CN114363499A - Image processing method and device, computer equipment and storage medium - Google Patents
Image processing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114363499A CN114363499A CN202210275399.9A CN202210275399A CN114363499A CN 114363499 A CN114363499 A CN 114363499A CN 202210275399 A CN202210275399 A CN 202210275399A CN 114363499 A CN114363499 A CN 114363499A
- Authority
- CN
- China
- Prior art keywords
- image
- queue
- head
- reference queue
- pipeline robot
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/50—Constructional details
- H04N23/555—Constructional details for picking-up images in sites, inaccessible due to their dimensions or hazardous conditions, e.g. endoscopes or borescopes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
The application discloses an image processing method, an image processing device, computer equipment and a storage medium, wherein the method comprises the following steps: receiving the position image sent by the pipeline robot, and adding the position image into an image reference queue until the image reference queue is full; judging whether the queue head image meets a retention strategy or not; if the image at the head of the queue meets the retention strategy, transferring the image at the head of the queue to an effective image queue; if the queue head image does not meet the retention strategy, deleting the queue head image from the image reference queue; if the image acquisition work of the pipeline robot is not finished, updating the image reference queue and continuously receiving the position image sent by the pipeline robot; and if the image acquisition work of the pipeline robot is finished, sequentially transferring the position images which meet the retention strategy in the image reference queue to the effective image queue, and outputting the effective image queue. The method only keeps the position image with abnormal image state in the effective image queue, thereby reducing the storage requirement.
Description
Technical Field
The present application belongs to the field of image processing technologies, and in particular, to an image processing method and apparatus, a computer device, and a storage medium.
Background
The combination of the image processing technology and the computer vision technology greatly improves the image processing efficiency. The detection of cracks, perforations or corrosion blocks of the pipeline is obtained by processing images acquired by a robot based on computer vision, and because the pipeline is generally long and different angles of the pipeline at the position of the robot need to be shot, a huge memory is needed to store effective information of the shot images. Among the stored effective information of the photographed image, data really about the problematic pipe is very small, the image processing system needs to calculate a large amount of data to obtain the problematic pipe information, the processing efficiency is low, and the lamp shadow of the pipe robot, impurities or sludge in the pipe are easily mistakenly judged as cracks, perforations or corrosion blocks, thereby causing a problem of low detection accuracy, which needs to be changed.
Disclosure of Invention
The application aims to provide an image processing method, an image processing device, a computer device and a storage medium, and aims to reduce the storage requirement of unnecessary images.
In order to solve the above technical problem, an embodiment of the present application provides the following technical solutions:
in a first aspect, the present application provides an image processing method, including:
receiving a position image sent by a pipeline robot, and adding the position image into an image reference queue until the image reference queue is full, wherein the position image at the head of the image reference queue is marked as a head image;
judging whether the queue head image meets a retention strategy;
if the queue head image meets the retention strategy, transferring the queue head image to an effective image queue;
if the queue head image does not meet the retention strategy, deleting the queue head image from the image reference queue;
judging whether the image acquisition work of the pipeline robot is finished or not;
if the image acquisition work of the pipeline robot is not finished, updating the image reference queue, and returning to the step of adding the position image sent by the pipeline robot into the image reference queue;
if the image acquisition work of the pipeline robot is finished, sequentially transferring the position images meeting the retention strategy in the image reference queue to the effective image queue;
and outputting the effective image queue.
In a second aspect, the present application provides an image processing apparatus, comprising:
the acquisition module is used for receiving a position image sent by the pipeline robot and adding the position image into an image reference queue until the image reference queue is full, wherein the position image at the head of the image reference queue is marked as a head image;
the first judgment module is used for judging whether the head image meets a reservation strategy;
if the queue head image meets a retention strategy, transferring the queue head image to an effective image queue;
if the queue head image does not meet the retention strategy, deleting the queue head image from the image reference queue;
the second judgment module is used for judging whether the image acquisition work of the pipeline robot is finished or not;
if the image acquisition work of the pipeline robot is not finished, updating the image reference queue, and returning to the step of adding the position image sent by the pipeline robot into the image reference queue;
if the image acquisition work of the pipeline robot is finished, sequentially transferring the position images remained in the image reference queue to the effective image queue;
and the output module is used for outputting the effective image queue.
In a third aspect, the present application provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the image processing method as provided in the first aspect when executing the computer program.
In a fourth aspect, the present application provides a storage medium having stored thereon a computer program which, when run on a computer, causes the computer to perform the image processing method as provided in the first aspect, among others.
The embodiment of the application provides an image processing method, an image processing device, a computer device and a storage medium, which can selectively store image information of a pipeline with cracks, perforations or corrosion blocks in an image shot by a pipeline robot, wherein the image shot by the pipeline robot is temporarily stored in an image reference queue, when the image reference queue is full, whether the image reference queue is abandoned or transferred to an effective image queue to be output is judged according to the image state of a queue head image, and the abandoned image is the image of the pipeline without the cracks, the perforations or the corrosion blocks, so that the storage requirement of unnecessary images is greatly reduced, the calculation amount of an image processing system is reduced, and the image processing efficiency is improved.
Drawings
The technical solution and other advantages of the present application will become apparent from the detailed description of the embodiments of the present application with reference to the accompanying drawings.
Fig. 1 is a scene schematic diagram of a processing system of an image processing method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of an image processing method according to an embodiment of the present application;
fig. 3 is another schematic flow chart of an image processing method according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application;
fig. 5 is another schematic structural diagram of an image processing apparatus according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a server according to an embodiment of the present application.
Detailed Description
Referring to the drawings, wherein like reference numbers refer to like elements, the principles of the present application are illustrated as being implemented in a suitable computing environment. The following description is based on illustrated embodiments of the application and should not be taken as limiting the application with respect to other embodiments that are not detailed herein.
In the description that follows, specific embodiments of the present application will be described with reference to steps and symbols executed by one or more computers, unless otherwise indicated. Accordingly, these steps and operations will be referred to, several times, as being performed by a computer, the computer performing operations involving a processing unit of the computer in electronic signals representing data in a structured form. This operation transforms the data or maintains it at locations in the computer's memory system, which may be reconfigured or otherwise altered in a manner well known to those skilled in the art. The data maintains a data structure that is a physical location of the memory that has particular characteristics defined by the data format. However, while the principles of the application have been described in language specific to above, it is not intended to be limited to the specific form set forth herein, and it will be recognized by those of ordinary skill in the art that various of the steps and operations described below may be implemented in hardware.
The term "module" as used herein may be considered a software object executing on the computing system. The various components, modules, engines, and services described herein may be viewed as objects implemented on the computing system. The apparatus and method described herein are preferably implemented in software, but may also be implemented in hardware, and are within the scope of the present application.
The embodiment of the application provides an image processing method, an image processing device, computer equipment and a storage medium.
Referring to fig. 1, the view is a scene schematic diagram of an image processing system provided in the embodiment of the present application, where the image processing system may include a processing device that determines whether an image has an abnormality, and may be specifically integrated in a server or other devices, and is mainly used to acquire an image and construct an image reference queue, where the total number of images that can be stored in the image reference queue may be set manually, and the storage amount is greater than or equal to 3. In the process of processing the images in the image reference queue, the images with abnormal image states are judged and verified, the judgment and verification are performed according to the adjacent images of the images, the images obtained by the robot at the same position and different shooting angles are compared with the outline information of the images at the adjacent positions, and the pipeline images with problems caused by light shadows, sundries or sludge in the pipeline can be further eliminated, so that the larger the storage capacity of the image reference queue is, the higher the detection accuracy of the images is.
In addition, this image processing system can also include pipeline robot and user display terminal, and pipeline robot mainly used inputs the image of its pipeline inner wall of shooing to the image processing system that this application provided, and user display terminal is used for showing the pipeline inner wall image of different positions in the pipeline to pipeline robot operating personnel through the image.
Of course, the image processing system may further include a memory, for example, operable to store a state criterion for determining an image state of the position image, a retention policy for determining whether a head-of-line image is retained, a criterion for checking the image state of the position image, and the like, and transmit to the processing device for determining whether an abnormality exists in the image based on a call instruction of the processing device for determining whether an abnormality exists in the image.
The details will be described below separately.
In the present embodiment, description will be made from the viewpoint of a processing device that determines whether there is an abnormality in a position image, and the processing device may be specifically integrated in a server or the like.
An image processing method, comprising: receiving a position image sent by the pipeline robot, adding the position image into an image reference queue until the image reference queue is full, wherein the position image at the head of the image reference queue is recorded as a head image; judging whether the queue head image meets a retention strategy or not; if the image at the head of the queue meets the retention strategy, transferring the image at the head of the queue to an effective image queue; if the queue head image does not meet the retention strategy, deleting the queue head image from the image reference queue; judging whether the image acquisition work of the pipeline robot is finished or not; if the image acquisition work of the pipeline robot is not finished, updating the image reference queue, and returning to the step of adding the position image sent by the pipeline robot into the image reference queue; if the image acquisition work of the pipeline robot is finished, sequentially transferring the position images which meet the retention strategy in the image reference queue to an effective image queue; and outputting the effective image queue.
Referring to fig. 2, fig. 2 is a schematic flowchart of an image processing method according to a first embodiment of the present application. The method comprises the following steps:
in 201, the position image sent by the pipeline robot is received, and the position image is added into an image reference queue until the image reference queue is full, wherein the position image at the head of the image reference queue is recorded as a head image.
In the specific implementation process, the pipeline robot walks and shoots the omnidirectional image of different positions in the pipeline, and the mode of shooing the image can have the multiple, can set up the pipeline robot and stop after walking fixed distance at every turn and shoot, can also decide the distance of walking next time according to the image state of the position image of shooing, promptly: the pipeline robot travels d1 meters if the image state of the current position image is not abnormal, travels d2 meters if the image state of the current position image is abnormal, and d1 > d2 in order to detect a high-quality abnormal position image. The service life of the pipeline and the precision requirement of the detection result can be considered when the distance of the pipeline robot walking each time is determined. The shorter the distance of the pipeline robot walking each time is, the more position images are shot, the more accurate the final detection result is, and the walking distance of the pipeline robot is not limited.
The position images need to be sequentially added into the image reference queue according to the received sequence, the larger the accommodating capacity of the image reference queue is, the more accurate the verification of the position images with the abnormality is, so that the possibility of erroneous judgment is reduced, and the accommodating capacity of the image reference queue is not limited.
In 202, it is determined whether the head image satisfies the retention policy, and if the head image satisfies the retention policy, the head image is transferred to the effective image queue, and if the head image does not satisfy the retention policy, the head image is deleted from the image reference queue.
Before judging whether the image of the head of the queue meets the retention strategy, preprocessing the image of the head of the queue, such as denoising, graying and contour extraction, is needed, and whether the image is abnormal is judged according to the contour and the gray value of the image, wherein the abnormality specifically refers to the existence of cracks, perforations or corrosion blocks on a pipeline to which the image is applied. The images which are not abnormal do not need to be reserved, the storage amount and the calculation amount are reduced, only the images which are abnormal are reserved, and meanwhile, the images which are abnormal are stored in an effective image queue to be convenient for follow-up viewing.
In 203, it is determined whether the image capturing work of the pipeline robot is finished, if the image capturing work of the pipeline robot is not finished, the image reference queue is updated, and the step of adding the position image sent by the pipeline robot into the image reference queue is returned, and if the image capturing work of the pipeline robot is finished, the position images which meet the retention policy in the image reference queue are sequentially transferred to the effective image queue.
It can be understood that after the pipeline robot finishes the image acquisition work, no position image is added in the image reference queue any more, and the position images which are left in the image reference queue and meet the retention strategy are transferred to the effective image queue at the moment; when the pipeline robot does not finish the image acquisition work, all the position images left in the image reference queue need to be sequentially transferred, and the position images sent by the pipeline robot are continuously received and added to the tail of the image reference queue.
At 204, the active image queue is output.
The position image with the abnormality is stored in the effective image queue and can be displayed on a user display terminal. In the specific display process of the user display terminal, the pipeline position mark corresponding to the abnormal position image may be displayed, and the unmarked position represents that the abnormal pipeline does not exist, which is not limited herein.
As described above, in the image processing method provided in this embodiment, the obtained position image is stored in the image reference queue, and then the image state of the position image in the image reference queue is determined, and only the position image with an abnormal image state is retained in the effective image queue, so that the storage requirement is reduced.
The method described in the above embodiments is further illustrated in detail by way of example.
Because the image state of the position image is judged according to the contour information and the gray information extracted from the image, and the contour information and the gray information are influenced by illumination, impurities in the pipeline and the image shooting quality, the contours of shadows and the impurities can be wrongly judged as cracks or corrosion blocks, so that the detected abnormal position of the pipeline is inaccurate.
Based on this, the embodiment of the present application provides an image processing method, which can reduce memory for storing image data and improve detection accuracy. Referring to fig. 3, fig. 3 is another schematic flow chart of an image processing method according to an embodiment of the present disclosure. The method comprises the following steps:
adding the acquired position image into an image reference queue → (II) judging whether the image reference queue needs to be updated → (III) determining the storage position of the head image → (IV) determining an effective image queue; as will be described in detail below.
Adding the acquired position image into an image reference queue:
301. and receiving the position image sent by the pipeline robot.
It can be understood that the pipeline robot sends the images shot at different positions in the pipeline to the image processing device, the robot can advance at different speeds to perform interval shooting, the interval distance can be flexibly set according to specific conditions, the shorter the interval distance is, the more images are obtained, the more accurate the detection of the pipeline is, but the larger the data volume to be processed at the same time is.
302. And determining the image state of the position image according to the state criterion, and adding the position image into the image reference queue until the image reference queue is full.
And adjacent position images within a certain distance are stored in an image reference queue for processing, so that unnecessary position images can be deleted conveniently and timely, and the memory pressure is reduced. The accommodating amount of the image reference queue can be preset according to specific situations.
And (II) judging whether the image reference queue needs to be updated or not.
303. And judging whether the image states of all position images in the image reference queue are consistent or not.
It can be understood that if the image states of all the position images in the image reference queue are non-abnormal, it indicates that the pipeline corresponding to the position images does not have cracks, perforations or corrosion blocks; if the image states of all the position images in the image reference queue are abnormal, the pipeline corresponding to the position images is not provided with cracks, perforations or corrosion blocks, and the same cracks or corrosion blocks are possible.
304. And carrying out misjudgment and verification on the position image with abnormal image state and the adjacent position image.
When the image states of all position images in the image reference queue are inconsistent, the possibility that lamp light shadow or sundries in the pipeline are wrongly judged as cracks, perforations or corrosion blocks exists, and therefore the misjudgment rate can be reduced by carrying out misjudgment and verification on abnormal position images. The position images comprise images of the pipeline robot at a certain position under different conditions, and the real state of the object can be further identified by utilizing the multidimensional images.
305. And judging whether the image state of the position image after misjudgment and verification changes.
And if the image state of the position image after misjudgment and verification changes, indicating that the position image is misjudged.
306. The image state of the position image is updated.
And modifying the image state of the misjudged position image.
And (III) determining the storage position of the head-of-line image.
307. Judging whether the image state of the head image of the queue is abnormal or not;
since the pipe wall of most sections in the pipeline is intact, the position images of the positions are not necessarily preserved, and therefore, the image state of the head-of-line image needs to be judged whether the preservation strategy is met.
308. And transferring the head image to an effective image queue.
And transferring the head image meeting the retention strategy to an effective image queue, wherein the effective image queue is a position image of a corresponding position where the inner wall of the pipeline has an abnormality.
309. And deleting the head-of-line image from the image reference queue.
For the head-of-line image which does not satisfy the retention policy, it is not necessary to keep it, and therefore it is deleted from the image reference queue.
And (IV) determining an effective image queue.
310. And judging whether the image acquisition work of the pipeline robot is finished or not.
If the image acquisition work of the pipeline robot is finished, a new position image is not added into the image reference queue, and the image reference queue is not full at the moment, the image processing device does not execute the operation after 202 any more, and the position images left in the image reference queue need to be processed.
311. And sequentially transferring the position images meeting the retention strategy in the image reference queue to the effective image queue.
And when the image acquisition work of the pipeline robot is finished and the image reference queue is not full, directly and sequentially transferring the position images which meet the retention strategy in the image reference queue to the effective image queue.
312. And sequentially advancing all position images in the image reference queue.
If the image acquisition work of the pipeline robot is not finished, all position images in the image reference queue need to be sequentially transferred at the moment, and a position is reserved to be convenient for storing the position image of the next position transmitted by the pipeline robot.
313. And outputting the effective image queue.
The effective image queue stores position images of positions where the inner wall of the pipeline is abnormal, so that the condition of the inner wall of the pipeline is visually displayed and processed, and operators can conveniently perform corresponding repair processing.
As can be seen from the above, in the image processing method provided in this embodiment, the obtained position images are stored in the image reference queue, when the image reference queue is full, the image states of all the position images in the image reference queue are determined to be judged, if the image states of all the position images are consistent, it is determined whether the position images are retained in the valid image queue directly according to the image state of the first image of the queue, if the image states of all the position images are inconsistent, the position images with abnormal image states in the image reference queue need to be subjected to misjudgment and verification, and then the position images subjected to misjudgment and verification are subjected to image state judgment. Through misjudgment and verification among position images with similar positions in the image reference queue, the misjudgment probability of the inner wall of the pipeline can be reduced, the position images with non-abnormal image states are discarded, only the abnormal position images are reserved, and the memory required for storing the images is reduced.
As described above, in the image processing method provided in this embodiment, the obtained position image is stored in the image reference queue, and then the image state of the position image in the image reference queue is determined, and only the position image with an abnormal image state is retained in the effective image queue, so that the storage requirement is reduced.
In order to better implement the image processing method provided by the embodiment of the present application, the embodiment of the present application further provides an apparatus based on the image processing method. The terms are the same as the image processing method, and details of implementation can be referred to the description in the method embodiment.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present disclosure, and the image processing apparatus may include an obtaining module 401, a first determining module 402, a second determining module 403, and an output module 404.
The acquiring module 401 is configured to receive the position image sent by the pipeline robot, and add the position image into the image reference queue until the image reference queue is full, where the position image at the head of the image reference queue is recorded as a head image.
In the specific implementation process, the pipeline robot walks and shoots the omnidirectional image of different positions in the pipeline, and the mode of shooing the image can have the multiple, can set up the pipeline robot and stop after walking fixed distance at every turn and shoot, can also decide the distance of walking next time according to the image state of the position image of shooing, promptly: the pipeline robot travels d1 meters if the image state of the current position image is not abnormal, travels d2 meters if the image state of the current position image is abnormal, and d1 > d2 in order to detect a high-quality abnormal position image. The service life of the pipeline and the precision requirement of the detection result can be considered when the distance of the pipeline robot walking each time is determined. The shorter the distance of the pipeline robot walking each time is, the more position images are shot, the more accurate the final detection result is, and the walking distance of the pipeline robot is not limited.
The position images need to be sequentially added into the image reference queue according to the received sequence, the larger the accommodating capacity of the image reference queue is, the more accurate the verification of the position images with the abnormality is, so that the possibility of erroneous judgment is reduced, and the accommodating capacity of the image reference queue is not limited.
The first determining module 402 is configured to determine whether the first image meets the retention policy, transfer the first image to the effective image queue if the first image meets the retention policy, and delete the first image from the image reference queue if the first image does not meet the retention policy.
The first determining module is specifically configured to: before judging whether the image of the head of the queue meets the retention strategy, preprocessing the image of the head of the queue, such as denoising, graying and contour extraction, is needed, and whether the image is abnormal is judged according to the contour and the gray value of the image, wherein the abnormality specifically refers to the existence of cracks, perforations or corrosion blocks on the pipeline to which the image is applied. The images which are not abnormal do not need to be reserved, the storage amount and the calculation amount are reduced, only the images which are abnormal are reserved, and meanwhile, the images which are abnormal are stored in an effective image queue to be convenient for follow-up viewing.
The second judging module can be used for judging whether the image acquisition work of the pipeline robot is finished or not, if the image acquisition work of the pipeline robot is not finished, the image reference queue is updated, the step of adding the position image sent by the pipeline robot into the image reference queue is returned, and if the image acquisition work of the pipeline robot is finished, the position images which meet the retention strategy in the image reference queue are sequentially transferred to the effective image queue.
It can be understood that after the pipeline robot finishes the image acquisition work, no position image is added in the image reference queue any more, and the position images which are left in the image reference queue and meet the retention strategy are transferred to the effective image queue at the moment; when the pipeline robot does not finish the image acquisition work, all the position images left in the image reference queue need to be sequentially transferred, and the position images sent by the pipeline robot are continuously received and added to the tail of the image reference queue.
The output module may be operable to output the active image queue.
The position image with the abnormality is stored in the effective image queue, and the output module can display the position image with the abnormality on the user display terminal. In the specific display process of the user display terminal, the output module may display the pipeline position mark corresponding to the abnormal position image, and the unmarked position represents that the abnormal pipeline does not exist, which is not limited herein.
In this way, in the image processing apparatus provided in this embodiment, the obtaining module stores the obtained position image in the image reference queue first, and the first determining module and the second determining module perform image state determination on the position image in the image reference queue, and only the position image with an abnormal image state is retained in the effective image queue, so that the storage requirement is reduced.
The method described in the above embodiments is further illustrated in detail by way of example.
Because the image state of the position image is judged according to the contour information and the gray information extracted from the image, and the contour information and the gray information are influenced by illumination, impurities in the pipeline and the image shooting quality, the contours of shadows and the impurities can be wrongly judged as cracks or corrosion blocks, so that the detected abnormal position of the pipeline is inaccurate.
The method described in the above embodiments is further illustrated in detail by way of example.
Because the image state of the position image is judged according to the contour information and the gray information extracted from the image, and the contour information and the gray information are influenced by illumination, impurities in the pipeline and the image shooting quality, the contours of shadows and the impurities can be wrongly judged as cracks or corrosion blocks, so that the detected abnormal position of the pipeline is inaccurate.
Based on this, the embodiments of the present application provide an image processing apparatus, which can reduce the memory for storing image data and improve the detection accuracy. Referring to fig. 5, fig. 5 is another schematic flow chart of the image processing apparatus according to the embodiment of the present disclosure. The method comprises the following steps:
the first receiving sub-module → (second) second determining sub-module → (third) third determining sub-module → (fourth) outputting module, which will be described in detail below.
And (I) a receiving submodule.
The receiving submodule 501 is configured to receive the position image transmitted from the pipeline robot.
It can be understood that the pipeline robot sends the images shot at different positions in the pipeline to the image processing device, the robot can advance at different speeds to perform interval shooting, the interval distance can be flexibly set according to specific conditions, the shorter the interval distance is, the more images are obtained, the more accurate the detection of the pipeline is, but the larger the data volume to be processed at the same time is.
The calculation module 502 is configured to determine an image status of the position image according to the status criterion, and add the position image to the image reference queue until the image reference queue is full.
And adjacent position images within a certain distance are stored in an image reference queue for processing, so that unnecessary position images can be deleted conveniently and timely, and the memory pressure is reduced. The accommodating amount of the image reference queue can be preset according to specific situations.
And (II) a first judgment submodule.
The first judging sub-module 503 is used to judge whether the image statuses of all the position images in the image reference queue are consistent.
It can be understood that if the image states of all the position images in the image reference queue are non-abnormal, it indicates that the pipeline corresponding to the position images does not have cracks, perforations or corrosion blocks; if the image states of all the position images in the image reference queue are abnormal, the pipeline corresponding to the position images is not provided with cracks, perforations or corrosion blocks, and the same cracks or corrosion blocks are possible.
The misjudgment checking module 504 is configured to perform misjudgment checking on the position image with the abnormal image state and the adjacent position image.
When the image states of all position images in the image reference queue are inconsistent, the possibility that lamp light shadow or sundries in the pipeline are wrongly judged as cracks, perforations or corrosion blocks exists, and therefore the misjudgment rate can be reduced by carrying out misjudgment and verification on abnormal position images. The position images comprise images of the pipeline robot at a certain position under different conditions, and the real state of the object can be further identified by utilizing the multidimensional images.
The second determination submodule 305 is configured to determine whether the image state of the position image after the erroneous determination check has changed.
And if the image state of the position image after misjudgment and verification changes, indicating that the position image is misjudged.
The updating module 506 is configured to update the image status of the position image and modify the image status of the misjudged position image.
And (III) a third judgment submodule.
The third determining sub-module 507 is configured to determine whether the image state of the head image is abnormal.
Since the pipe wall of most sections in the pipeline is intact, the position images of the positions are not necessarily preserved, and therefore, the image state of the head-of-line image needs to be judged whether the preservation strategy is met.
The first transfer module 508 is used to transfer the head of queue image to the active image queue.
And transferring the head image meeting the retention strategy to an effective image queue, wherein the effective image queue is a position image of a corresponding position where the inner wall of the pipeline has an abnormality.
The deleting module 509 is configured to delete the head-of-line image from the image reference queue.
For the head-of-line image which does not satisfy the retention policy, it is not necessary to keep it, and therefore it is deleted from the image reference queue.
And (IV) an output module.
The fourth judging submodule 510 is configured to judge whether the image capturing operation of the pipeline robot is finished.
If the image acquisition work of the pipeline robot is finished, a new position image is not added into the image reference queue any more, and at the moment, the image reference queue is not full, the image processing device does not execute the operation after 502 any more, and the position image left in the image reference queue needs to be processed.
The second transfer module 511 is configured to sequentially transfer the position images satisfying the retention policy in the image reference queue to the effective image queue.
And when the image acquisition work of the pipeline robot is finished and the image reference queue is not full, directly and sequentially transferring the position images which meet the retention strategy in the image reference queue to the effective image queue.
The shift module 512 is used to sequentially shift forward all position images in the image reference queue.
If the image acquisition work of the pipeline robot is not finished, all position images in the image reference queue need to be sequentially transferred at the moment, and a position is reserved to be convenient for storing the position image of the next position transmitted by the pipeline robot.
The output module 513 is used for outputting the valid image queue.
The effective image queue stores position images of positions where the inner wall of the pipeline is abnormal, so that the condition of the inner wall of the pipeline is visually displayed and processed, and operators can conveniently perform corresponding repair processing.
As can be seen from the above, in the image processing method provided in this embodiment, the obtained position images are stored in the image reference queue, when the image reference queue is full, the image states of all the position images in the image reference queue are determined to be judged, if the image states of all the position images are consistent, it is determined whether the position images are retained in the valid image queue directly according to the image state of the first image of the queue, if the image states of all the position images are inconsistent, the position images with abnormal image states in the image reference queue need to be subjected to misjudgment and verification, and then the position images subjected to misjudgment and verification are subjected to image state judgment. Through misjudgment and verification among position images with similar positions in the image reference queue, the misjudgment probability of the inner wall of the pipeline can be reduced, the position images with non-abnormal image states are discarded, only the abnormal position images are reserved, and the memory required for storing the images is reduced.
As described above, in the image processing apparatus provided in this embodiment, the acquired position image is stored in the image reference queue, and then the image state of the position image in the image reference queue is determined, and only the position image with an abnormal image state is retained in the effective image queue, so that the storage requirement is reduced.
In a specific implementation, the above units may be implemented as independent entities, or may be combined arbitrarily to be implemented as the same or several entities, and the specific implementation of the above units may refer to the foregoing method embodiments, which are not described herein again.
The image processing apparatus may be specifically integrated in a device such as a server.
The embodiment of the present application also provides a server, in which the image processing apparatus according to the embodiment of the present application can be integrated, as shown in fig. 6, which shows a schematic structural diagram of a server 600 according to the embodiment of the present application, specifically:
the server 600 may include components such as a processor 601 of one or more processing cores, memory 602 of one or more computer-readable storage media, a power supply 603, and an input unit 604. Those skilled in the art will appreciate that the server architecture shown in FIG. 6 is not meant to be limiting, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components. Wherein:
the processor 601 is a control center of the server, connects various parts of the entire server using various interfaces and lines, and performs various functions of the server and processes data by running or executing software programs and/or modules stored in the memory 602 and calling data stored in the memory 602, thereby performing overall monitoring of the server. Optionally, processor 601 may include one or more processing cores; preferably, the processor 601 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 601.
The memory 602 may be used to store software programs and modules, and the processor 601 executes various functional applications and data processing by operating the software programs and modules stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to the use of the server, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. Accordingly, the memory 602 may also include a memory controller to provide the processor 601 with access to the memory 602.
The server further includes a power supply 603 for supplying power to each component, and preferably, the power supply 603 may be logically connected to the processor 601 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system. The power supply 603 may also include any component of one or more dc or ac power sources, recharging systems, power failure detection circuitry, power converters or inverters, power status indicators, and the like.
The server may also include an input unit 604, which input unit 604 may be used to receive input numeric or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.
Although not shown, the server may further include a display unit and the like, which will not be described in detail herein. Specifically, in this embodiment, the processor 601 in the server loads the executable file corresponding to the process of one or more application programs into the memory 602 according to the following instructions, and the processor 601 runs the application programs stored in the memory 602, thereby implementing various functions as follows:
receiving a position image sent by a pipeline robot, and adding the position image into an image reference queue until the image reference queue is full, wherein the position image at the head of the image reference queue is marked as a head image; judging whether the queue head image meets a retention strategy; if the queue head image meets the retention strategy, transferring the queue head image to an effective image queue; if the queue head image does not meet the retention strategy, deleting the queue head image from the image reference queue; judging whether the image acquisition work of the pipeline robot is finished or not; if the image acquisition work of the pipeline robot is not finished, updating the image reference queue, and returning to the step of adding the position image sent by the pipeline robot into the image reference queue; if the image acquisition work of the pipeline robot is finished, sequentially transferring the position images meeting the retention strategy in the image reference queue to the effective image queue; and outputting the effective image queue.
In some embodiments, the processor 601 is configured to receive the position image transmitted by the pipeline robot, and add the position image to the image reference queue until the image reference queue is full, wherein the position image at the head of the image reference queue is recorded as a head image.
In the specific implementation process, the pipeline robot walks and shoots the omnidirectional image of different positions in the pipeline, and the mode of shooing the image can have the multiple, can set up the pipeline robot and stop after walking fixed distance at every turn and shoot, can also decide the distance of walking next time according to the image state of the position image of shooing, promptly: the pipeline robot travels d1 meters if the image state of the current position image is not abnormal, travels d2 meters if the image state of the current position image is abnormal, and d1 > d2 in order to detect a high-quality abnormal position image. The service life of the pipeline and the precision requirement of the detection result can be considered when the distance of the pipeline robot walking each time is determined. The shorter the distance of the pipeline robot walking each time is, the more position images are shot, the more accurate the final detection result is, and the walking distance of the pipeline robot is not limited.
The processor 601 may further be configured to add the position images to the image reference queue in sequence according to the received sequence, where the larger the accommodation amount of the image reference queue is, the more accurate the verification is performed on the position image with the abnormality, so as to reduce the possibility of erroneous judgment, where the accommodation amount of the image reference queue is not limited.
Further, the processor 601 may further determine whether the head image meets a retention policy, transfer the head image to the effective image queue if the head image meets the retention policy, and delete the head image from the image reference queue if the head image does not meet the retention policy.
Before judging whether the image at the head of the queue meets the retention strategy, the processor 601 needs to perform preprocessing on the image at the head of the queue, such as denoising, graying and contour extraction, and judges whether the image has an abnormality according to the contour and the gray value of the image, wherein the abnormality specifically refers to the existence of a crack, a perforation or a corrosion block on a pipeline to which the image corresponds. The images which are not abnormal do not need to be reserved, the storage amount and the calculation amount are reduced, only the images which are abnormal are reserved, and meanwhile, the images which are abnormal are stored in an effective image queue to be convenient for follow-up viewing.
It can be understood that the processor 601 can also determine whether the image capturing work of the pipeline robot is finished, if the image capturing work of the pipeline robot is not finished, update the image reference queue, and return to the step of adding the position image sent by the pipeline robot into the image reference queue, and if the image capturing work of the pipeline robot is finished, sequentially transfer the position images satisfying the retention policy in the image reference queue to the effective image queue.
It can be understood that after the pipeline robot finishes the image acquisition work, no position image is added in the image reference queue any more, and the position images which are left in the image reference queue and meet the retention strategy are transferred to the effective image queue at the moment; when the pipeline robot does not finish the image acquisition work, all the position images left in the image reference queue need to be sequentially transferred, and the position images sent by the pipeline robot are continuously received and added to the tail of the image reference queue.
In particular implementations, processor 601 may also output an active image queue.
The position image with the abnormality is stored in the effective image queue and can be displayed on a user display terminal. In the specific display process of the user display terminal, the pipeline position mark corresponding to the abnormal position image may be displayed, and the unmarked position represents that the abnormal pipeline does not exist, which is not limited herein.
As described above, in the image processing apparatus provided in this embodiment, the processor 601 first stores the acquired position image in the image reference queue, and then performs image state judgment on the position image in the image reference queue, and only the position image with an abnormal image state is retained in the effective image queue, which reduces the storage requirement.
In the above embodiments, the descriptions of the embodiments have respective emphasis, and parts that are not described in detail in a certain embodiment may refer to the above detailed description of the image processing method, and are not described herein again.
The image processing apparatus provided in the embodiment of the present application, for example, a computer, a tablet computer, a mobile phone with a touch function, and the like, belongs to the same concept as the image processing method in the above embodiments, and any method provided in the embodiment of the image processing method may be run on the image processing apparatus, and a specific implementation process thereof is described in the embodiment of the image processing method, and is not described herein again.
It should be noted that, for the image processing method described in this application, it can be understood by those skilled in the art that all or part of the process for implementing the image processing method described in this application may be implemented by controlling the relevant hardware through a computer program, where the computer program may be stored in a computer-readable storage medium, such as a memory of a terminal, and executed by at least one processor in the terminal, and during the execution, the process may include the process of the embodiment of the image processing method. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
In the image processing apparatus according to the embodiment of the present application, each functional module may be integrated into one processing chip, each module may exist alone physically, or two or more modules may be integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium, such as a read-only memory, a magnetic or optical disk, or the like.
The foregoing detailed description has provided an image processing method, an apparatus, a computer device, and a storage medium according to embodiments of the present application, and specific examples have been applied in the present application to explain the principles and implementations of the present application, and the descriptions of the foregoing embodiments are only used to help understand the method and the core ideas of the present application; meanwhile, for those skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. An image processing method, comprising:
receiving a position image sent by a pipeline robot, and adding the position image into an image reference queue until the image reference queue is full, wherein the position image at the head of the image reference queue is marked as a head image;
judging whether the queue head image meets a retention strategy;
if the queue head image meets the retention strategy, transferring the queue head image to an effective image queue;
if the queue head image does not meet the retention strategy, deleting the queue head image from the image reference queue;
judging whether the image acquisition work of the pipeline robot is finished or not;
if the image acquisition work of the pipeline robot is not finished, updating the image reference queue, and returning to the step of adding the position image sent by the pipeline robot into the image reference queue;
if the image acquisition work of the pipeline robot is finished, sequentially transferring the position images meeting the retention strategy in the image reference queue to the effective image queue;
and outputting the effective image queue.
2. The image processing method according to claim 1,
after receiving the position image sent by the pipeline robot and before adding the position image into the image reference queue, the method further comprises the following steps:
determining an image state of the location image according to a state criterion.
3. The image processing method according to claim 1 or claim 2, wherein said determining whether the head-of-line image satisfies a retention policy comprises:
modifying the image states of the position images according to modification criteria when the image states of all the position images in the image reference queue are inconsistent;
judging whether the image state of the queue head image is abnormal or not;
if the image state of the head of line image is not abnormal, the head of line image does not meet the retention strategy;
and if the image state of the queue head image is abnormal, the queue head image meets the retention strategy.
4. The image processing method according to claim 1,
said updating said image reference queue comprises:
and sequentially advancing all the position images in the image reference queue.
5. The image processing method of claim 3, wherein said modifying the image state of the position image according to modification criteria comprises:
carrying out misjudgment and verification on the position image with the abnormal image state and the position image adjacent to the position image;
and if the image state of the position image after misjudgment and verification changes, updating the image state of the position image.
6. The image processing method according to claim 3, wherein said determining whether the image status of the head-of-line image is abnormal comprises:
judging whether the image state of the queue head image meets a state retention criterion;
if so, the image state of the queue head image is abnormal;
and if not, the image state of the queue head image is non-abnormal.
7. The image processing method according to claim 5, wherein the checking for the misjudgment of the image feature information of the position image with the abnormal image state and the position image adjacent to the position image comprises:
if the pipeline corresponding to the position image has cracks, carrying out misjudgment and verification on crack information on the position image and the position image adjacent to the position image;
if the pipeline corresponding to the position image has a perforation, carrying out error judgment and verification on perforation information of the position image and the position image adjacent to the position image;
and if the pipeline corresponding to the position image has a corrosion block, carrying out misjudgment and verification on corrosion block information on the position image and the adjacent position image.
8. An image processing apparatus characterized by comprising:
the acquisition module is used for receiving a position image sent by the pipeline robot and adding the position image into an image reference queue until the image reference queue is full, wherein the position image at the head of the image reference queue is marked as a head image;
the first judgment module is used for judging whether the head image meets a reservation strategy;
if the queue head image meets a retention strategy, transferring the queue head image to an effective image queue;
if the queue head image does not meet the retention strategy, deleting the queue head image from the image reference queue;
the second judgment module is used for judging whether the image acquisition work of the pipeline robot is finished or not;
if the image acquisition work of the pipeline robot is not finished, updating the image reference queue, and returning to the step of adding the position image sent by the pipeline robot into the image reference queue;
if the image acquisition work of the pipeline robot is finished, sequentially transferring the position images remained in the image reference queue to the effective image queue;
and the output module is used for outputting the effective image queue.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method according to any of claims 1-7 are implemented when the computer program is executed by the processor.
10. A storage medium having stored thereon a computer program for causing a computer to perform the steps of the method according to any of claims 1 to 7 when the computer program is run on the computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210275399.9A CN114363499A (en) | 2022-03-21 | 2022-03-21 | Image processing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210275399.9A CN114363499A (en) | 2022-03-21 | 2022-03-21 | Image processing method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114363499A true CN114363499A (en) | 2022-04-15 |
Family
ID=81095070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210275399.9A Pending CN114363499A (en) | 2022-03-21 | 2022-03-21 | Image processing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114363499A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204678070U (en) * | 2015-05-26 | 2015-09-30 | 四川大学 | Based on Big Dipper location and the depopulated zone petroleum pipeline monitoring system of short message |
| CN105184788A (en) * | 2015-08-31 | 2015-12-23 | 广州杰赛科技股份有限公司 | Pipeline detection terminal and method |
| CN208170009U (en) * | 2018-04-27 | 2018-11-30 | 钦州学院 | A kind of buried natural gas line security protection early warning system |
| CN109827028A (en) * | 2019-02-21 | 2019-05-31 | 西安理工大学 | A kind of pipeline crack detection robot and its control method |
| CN111553265A (en) * | 2020-04-27 | 2020-08-18 | 河北天元地理信息科技工程有限公司 | Method and system for detecting internal defects of drainage pipeline |
| CN112468871A (en) * | 2020-11-24 | 2021-03-09 | 青岛创新奇智科技集团有限公司 | Monitoring video playing method and device and electronic equipment |
| CN112712148A (en) * | 2020-12-30 | 2021-04-27 | 杭州越歌科技有限公司 | Underground pipe network monitoring method, system, device and storage medium |
| CN112770090A (en) * | 2020-12-28 | 2021-05-07 | 杭州电子科技大学 | Monitoring method based on transaction detection and target tracking |
-
2022
- 2022-03-21 CN CN202210275399.9A patent/CN114363499A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204678070U (en) * | 2015-05-26 | 2015-09-30 | 四川大学 | Based on Big Dipper location and the depopulated zone petroleum pipeline monitoring system of short message |
| CN105184788A (en) * | 2015-08-31 | 2015-12-23 | 广州杰赛科技股份有限公司 | Pipeline detection terminal and method |
| CN208170009U (en) * | 2018-04-27 | 2018-11-30 | 钦州学院 | A kind of buried natural gas line security protection early warning system |
| CN109827028A (en) * | 2019-02-21 | 2019-05-31 | 西安理工大学 | A kind of pipeline crack detection robot and its control method |
| CN111553265A (en) * | 2020-04-27 | 2020-08-18 | 河北天元地理信息科技工程有限公司 | Method and system for detecting internal defects of drainage pipeline |
| CN112468871A (en) * | 2020-11-24 | 2021-03-09 | 青岛创新奇智科技集团有限公司 | Monitoring video playing method and device and electronic equipment |
| CN112770090A (en) * | 2020-12-28 | 2021-05-07 | 杭州电子科技大学 | Monitoring method based on transaction detection and target tracking |
| CN112712148A (en) * | 2020-12-30 | 2021-04-27 | 杭州越歌科技有限公司 | Underground pipe network monitoring method, system, device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 李玮燕等: "渗滤液导排管道检测机器人的研究", 《计算机工程与设计》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113392794B (en) | Vehicle line crossing identification method and device, electronic equipment and storage medium | |
| EP4064212A2 (en) | Method and apparatus for detecting camera occlusion, device, storage medium and program product | |
| CN112148779A (en) | Method, device and storage medium for determining service index | |
| CN110390813B (en) | Big data processing system based on vehicle type identification | |
| CN116166583B (en) | Data precision conversion method and device, DMA controller and medium | |
| CN114363499A (en) | Image processing method and device, computer equipment and storage medium | |
| CN111914793A (en) | Early warning method, device and equipment based on regional population | |
| CN110751055A (en) | Intelligent manufacturing system | |
| CN114333409B (en) | Target tracking method, device, electronic equipment and storage medium | |
| CN115129659A (en) | Main and auxiliary kernel computer processing platform | |
| CN114119990B (en) | Method, apparatus and computer program product for image feature point matching | |
| CN113377476B (en) | Interface display method, related device and computer program product | |
| CN111626081B (en) | Method and device for determining state of loading and unloading port and storage medium | |
| CN110991296B (en) | Video annotation method and device, electronic equipment and computer-readable storage medium | |
| CN114639164B (en) | Behavior recognition method, device equipment and storage medium based on voting mechanism | |
| CN112783507B (en) | Data stream guiding playback method and device, electronic equipment and readable storage medium | |
| CN112069959A (en) | Human body detection method, human body detection device, electronic equipment and storage medium | |
| CN118247719A (en) | Early warning method and device for dumping cage vehicle and related equipment thereof | |
| CN115775361A (en) | Loading state recognition method, device, equipment and computer readable storage medium | |
| CN117788789A (en) | Parabolic target detection method and device, computer equipment and storage medium | |
| CN118394502A (en) | Efficient computing power scheduling method and system for cloud rendering | |
| CN117933353A (en) | Reinforced learning model training method and device, electronic equipment and storage medium | |
| CN117372477A (en) | Target tracking matching method, device, equipment and medium | |
| CN114677320A (en) | Video frame selection method and device, electronic equipment and storage medium | |
| CN115984798A (en) | Lane line detection method, lane line detection device, electronic device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220415 |
|
| RJ01 | Rejection of invention patent application after publication |