CN213659503U - Image data processing system, storage policy device - Google Patents
Image data processing system, storage policy device Download PDFInfo
- Publication number
- CN213659503U CN213659503U CN202023044797.5U CN202023044797U CN213659503U CN 213659503 U CN213659503 U CN 213659503U CN 202023044797 U CN202023044797 U CN 202023044797U CN 213659503 U CN213659503 U CN 213659503U
- Authority
- CN
- China
- Prior art keywords
- image
- classifier
- chip
- storage
- memory
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present application relates to an image data processing system and a storage policy device. The image data processing system comprises an image acquisition device, a storage strategy device and a server cluster; the image acquisition device is connected with the storage strategy equipment, and the storage strategy equipment is in communication connection with the server cluster; the image acquisition device transmits the acquired image to the storage strategy equipment; the storage strategy device comprises a chip, a classifier and a memory; the chip is electrically connected with the classifier, and the classifier is electrically connected with the memory; the chip is used for detecting and classifying the images and transmitting the classification result to the classifier; the classifier is used for transmitting the image to the first storage and transmitting the image with the classification result of being qualified to the server cluster. Above-mentioned utility model carries out the discernment of effective image based on the image acquisition condition through storage strategy equipment, and the image that the guarantee got into the image processing link has higher quality to help promoting visual detection treatment effeciency.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to an image data processing system and a storage policy device.
Background
The optical image sensing-based surface defect automatic optical (visual) detection technology becomes an important means for surface defect detection, has the advantages of automation, non-contact, high speed, high precision, high stability and the like, and is rapidly developed in the fields of precision manufacturing and assembling industries, such as mobile phones, liquid crystal panels, silicon wafers, printed circuit boards and the like.
Products in the above fields are generally large-format products, and multiple imaging needs to be performed on an object to be inspected in the inspection process, so that high false alarm rate caused by local deformation of the object to be inspected and problems that micro defects, sub-pixel defects and the like are difficult to stably inspect easily occur. At present, the detection equipment with high precision, high real-time performance and high reliability requirements has higher cost. The real-time visual inspection technology is adopted to inspect large-format products, imaging of an object to be inspected is converted into a large-format image through devices such as an optical sensor, a motion device and signal processing, and then image splicing, defect detection, image calibration, image matching and the like are carried out on the basis of the large-format image.
At present, in real-time visual inspection, a GPU (Graphics Processing Unit) computation acceleration module is often used to implement parallel computation of images, or the capacity of a memory is increased to solve the computation bottleneck problem, which is difficult to adapt to the difficulties of large width, high precision, large capacity and the like faced by the Processing process of large-format images, so a system for detecting large-format images more efficiently is urgently needed.
SUMMERY OF THE UTILITY MODEL
In view of the above, it is desirable to provide an image data processing system and a storage policy device capable of efficiently detecting a large-format image.
In a first aspect, an embodiment of the present application provides an image data processing system, where the system includes: the system comprises an image acquisition device, a storage strategy device and a server cluster; the image acquisition device is connected with the storage strategy equipment, and the storage strategy equipment is in communication connection with the server cluster;
the image acquisition device transmits the acquired image to the storage strategy equipment;
the storage strategy device comprises a chip, a classifier and a first memory; the chip is electrically connected with the classifier, and the classifier is electrically connected with the first memory;
the chip is used for detecting and classifying the images and transmitting the classification result to the classifier;
the classifier is used for transmitting the image to the first storage, and transmitting the image with the classification result of being qualified to the server cluster.
In one embodiment, the storage policy device further comprises a communication means and a second memory; the communication device is electrically connected with the chip;
the communication device is used for receiving an image adding instruction and sending the image adding instruction to the chip;
the chip is used for indicating the classifier to transmit the newly added image acquired by the image acquisition device to the second memory based on the image newly added instruction.
In one embodiment, the storage policy device further comprises a sensing device, wherein the sensing device is electrically connected with the chip;
the sensing device is used for detecting the image and sending a detection result to the chip;
the chip is used for detecting and classifying the image based on the detection result.
In one embodiment, the sensing device comprises one or more of a photosensitive sensor, a time collector, a dynamic range test card, a definition test card, a color test card and a color difference test card.
In one embodiment, the storage policy device further comprises a data compression processor; the classifier and the first memory are connected through the data compression processor;
the classifier is used for transmitting the image to the data compression processor;
the data compression processor is used for compressing the image and transmitting the image to the first memory.
In one embodiment, the storage policy device further comprises a display device.
In one embodiment, the system further comprises an image acquisition card; the image acquisition device is connected with the storage strategy equipment through the image acquisition card.
In one embodiment, the server cluster comprises a cluster manager and an image processing cluster; the cluster manager is in communication connection with each server in the image processing cluster; each server is provided with a Central Processing Unit (CPU) and a Graphic Processing Unit (GPU);
the cluster manager is used for determining a parallel processing task and a logic analysis processing task in the image processing tasks, sending data required by the parallel processing task to the GPU node, and sending data required by the logic analysis processing task to the CPU node.
In one embodiment, a distributed storage system is arranged in the server cluster; and the server cluster is used for storing the image with the qualified classification result into the distributed storage system.
In a second aspect, an embodiment of the present application provides a storage policy device, including: a chip, a classifier and a memory; the chip is electrically connected with the classifier, and the classifier is electrically connected with the memory;
the chip is used for detecting and classifying the images and transmitting the classification result to the classifier;
the classifier is used for transmitting the image to the memory and/or an external storage device based on the classification result.
The image data processing system comprises an image acquisition device, a storage strategy device and a server cluster; the image acquisition device is connected with the storage strategy equipment, and the storage strategy equipment is in communication connection with the server cluster; the image acquisition device transmits the acquired image to the storage strategy equipment; the storage strategy device comprises a chip, a classifier and a first memory; the chip is electrically connected with the classifier, and the classifier is electrically connected with the first memory; the chip is used for detecting and classifying the images and transmitting the classification result to the classifier; the classifier is used for transmitting the image to the first storage and transmitting the image with the classification result of being qualified to the server cluster. Effective image recognition is carried out on the basis of image acquisition conditions through the storage strategy equipment, and the image entering an image processing link is guaranteed to have higher quality, so that the operation pressure of the system is reduced, and the improvement of the visual detection processing efficiency is facilitated.
Drawings
FIG. 1 is a schematic diagram of an image data processing system in one embodiment;
FIG. 2 is a diagram illustrating an exemplary storage policy facility;
FIG. 3 is a schematic diagram of an image data processing system in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It will be understood that when an element is referred to as being "disposed on" or "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only and do not represent the only embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
In one embodiment, there is provided an image data processing system, as shown in fig. 1, comprising: the image acquisition device 110, the storage policy device 120, and the server cluster. The image capturing device 110 may be connected to the storage policy device 120 through a video cable or the like; the storage policy device 120 is communicatively coupled to the cluster of servers.
The image capturing device 110 may comprise at least one video camera, a still camera, etc., and may be a device in a machine vision inspection apparatus such as an optical system, a mechanical transmission platform, and a motion system. For the object to be detected with smaller size, an image acquisition device with a single camera can be adopted; for large-format objects to be detected, an image acquisition device with multiple cameras can be adopted. The image capturing device 110 may be configured to capture an image of an object to be detected, obtain at least one image, and send the at least one image to the storage policy device 120.
As shown in fig. 2, the storage policy device 120 includes therein a chip 210, a classifier 220, and a first memory 230. Wherein the chip 210 and the classifier 220 are electrically connected; the classifier 220 is electrically connected to the memory 230. The chip 210 may be a programmable chip, such as a DSP (Digital Signal Processing) chip, for loading a memory strategy programmed by a programming language (e.g., C language). The chip 210 is configured to perform detection classification (which may include detection of image size, resolution, brightness, grayscale level, timestamp, integrity, etc.), classify the image into a high-value image (which may be an image that is qualified for detection) and a low-value image (which may be an image that is not qualified for detection), and send the high-value image and the low-value image to the classifier 220. The classifier 220 is configured to send the high value image and the low value image to the memory 230 and send the high value image to the cluster manager 130. The first memory 230 may be a distributed storage system for performing distributed storage of images.
The server cluster may be a server cluster based on a distributed service framework, and the distributed service framework may be implemented based on ZooKeeper (a distributed, open source distributed application coordination service), and the like. The server cluster may include a cluster manager 130 and an image processing cluster 140. The cluster manager 130 is communicatively coupled to the storage policy device 120 and to the image processing cluster 140. The cluster manager 130 may be a management server in a distributed service framework, and may be implemented by using high-performance cluster software keepalived (a switching mechanism software), or the like. The cluster manager 130 may be configured to monitor the status of each service node in the image processing cluster 140 and implement load balancing. Image processing cluster 140 is used to process tasks assigned by cluster manager 130.
The image data processing system comprises an image acquisition device, a storage strategy device and a server cluster; the image acquisition device is connected with the storage strategy equipment, and the storage strategy equipment is in communication connection with the server cluster; the image acquisition device transmits the acquired image to the storage strategy equipment; the storage strategy device comprises a chip, a classifier and a memory; the chip is electrically connected with the classifier, and the classifier is electrically connected with the memory; the chip is used for detecting and classifying the images and transmitting the classification result to the classifier; the classifier is used for transmitting the image to the first storage and transmitting the image with the classification result of being qualified to the server cluster. Effective image recognition is carried out on the basis of image acquisition conditions through the storage strategy equipment, and the image entering an image processing link is guaranteed to have higher quality, so that the operation pressure of the system is reduced, and the improvement of the visual detection processing efficiency is facilitated.
In one embodiment, continuing with FIG. 2, the storage policy device 120 further comprises a communication means 240 and a second memory 250; the communication device 240 is electrically connected to the chip 220. The communication device 240 is used for transmitting signals generated during the execution of the image processing task, such as an image adding instruction sent by the cluster manager 130. The communication means 240 transmits the image addition instruction to the chip 220. The chip 220 may be configured to instruct the classifier 220 to directly store the newly added image currently acquired in the second memory 250 for task scheduling by the cluster manager 130 based on the image newly adding instruction. The second memory 250 may be an incremental memory.
In this embodiment, by setting the incremental memory for directly storing the newly added image in the storage policy device, the problems of data redundancy and huge data amount caused by multiple imaging can be alleviated, and the effect of saving the memory can be achieved while performing real-time processing.
In one embodiment, the storage policy device 120 further comprises a sensing means 260, the sensing means 260 being electrically connected to the chip 220. The sensing device 260 may be one or more of a photosensitive sensor, a time collector, a dynamic range test card, a definition test card, a color test card, and a color difference test card. The sensing device 260 can detect the image to obtain the detection results of the image such as time and color attributes. The sensing device 260 sends the detection result to the chip 220, so that the chip 220 detects and classifies the image based on the detection result.
In this embodiment, the sensing device for directly detecting the image is arranged in the storage policy device, so that the image entering the image processing link can be guaranteed to have higher effectiveness, the calculation pressure of the server cluster is reduced, and the improvement of the image processing efficiency is facilitated.
In one embodiment, the storage policy device 120 further includes a data compression processor 270. The classifier 220 and the first memory 230 in the storage policy device 120 are connected through a data compression processor. The classifier 220 is configured to transmit the classified image sent by the chip to the data compression processor 270. The data compression processor 270 is configured to classify and compress the images with the same detection result, form a compressed packet corresponding to the detection result, and send the compressed packet to the first memory 230 for storage.
In this embodiment, by setting the data compression processor that can be used to compress the image in the storage policy device, the occupied space of the image can be reduced, and the memory can be saved.
In one embodiment, the storage policy device 120 further comprises a display means 280. The Display device 280, i.e., a Display, may be any of a CRT (Cathode Ray Tube) Display, an LCD (Liquid Crystal Display), and the like. The display device 280 may be used to configure image processing tasks, present image processing results, configure relevant detection conditions (e.g., detection thresholds, etc.) for images.
In this embodiment, by setting the display device in the storage policy device, the user can configure the image processing task and know the related process and result of the image processing task in time, thereby improving the operability of image processing.
In one embodiment, as shown in FIG. 3, the image processing system further comprises an image acquisition card 310. The image capture card 310 is an interface between the image capture device 110 and the storage policy device 120, and the image capture device 110 is connected to the storage policy device 120 via the image capture card. The image acquisition card 310 is used for acquiring the image signal acquired by the image acquisition device 110 into the storage policy device 120, and storing the image signal in the storage policy device 120 in the form of a data file.
In one embodiment, as shown in FIG. 3, each server 150 of the image processing cluster has a central processing unit CPU and a graphics processing unit GPU disposed therein. The CPU is a final execution unit for information processing and program operation, which is an operation and control core of the computer system. The GPU, also called a display core, a visual processor, and a display chip, is a microprocessor that is dedicated to image and graphics related operations on personal computers, workstations, game machines, and some mobile devices (e.g., tablet computers, smart phones, etc.). The cluster manager 130 is configured to determine a parallel processing task and a logic analysis processing task in the image processing tasks, and send data required by the parallel processing task to the target GPU node. And sending data required by the logic analysis processing task to the target CPU node. The target GPU node may be considered as a node that can be used to process parallel processing tasks in all GPU nodes. The target CPU node may be regarded as a node that can be used to process the logic analysis processing task among all the CPU nodes.
In this example. By independently registering the processor nodes, the management of information such as types and processing resources of the processing nodes is facilitated, and the matched target processor nodes can be rapidly determined according to the types and the processing resources of the processors required by the image processing task; after the target processor node is determined, the image processing task is processed based on the parallel processing architecture, and the processing efficiency of the image data can be effectively improved.
In one embodiment, a distributed storage system is arranged in a server cluster; and the server cluster is used for storing the images with qualified classification results into the distributed storage system. The distributed storage system can be a memory resource pool formed by combining a plurality of memory modules. The parallel process of distributed memory computing is completed by a plurality of processes (executing multithreading); each process has its own memory space. In distributed memory, these processes are distributed among multiple computers, multiple processors, and/or multiple cores, collectively forming a parallel program.
In this embodiment, a mode of combining a distributed memory and a parallel processing architecture is adopted, and an image to be processed is directly loaded to the distributed memory, so that the real-time requirement of image processing can be better met, and data blocking is slowed down.
In one embodiment, a storage policy device is provided for classifying image detections and storing images in an internal memory and/or an external storage device of the storage policy device, respectively, based on the classification results. The specific implementation of the storage policy device can refer to the above embodiment and fig. 2, which is not specifically set forth herein. The external storage device may be a storage device in a terminal or a server. The terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server may be implemented as a stand-alone server or as a server cluster consisting of a plurality of servers.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the utility model. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An image data processing system, characterized in that the system comprises: the system comprises an image acquisition device, a storage strategy device and a server cluster; the image acquisition device is connected with the storage strategy equipment; the storage strategy equipment is in communication connection with the server cluster;
the image acquisition device transmits the acquired image to the storage strategy equipment;
the storage strategy device comprises a chip, a classifier and a first memory; the chip is electrically connected with the classifier, and the classifier is electrically connected with the first memory;
the chip is used for detecting and classifying the images and transmitting the classification result to the classifier;
the classifier is used for transmitting the image to the first storage, and transmitting the image with the classification result of being qualified to the server cluster.
2. The system of claim 1, wherein the storage policy device further comprises a communication means and a second memory; the communication device is electrically connected with the chip;
the communication device is used for receiving an image adding instruction and sending the image adding instruction to the chip;
the chip is used for indicating the classifier to transmit the newly added image acquired by the image acquisition device to the second memory based on the image newly added instruction.
3. The system of claim 1, wherein the storage policy device further comprises a sensing device electrically connected to the chip;
the sensing device is used for detecting the image and sending a detection result to the chip;
the chip is used for detecting and classifying the image based on the detection result.
4. The system of claim 3, wherein the sensing device comprises one or more of a light sensor, a time collector, a dynamic range test card, a sharpness test card, a color test card, and a color difference test card.
5. The system of claim 1, wherein the storage policy device further comprises a data compression processor; the classifier and the first memory are connected through the data compression processor;
the classifier is used for transmitting the image to the data compression processor;
the data compression processor is used for compressing the image and transmitting the image to the first memory.
6. The system of claim 1, wherein the storage policy device further comprises a display device.
7. The system of claim 1, further comprising an image acquisition card; the image acquisition device is connected with the storage strategy equipment through the image acquisition card.
8. The system of claim 1, wherein the server cluster comprises a cluster manager and an image processing cluster; the manager is in communication connection with the image processing cluster; each server in the image processing cluster is provided with a Central Processing Unit (CPU) and a Graphic Processing Unit (GPU);
the cluster manager is used for determining a parallel processing task and a logic analysis processing task in the image processing tasks, sending data required by the parallel processing task to the GPU node, and sending data required by the logic analysis processing task to the CPU node.
9. The system of claim 1, wherein a distributed storage system is disposed in the server cluster; and the server cluster is used for storing the image with the qualified classification result into the distributed storage system.
10. A storage policy apparatus, comprising: a chip, a classifier and a memory; the chip is electrically connected with the classifier, and the classifier is electrically connected with the memory;
the chip is used for detecting and classifying the images and transmitting the classification result to the classifier;
the classifier is used for transmitting the image to the memory and/or an external storage device based on the classification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202023044797.5U CN213659503U (en) | 2020-12-17 | 2020-12-17 | Image data processing system, storage policy device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202023044797.5U CN213659503U (en) | 2020-12-17 | 2020-12-17 | Image data processing system, storage policy device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN213659503U true CN213659503U (en) | 2021-07-09 |
Family
ID=76690098
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202023044797.5U Active CN213659503U (en) | 2020-12-17 | 2020-12-17 | Image data processing system, storage policy device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN213659503U (en) |
-
2020
- 2020-12-17 CN CN202023044797.5U patent/CN213659503U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112506637A (en) | Image data processing method, image data processing device, computer equipment and storage medium | |
| WO2020007119A1 (en) | Display screen peripheral circuit detection method and device, electronic device and storage medium | |
| CN112449147B (en) | Video cluster monitoring system of photovoltaic power station and image processing method thereof | |
| CN115631178B (en) | Automatic wafer defect detection method, system, equipment and storage medium | |
| WO2022017197A1 (en) | Intelligent product quality inspection method and apparatus | |
| CN110261392A (en) | Quality determining method, device, electronic equipment and system | |
| CN116012354A (en) | Method, device, equipment and storage medium for detecting silk-screen defect of chip capacitor | |
| CN116167992A (en) | Defect detection method, defect detection device, electronic device and computer readable storage medium | |
| KR20220151583A (en) | Image processing method and device, electronic equipment and medium | |
| EP1080447B1 (en) | Image processing inspection apparatus | |
| CN213659503U (en) | Image data processing system, storage policy device | |
| CN112637587B (en) | Dead pixel detection method and device | |
| CN110751055B (en) | Intelligent manufacturing system | |
| US20240185414A1 (en) | Mark hole positioning method and apparatus, assembly device, and storage medium | |
| CN116993654B (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN110263885B (en) | Method and device for checking projector fault, terminal equipment and storage medium | |
| CN116465367A (en) | Equipment checking method, device, equipment and medium | |
| CN112967258B (en) | Display defect detection method and device for watch and computer readable storage medium | |
| CN115829911A (en) | Method, apparatus and computer storage medium for detecting imaging consistency of a system | |
| CN110046658B (en) | Method for remote operation of a device and related apparatus | |
| CN115619698A (en) | Method and device for detecting defects of circuit board and model training method | |
| Sieczkowski et al. | Use of a Raspberry PI single-board computer for image acquisition and transmission | |
| US12067710B2 (en) | Method and apparatus for spot-checking visual inspection system | |
| CN116818774A (en) | Defect detection method, defect detection device, electronic equipment and storage medium | |
| CN118396931A (en) | Automatic image detection system and automatic image detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |