A real-time multidimensional analysis method and system for big data images

Abstract

The present invention is applicable to the field of image analysis technology, and provides a real-time multi-dimensional analysis method and system for big data images, the method comprising: a terminal device uploads an image to be processed, extracts image features in the image to be processed, matches the features of a preset image, outputs the preset image if the match is successful, and updates or retains the historical preset image after each successful match; wherein, a plurality of preset images have feature identifiers corresponding to each other, the feature identifiers are generated according to the features of the preset image, and the feature identifiers are stored in a feature table; matching the features of the preset image comprises: matching the feature identifier of the image to be processed with the feature identifier in the feature table to obtain a preset image corresponding to the matching image, and using a table for extraction and comparison, which greatly improves work efficiency, reduces server configuration requirements, and improves user experience.

Description

Technical Field

[0001] The present invention belongs to the technical field of image analysis, and in particular relates to a real-time multi-dimensional analysis method and system for big data images. Background Art

[0002] In the current technology, when an image is analyzed and recognized, all the pictures in the database need to be compared with the image one by one. When the same image (or a similar image) is input again for recognition, all the pictures in the database will still be searched and compared as in the last recognition. Such repeated searches will consume a lot of time, especially when searching and comparing in a large database. This time consumption will be more serious. Therefore, there is an urgent need for an analysis technology that optimizes this repeated search. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a real-time multidimensional analysis method and system for big data images, aiming to solve the problem that the prior art cannot provide an effective real-time multidimensional analysis method for big data images, resulting in low image recognition and analysis efficiency and poor user experience.

[0004] In one aspect, the present invention provides a method for real-time multidimensional analysis of big data images, the method comprising the following steps:

[0005] The terminal device uploads the image to be processed;

[0006] Extracting image features from the image to be processed;

[0007] Matching with the features of a preset image, and outputting the preset image if the match succeeds;

[0008] After each successful match, the preset image is updated or retained as a history.

[0009] Furthermore, the terminal device uploading the image to be processed includes: the terminal device uploading the image to be processed to a nearby edge computing node;

[0010] The extracting the image features in the image to be processed comprises: extracting the image features in the image to be processed by the edge computing node;

[0011] The matching with the features of the preset image includes: the edge computing node matches the features of the preset image stored in the central server according to the image features in the image to be processed;

[0012] Outputting the preset image when the match is successful includes: the central server sending the preset image to the terminal device through the edge computing node;

[0013] After successfully matching the features of the preset image, the image to be processed becomes a matched image.

[0014] Further, the updating or retaining of the historical preset image after each successful matching includes:

[0015] The edge computing node sends the matched image to the central server, and the central server uses the matched image to replace and update the corresponding preset image or retains the replaced preset image.

[0016] Further preferably, the image to be processed and the preset image are both three-dimensional images, and the central server stores a plurality of different preset images;

[0017] Each of the plurality of preset images has a corresponding feature identifier, the feature identifier is generated according to the features of the preset image, and the feature identifier is stored in a feature table.

[0018] Furthermore, the feature table also stores a storage path identifier of a storage location of a preset image corresponding to the feature identifier;

[0019] The central server sending the preset image to the terminal device through the edge computing node includes: extracting the preset image according to the storage path identifier and sending the preset image to the terminal device through the edge computing node;

[0020] The preset image is stored in the edge computing node, and the central server backs up the preset image stored in the edge computing node;

[0021] When the preset image cannot be found according to the storage path identifier, it is extracted from the central server according to the feature identifier.

[0022] Furthermore, before matching the features of the preset image, the method includes:

[0023] Generating a feature identifier of the image to be processed according to the image features extracted from the image to be processed;

[0024] The matching with the features of the preset image includes: matching the feature identifier of the image to be processed with the feature identifier in the feature table.

[0025] Further preferably, the extracting image features from the image to be processed includes:

[0026] Preset one or more image feature thresholds, and extract image features in the image to be processed when the image feature threshold in the image to be processed exceeds the preset image feature threshold;

[0027] The image feature threshold is a feature threshold of a local area of ​​the image.

[0028] In another aspect, the present invention provides a big data image real-time multi-dimensional analysis system, the system comprising:

[0029] Edge computing nodes receive images to be processed uploaded by terminal devices;

[0030] A feature extraction unit, which presets one or more image feature thresholds, and extracts image features in the image to be processed when the image feature threshold in the image to be processed exceeds the preset image feature threshold;

[0031] A feature identifier generating unit, which generates a feature identifier of the image to be processed according to the image features extracted from the image to be processed;

[0032] A feature table generating unit, which generates a feature identifier and a storage path identifier of a storage location of the preset image corresponding to the feature identifier according to the feature of the preset image, and generates a feature table according to the feature identifier and the storage path identifier;

[0033] A matching unit, matching the features of the image to be processed with the features of the preset image;

[0034] A central server storing feature tables and preset images;

[0035] The image output unit outputs a preset image corresponding to the matching image.

[0036] On the other hand, the present invention also provides a non-volatile computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by one or more processors, the one or more processors can execute the above-mentioned real-time multidimensional analysis method of big data images.

[0037] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the above-mentioned real-time multidimensional analysis method for big data images.

[0038] The beneficial effects of the present invention are as follows: a terminal device uploads an image to be processed, extracts image features in the image to be processed, matches the features of a preset image, outputs the preset image if the match is successful, and updates or retains the historical preset image after each successful match; wherein, multiple preset images have feature identifiers corresponding to each other, the feature identifiers are generated according to the features of the preset image, and the feature identifiers are stored in a feature table; matching the features of the preset image includes: matching the feature identifier of the image to be processed with the feature identifier in the feature table to obtain a preset image corresponding to the matching image, and using a table for extraction and comparison, which greatly improves work efficiency, reduces server configuration requirements, and improves user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flowchart of the implementation of the method for real-time multi-dimensional analysis of big data images provided in the first embodiment of the present invention;

[0040] Figure 2 It is a structural diagram of a big data image real-time multi-dimensional analysis system provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0042] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments:

[0043] Embodiment 1:

[0044] Figure 1 The implementation process of the real-time multi-dimensional analysis method of big data images provided by the first embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0045] In step S101, the terminal device uploads the image to be processed;

[0046] In an embodiment of the present invention, the terminal device uploading the image to be processed includes: the terminal device uploading the image to be processed to a nearby edge computing node;

[0047] In step S102, image features are extracted from the image to be processed;

[0048] In an embodiment of the present invention, extracting image features in the image to be processed includes: extracting image features in the image to be processed by an edge computing node;

[0049] In step S103, matching is performed with features of a preset image, and if the match is successful, the preset image is output;

[0050] In an embodiment of the present invention, matching with features of a preset image includes: the edge computing node matches, based on image features in the image to be processed, features of a preset image stored in a central server;

[0051] Outputting the preset image when the match is successful includes: the central server sends the preset image to the terminal device through the edge computing node; wherein, after the feature of the preset image is successfully matched, the image to be processed becomes the matched image;

[0052] In step S104, after each successful match, the historical preset image is updated or retained;

[0053] In an embodiment of the present invention, updating or retaining the historical preset image after each successful matching includes:

[0054] The edge computing node sends the matched image to the central server, and the central server uses the matched image to replace and update the corresponding preset image or retains the replaced preset image.

[0055] In an embodiment of the present invention, a terminal device uploads an image to be processed, extracts image features in the image to be processed, matches the features of a preset image, outputs the preset image if the match is successful, and updates or retains the historical preset image after each successful match; wherein, a plurality of preset images each have a corresponding feature identifier, the feature identifier is generated based on the features of the preset image, and the feature identifier is stored in a feature table; matching the features of the preset image includes: matching the feature identifier of the image to be processed with the feature identifier in the feature table to obtain a preset image corresponding to the matching image, and using a table for extraction and comparison, which greatly improves work efficiency, reduces server configuration requirements, and improves user experience.

[0056] In an embodiment of the present invention, further, the image to be processed and the preset image are both three-dimensional images, and a plurality of different preset images are stored in the central server;

[0057] Further preferably, each of the plurality of preset images has a corresponding feature identifier, the feature identifier is generated according to the features of the preset image, and the feature identifier is stored in a feature table.

[0058] Furthermore, the feature table also stores a storage path identifier of a storage location of a preset image corresponding to the feature identifier;

[0059] The central server sending the preset image to the terminal device through the edge computing node includes: extracting the preset image according to the storage path identifier and sending the preset image to the terminal device through the edge computing node;

[0060] The preset images are stored in the edge computing nodes, and the central server backs up the preset images stored in the edge computing nodes to ensure data security and avoid loss.

[0061] When the preset image cannot be found according to the storage path identifier, it is extracted from the central server according to the feature identifier.

[0062] Furthermore, before matching with the features of the preset image, the method includes: generating a feature identifier of the image to be processed based on the image features extracted from the image to be processed;

[0063] Matching the features of the preset image includes: matching the feature identifier of the image to be processed with the feature identifier in the feature table.

[0064] Further preferably, extracting image features from the image to be processed includes: presetting one or more image feature thresholds, and extracting image features from the image to be processed when the image feature threshold in the image to be processed exceeds the preset image feature threshold; the image feature threshold is a feature threshold of a local area of ​​the image; to meet different usage requirements.

[0065] Embodiment 2:

[0066] Figure 2 The structure of the big data image real-time multi-dimensional analysis system provided by the second embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, including:

[0067] The edge computing node 200 receives the image to be processed uploaded by the terminal device;

[0068] The feature extraction unit 201 presets one or more image feature thresholds, and extracts image features in the image to be processed when the image feature threshold in the image to be processed exceeds the preset image feature threshold;

[0069] A feature identifier generating unit 202 generates a feature identifier of the image to be processed according to the image features extracted from the image to be processed;

[0070] The feature table generating unit 203 generates a feature identifier and a storage path identifier of a storage location of the preset image corresponding to the feature identifier according to the feature of the preset image, and generates a feature table according to the feature identifier and the storage path identifier;

[0071] A matching unit 204 matches the features of the image to be processed with the features of a preset image;

[0072] The central server 300 stores the feature table and the preset image;

[0073] The image output unit 301 outputs a preset image corresponding to the matching image.

[0074] In the embodiment of the present invention, each unit of the big data image real-time multidimensional analysis system can be implemented by a corresponding hardware or software unit. Each unit can be an independent software or hardware unit or integrated into one software or hardware unit, which is not intended to limit the present invention.

[0075] Embodiment three:

[0076] Embodiment 3 of the present invention provides a non-volatile computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more processors, for example, to execute the above-described Figure 1 The method comprises steps S101 to S104.

[0077] As an example, the non-volatile storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable types of memory.

[0078] Embodiment 4:

[0079] Embodiment 4 of the present invention provides a computer program product, which includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the real-time multi-dimensional analysis method of big data images in the above method embodiment. For example, the above described Figure 1 The method comprises steps S101 to S104.

[0080] The embodiments described above are merely illustrative, in which the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can exist in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer electronic device (which can be a personal computer, a server, or a network electronic device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0082] Conditional language such as "can," "can," "might," or "may," among other things, unless specifically stated otherwise or otherwise understood within the context as used, is generally intended to convey that particular embodiments can include (while other embodiments do not) particular features, elements, and / or operations. Thus, such conditional language is generally not intended to imply that features, elements, and / or operations are in any way required for one or more embodiments or that one or more embodiments must include logic for determining whether such features, elements, and / or operations are included or will be performed in any particular embodiment, with or without student input or prompting.

[0083] What has been described herein in this specification and the accompanying drawings includes examples that can provide real-time multidimensional analysis methods and systems for big data images. Of course, it is not possible to describe every conceivable combination of elements and / or methods for the purpose of describing the various features of the present disclosure, but it can be recognized that many other combinations and permutations of the disclosed features are possible. Therefore, it is obvious that various modifications can be made to the present disclosure without departing from the scope or spirit of the present disclosure. In addition, or in an alternative, other embodiments of the present disclosure may be apparent from consideration of this specification and the accompanying drawings and from the practice of the present disclosure as presented herein. It is intended that the examples proposed in this specification and the accompanying drawings are considered to be illustrative and not restrictive in all respects. Although specific terms are employed herein, they are used in a general and descriptive sense and are not used for the purpose of limitation.

Claims

1. A real-time multi-dimensional analysis method for big data images, characterized in that: The method comprises the following steps: The terminal device uploads the image to be processed; Extracting image features from the image to be processed; Matching with the features of a preset image, and outputting the preset image if the match succeeds; After each successful match, update or retain the preset image in history; The terminal device uploading the image to be processed includes: the terminal device uploading the image to be processed to a nearby edge computing node; The extracting the image features in the image to be processed comprises: extracting the image features in the image to be processed by the edge computing node; The matching with the features of the preset image includes: the edge computing node matches the features of the preset image stored in the central server according to the image features in the image to be processed; Outputting the preset image when the match is successful includes: the central server sending the preset image to the terminal device through the edge computing node; After successfully matching the features of the preset image, the image to be processed becomes a matched image; The matching with the features of the preset image includes: Generating a feature identifier of the image to be processed according to the image features extracted from the image to be processed; Generate a feature identifier and a storage path identifier of a storage location of the preset image corresponding to the feature identifier according to the feature of the preset image, and generate a feature table according to the feature identifier and the storage path identifier; The matching with the features of the preset image includes: matching the feature identifier of the image to be processed with the feature identifier in the feature table.

2. The method for real-time multidimensional analysis of big data images according to claim 1, characterized in that: The updating or retaining of the historical preset image after each successful match includes: The edge computing node sends the matched image to the central server, and the central server uses the matched image to replace and update the corresponding preset image or retains the replaced preset image.

3. The real-time multi-dimensional analysis method of big data images according to claim 2, characterized in that: The image to be processed and the preset image are both three-dimensional images, and the central server stores a plurality of different preset images; Each of the plurality of preset images has a feature identifier corresponding to each other, the feature identifier is generated according to the features of the preset image, and the feature identifier is stored in a feature table; The feature table also stores a storage path identifier of a storage location of a preset image corresponding to the feature identifier; The central server sending the preset image to the terminal device through the edge computing node includes: extracting the preset image according to the storage path identifier and sending the preset image to the terminal device through the edge computing node; The preset image is stored in the edge computing node, and the central server backs up the preset image stored in the edge computing node; When the preset image cannot be found according to the storage path identifier, it is extracted from the central server according to the feature identifier.

4. The method for real-time multidimensional analysis of big data images according to claim 1, characterized in that: The extracting of image features from the image to be processed comprises: Preset one or more image feature thresholds, and extract image features in the image to be processed when the image feature threshold in the image to be processed exceeds the preset image feature threshold; The image feature threshold is a feature threshold of a local area of ​​the image.

5. A big data image real-time multi-dimensional analysis system, characterized in that: The system comprises: Edge computing nodes receive images to be processed uploaded by terminal devices; A feature extraction unit, which presets one or more image feature thresholds, and extracts image features in the image to be processed when the image feature threshold in the image to be processed exceeds the preset image feature threshold; A feature identifier generating unit, which generates a feature identifier of the image to be processed according to the image features extracted from the image to be processed; A feature table generating unit, which generates a feature identifier and a storage path identifier of a storage location of the preset image corresponding to the feature identifier according to the feature of the preset image, and generates a feature table according to the feature identifier and the storage path identifier; A matching unit, matching the features of the image to be processed with the features of the preset image; A central server storing feature tables and preset images; An image output unit, outputting a preset image corresponding to the matching image; The terminal device uploading the image to be processed includes: the terminal device uploading the image to be processed to a nearby edge computing node; The extracting the image features in the image to be processed comprises: extracting the image features in the image to be processed by the edge computing node; The matching with the features of the preset image includes: the edge computing node matches the features of the preset image stored in the central server according to the image features in the image to be processed; Outputting the preset image when the match is successful includes: the central server sending the preset image to the terminal device through the edge computing node; After successfully matching the features of the preset image, the image to be processed becomes a matched image; The matching with the features of the preset image includes: Generating a feature identifier of the image to be processed according to the image features extracted from the image to be processed; The matching with the features of the preset image includes: matching the feature identifier of the image to be processed with the feature identifier in the feature table.

6. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores computer-executable instructions, which, when executed by one or more processors, enable the one or more processors to execute the real-time multidimensional analysis method for big data images as described in any one of claims 1-4.

7. A computer program product, characterized in that The computer program product includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the real-time multidimensional analysis method for big data images as described in any one of claims 1 to 4.

Images