding to the depressed housing image may be a character indicating the depression of the housing.
Optionally, the shell image recognition model to be trained is trained according to the training sample set, and the shell image recognition model after training is obtained and used as a new shell image recognition model.
In some embodiments, according to the training sample set, the executing entity may train the shell image recognition model to be trained through the following steps to obtain a trained shell image recognition model as a new shell image recognition model:
firstly, determining a network structure of the shell image recognition model to be trained. For example, it needs to determine which layers the shell image recognition model to be trained includes, the connection order relationship between layers, and which neurons each layer includes, the weight (weight) and bias term (bias) corresponding to each neuron, the activation function of each layer, and so on.
And secondly, taking each sample shell image included in the training sample set as the input of the shell image recognition model to be trained, taking each label corresponding to the sample shell image included in the training sample set as the expected output of the shell image recognition model to be trained, and training the shell image recognition model to be trained by utilizing a deep learning method.
And thirdly, determining the shell image recognition model to be trained obtained by training as the trained shell image recognition model.
Therefore, the shell image recognition model can be updated iteratively to enhance the accuracy of the shell image recognition model on the shell image recognition.
And 305, sending the determined detection result of each abnormal surface defect to a maintenance terminal to remind maintenance personnel to maintain the target case shell.
In some embodiments, the execution body may send the determined abnormal surface defect detection results to a maintenance terminal to remind a maintenance person to maintain the target enclosure housing. Here, the repair terminal may refer to a computing device displaying an abnormal chassis housing.
As can be seen from fig. 3, compared with the description of some embodiments corresponding to fig. 2, the process 300 in some embodiments corresponding to fig. 3 can detect the state of the computer case shell simultaneously in two ways, so as to improve the accuracy of detecting the computer case shell and reduce the outflow of the abnormal computer case shell.
With further reference to fig. 4, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a chassis enclosure detection apparatus, which correspond to those of the method embodiments shown in fig. 2, and which may be particularly applied in various electronic devices.
As shown in fig. 4, the chassis housing detection apparatus 400 of some embodiments includes: a control unit 401 and a recognition unit 402. The control unit 401 is configured to control an associated imaging device to capture a shell area image of each surface of a target chassis shell, so as to obtain a shell area image group, where the shell area image in the shell area image group includes a shell gray area image and a shell point cloud area image corresponding to the shell gray area image; an identifying unit 402 configured to execute the following processing steps for each shell gray scale region image included in the shell region image group: marking a target shell area in the shell gray area image to generate a marked shell gray area image; performing edge detection processing on a target shell area marked in the shell gray area marked image to obtain a shell outline corresponding to the target shell area; identifying a shell gray contour map corresponding to the shell contour from the shell gray area image; generating a shell point cloud contour map based on the shell gray contour map and a shell point cloud area image corresponding to the shell gray area image; and inputting the shell point cloud profile map into a shell image recognition model trained in advance to obtain a shell image recognition result.
It will be understood that the elements described in the apparatus 400 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and will not be described herein again.
Referring now to FIG. 5, a block diagram of an electronic device (e.g., computing device 101 of FIG. 1) 500 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 5 may represent one device or may represent multiple devices as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: controlling a related camera device to shoot a shell area image of each surface of a target case shell to obtain a shell area image group, wherein the shell area images in the shell area image group comprise a shell gray area image and a shell point cloud area image corresponding to the shell gray image; for each shell gray scale area image included in the shell area image group, executing the following processing steps: marking a target shell area in the shell gray area image to generate a marked shell gray area image; performing edge detection processing on a labeled target shell area in the labeled shell gray area image to obtain a shell outline corresponding to the target shell area; identifying a shell gray level profile image corresponding to the shell profile from the shell gray level area image; generating a shell point cloud contour map based on the shell gray contour map and a shell point cloud area image corresponding to the shell gray area image; and inputting the shell point cloud contour map into a shell image recognition model trained in advance to obtain a shell image recognition result.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, which may be described as: a processor includes a control unit and an identification unit. The names of the units do not limit the units themselves in some cases, for example, the control unit may be further described as "a unit that controls the associated imaging device to capture a shell area image of each surface of the target enclosure shell, resulting in a shell area image group, wherein the shell area image in the shell area image group includes a shell gray scale area image and a shell point cloud area image corresponding to the shell gray scale image".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) the features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.
Claims (8)
1. A chassis enclosure detection method includes:
controlling a related camera device to shoot a shell area image of each surface of a target case shell to obtain a shell area image group, wherein the shell area images in the shell area image group comprise a shell gray area image and a shell point cloud area image corresponding to the shell gray area image;
for each shell gray scale area image included in the shell area image group, executing the following processing steps:
marking a target shell area in the shell gray area image to generate a marked shell gray area image;
performing edge detection processing on a labeled target shell area in the labeled shell gray area image to obtain a shell outline corresponding to the target shell area;
identifying a shell gray level outline image corresponding to the shell outline from the shell gray level area image;
generating a shell point cloud contour map based on the shell gray contour map and a shell point cloud area image corresponding to the shell gray area image;
inputting the shell point cloud profile map into a shell image recognition model trained in advance to obtain a shell image recognition result;
the pre-trained shell image recognition model is obtained by training through the following steps:
determining a network structure of an initial shell image recognition model and initializing network parameters of the initial shell image recognition model;
acquiring a training image sample set, wherein the training image sample set comprises a chassis shell point cloud image sample set and a labeling information set corresponding to the chassis shell point cloud image sample set;
respectively taking a point cloud image sample set of the chassis shell in the training image sample set and the labeling information set as the input and the expected output of the initial shell image recognition model, and training the initial shell image recognition model by using a deep learning method;
determining an initial shell image recognition model obtained by training as the pre-trained shell image recognition model;
determining the shell image recognition result as an abnormal shell image recognition result in response to the shell image recognition result meeting a preset abnormal condition;
controlling the associated mobile detection equipment to perform surface defect detection on each surface of the target case to generate a surface defect detection result and obtain a surface defect detection result group;
for each surface defect detection result in the set of surface defect detection results, performing the following verification steps:
determining whether the surface defect detection result meets the preset abnormal condition;
in response to determining that the surface defect detection result meets the preset abnormal condition, determining whether the surface defect detection result has a corresponding abnormal shell image identification result;
in response to determining that the surface defect detection result has a corresponding abnormal shell image identification result, determining whether a defect result characterized by the surface defect detection result is consistent with a defect result characterized by the abnormal shell image identification result;
determining the surface defect detection result as an abnormal surface defect detection result in response to determining that the defect result characterized by the surface defect detection result is consistent with the defect result characterized by the abnormal shell image identification result.
2. The method of claim 1, wherein the verifying step further comprises:
and in response to determining that the defect result represented by the surface defect detection result is inconsistent with the defect result represented by the abnormal shell image recognition result, determining the pre-trained shell image recognition model as a shell image recognition model to be trained.
3. The method of claim 2, wherein the method further comprises:
acquiring a training sample set of a chassis shell, wherein training samples in the training sample set comprise a sample shell image and a label corresponding to the sample shell image;
and training the shell image recognition model to be trained according to the training sample set to obtain a shell image recognition model which is trained and used as a new shell image recognition model.
4. The method of claim 1, wherein generating a shell point cloud profile based on the shell gray scale profile and a shell point cloud area image corresponding to the shell gray scale area image comprises:
performing standardization processing on the shell point cloud area image to generate a standardized shell point cloud area image;
and identifying a standardized shell point cloud outline map corresponding to the shell gray outline map from the standardized shell point cloud area image as a shell point cloud outline map.
5. The method of claim 1, wherein the method further comprises:
and sending the determined detection result of each abnormal surface defect to a maintenance terminal so as to remind maintenance personnel to maintain the target case shell.
6. A chassis enclosure detection device, comprising:
the control unit is configured to control an associated camera to shoot a shell area image of each surface of a target case shell to obtain a shell area image group, wherein the shell area images in the shell area image group comprise a shell gray area image and a shell point cloud area image corresponding to the shell gray area image;
an identification unit configured to execute the following processing steps for each shell gray scale region image included in the shell region image group: marking a target shell area in the shell gray area image to generate a marked shell gray area image; performing edge detection processing on a labeled target shell area in the labeled shell gray area image to obtain a shell outline corresponding to the target shell area; identifying a shell gray level outline image corresponding to the shell outline from the shell gray level area image; generating a shell point cloud contour map based on the shell gray contour map and a shell point cloud area image corresponding to the shell gray area image; inputting the shell point cloud contour map into a shell image recognition model trained in advance to obtain a shell image recognition result, wherein the shell image recognition model trained in advance is obtained by the following steps:
determining a network structure of an initial shell image recognition model and initializing network parameters of the initial shell image recognition model;
acquiring a training image sample set, wherein the training image sample set comprises a chassis shell point cloud image sample set and a labeling information set corresponding to the chassis shell point cloud image sample set;
respectively taking a point cloud image sample set of the chassis shell in the training image sample set and the labeling information set as the input and the expected output of the initial shell image recognition model, and training the initial shell image recognition model by using a deep learning method;
determining an initial shell image recognition model obtained by training as the pre-trained shell image recognition model;
a determination unit configured to determine the shell image recognition result as an abnormal shell image recognition result in response to the shell image recognition result satisfying a preset abnormal condition;
a control unit configured to control the associated mobile inspection apparatus to perform surface defect inspection on each surface of the target chassis to generate surface defect inspection results, resulting in a surface defect inspection result set;
a verification unit configured to perform, for each surface defect detection result in the set of surface defect detection results, a verification step of:
determining whether the surface defect detection result meets the preset abnormal condition;
in response to determining that the surface defect detection result meets the preset abnormal condition, determining whether the surface defect detection result has a corresponding abnormal shell image identification result;
in response to determining that the surface defect detection result has a corresponding abnormal shell image identification result, determining whether a defect result characterized by the surface defect detection result is consistent with a defect result characterized by the abnormal shell image identification result;
determining the surface defect detection result as an abnormal surface defect detection result in response to determining that the defect result characterized by the surface defect detection result is consistent with the defect result characterized by the abnormal shell image identification result.
7. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5.
8. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111534086.2A CN114399467B (en) | 2021-12-15 | 2021-12-15 | Case shell detection method and device, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111534086.2A CN114399467B (en) | 2021-12-15 | 2021-12-15 | Case shell detection method and device, electronic equipment and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114399467A CN114399467A (en) | 2022-04-26 |
| CN114399467B true CN114399467B (en) | 2022-11-11 |
Family
ID=81226284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111534086.2A Active CN114399467B (en) | 2021-12-15 | 2021-12-15 | Case shell detection method and device, electronic equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114399467B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2014130031A (en) * | 2011-12-22 | 2016-02-10 | Конинклейке Филипс Н.В. | TREATMENT AND DISPLAY OF THE BREAST IMAGE |
| CN107064170A (en) * | 2017-04-11 | 2017-08-18 | 深圳市深视智能科技有限公司 | One kind detection phone housing profile tolerance defect method |
| CN112198170A (en) * | 2020-09-29 | 2021-01-08 | 合肥公共安全技术研究院 | Detection method for identifying water drops in three-dimensional detection of outer surface of seamless steel pipe |
| CN113379006A (en) * | 2021-08-16 | 2021-09-10 | 北京国电通网络技术有限公司 | Image recognition method and device, electronic equipment and computer readable medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109142366B (en) * | 2018-06-13 | 2021-01-01 | 广东拓斯达科技股份有限公司 | Spherical shell defect detection method and device and computer readable storage medium |
| CN113763355A (en) * | 2021-09-07 | 2021-12-07 | 创新奇智(青岛)科技有限公司 | Defect detection method and device, electronic equipment and storage medium |
-
2021
- 2021-12-15 CN CN202111534086.2A patent/CN114399467B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2014130031A (en) * | 2011-12-22 | 2016-02-10 | Конинклейке Филипс Н.В. | TREATMENT AND DISPLAY OF THE BREAST IMAGE |
| CN107064170A (en) * | 2017-04-11 | 2017-08-18 | 深圳市深视智能科技有限公司 | One kind detection phone housing profile tolerance defect method |
| CN112198170A (en) * | 2020-09-29 | 2021-01-08 | 合肥公共安全技术研究院 | Detection method for identifying water drops in three-dimensional detection of outer surface of seamless steel pipe |
| CN113379006A (en) * | 2021-08-16 | 2021-09-10 | 北京国电通网络技术有限公司 | Image recognition method and device, electronic equipment and computer readable medium |
Non-Patent Citations (2)
| Title |
|---|
| 3D Reconstruction and Measurement of Surface Defects in Prefabricated Elements Using Point Clouds;Zhao Xu et al.;《Journal of Computing in Civil Engineering》;20200731;1-12 * |
| 复合材料自动铺放表面缺陷检测技术研究进展;马少博;《复合材料科学与工程》;20201231;121-128 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114399467A (en) | 2022-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109410218B (en) | Method and apparatus for generating vehicle damage information | |
| US11276158B2 (en) | Method and apparatus for inspecting corrosion defect of ladle | |
| CN109858445B (en) | Method and apparatus for generating a model | |
| US11392792B2 (en) | Method and apparatus for generating vehicle damage information | |
| CN108830837B (en) | Method and device for detecting steel ladle corrosion defect | |
| CN109389072B (en) | Data processing method and device | |
| CN109947989B (en) | Method and apparatus for processing video | |
| CN110059623B (en) | Method and apparatus for generating information | |
| CN111598006B (en) | Method and device for labeling objects | |
| CN108509921B (en) | Method and apparatus for generating information | |
| CN110084317B (en) | Method and device for recognizing images | |
| CN109214501B (en) | Method and apparatus for identifying information | |
| CN108510084B (en) | Method and apparatus for generating information | |
| CN110070076B (en) | Method and device for selecting training samples | |
| CN111783626A (en) | Image recognition method and device, electronic equipment and storage medium | |
| CN111340015B (en) | Positioning method and device | |
| CN111402220B (en) | Method and device for acquiring information | |
| CN110008926B (en) | Method and device for identifying age | |
| CN110287817B (en) | Target recognition and target recognition model training method and device and electronic equipment | |
| CN111325160B (en) | Method and device for generating information | |
| CN114399467B (en) | Case shell detection method and device, electronic equipment and computer readable medium | |
| CN111310858B (en) | Method and device for generating information | |
| CN115712746A (en) | Image sample labeling method and device, storage medium and electronic equipment | |
| CN113034580B (en) | Image information detection method and device and electronic equipment | |
| CN110334763B (en) | Model data file generation method, model data file generation device, model data file identification device, model data file generation apparatus, model data file identification apparatus, and model data file identification medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: No.3-8-132, 1st floor, building 3, Fuqian street, Huairou District, Beijing Patentee after: Beijing Defeng Xinzheng Technology Co.,Ltd. Address before: Room 501, block B, building M8, yard 1, Jiuxianqiao East Road, Chaoyang District, Beijing 100015 Patentee before: Beijing Defeng new journey Technology Co.,Ltd. |
|
| CP03 | Change of name, title or address |