Image file gathering method and device and electronic equipment

Abstract

The invention discloses an image file gathering method and device and electronic equipment. The method comprises the steps that snapshot information corresponding to scatter images in a historical scatter set is acquired, and the scatter images in the historical scatter set are snapshot images which are not subjected to file gathering; according to the snapshot information, target file gathering images with the feature matching degree with the scatter images larger than a preset threshold value are determined from a file gathering set, and the images in the file gathering set are snapshot images with file gathering completed; and the scatter images are clustered into a file to which the target clustered image belongs. According to the method and the device, the technical problem of low file gathering rate caused by the fact that file gathering cannot be carried out on the snapshot images which are not filed in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a method, device and electronic device for image archiving. Background Art

[0002] Portrait clustering technology aims to automatically classify and archive images of people with similar features or identities for subsequent information retrieval, analysis and management. This technology is widely used in security monitoring, face recognition systems, social media analysis and other fields.

[0003] In the current intelligent traffic management system and video surveillance field, snapshot images are important data for recording traffic violations, safety incidents and daily monitoring. Their management and utilization efficiency are directly related to the improvement of public safety management. However, traditional image processing and storage technology faces a significant technical bottleneck: there is a lack of effective archiving mechanism for a large number of snapshot images that have not been archived in time.

[0004] Specifically, due to the continuous operation of monitoring equipment and the generation of massive data, a large number of snapshots are directly stored without filtering, classification or labeling, causing the data warehouse to expand rapidly, while key information is submerged in the ocean of data. Related technologies often focus on real-time snapshots and preliminary screening, but ignore the subsequent integration and management of unarchived images. This "heavy collection, light organization" situation directly leads to low archiving efficiency, that is, it is impossible to quickly and accurately extract valuable image information from massive data and archive it for subsequent analysis.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present application provide a method, device and electronic device for image archiving, so as to at least solve the technical problem in the related art that it is impossible to archive snapshots that have not been archived, resulting in a poor archiving rate.

[0007] According to one aspect of an embodiment of the present application, a method for image archiving is provided, including: obtaining snapshot information corresponding to a scattered image in a historical scatter point set, wherein the scattered image in the historical scatter point set is a snapshot image that has not been clustered; based on the snapshot information, determining a target clustered image from the clustering set whose feature matching degree with the scattered image is greater than a preset threshold, wherein the image in the clustering set is a snapshot image that has completed archiving; and archiving the scattered image into an archive to which the target clustered image belongs.

[0008] Optionally, the scattered image in the historical scatter point set is determined in the following manner: obtaining historical snapshot images acquired by an acquisition device; extracting feature information of the historical snapshot images; comparing the feature information with the cluster feature information of each image in the cluster set in turn to obtain a first comparison result; when the first comparison result indicates that the feature information is inconsistent with the cluster feature information of all images in the cluster set, the historical snapshot image is determined as the scattered image in the historical scatter point set.

[0009] Optionally, based on the snapshot information, a target clustered image having a feature matching degree with the scattered image greater than a preset threshold is determined from the clustered image set, including: obtaining metadata in the snapshot information, wherein the metadata includes: timestamp, geographic location, device information, and snapshot object features; based on the timestamp and the device number in the device information, determining from the clustered image set a first record set of the acquisition device corresponding to the device number within a first preset time period, wherein the timestamp is within the first preset time period; based on the snapshot object features and the first feature corresponding to the image in the first record set, determining the first captured image in the target clustered image.

[0010] Optionally, based on the first feature corresponding to the feature of the captured object and the images in the first record set, determining the first captured image in the target clustered image includes: determining the first feature corresponding to each image in the first record set; comparing the feature of the captured object and the first feature corresponding to each image in the first record set to obtain a second comparison result, wherein the second comparison result is used to represent the feature matching degree between the feature of the captured object and the first feature; based on the second comparison result, determining the image corresponding to the highest feature matching degree whose feature matching degree is greater than a preset threshold from the first record set as the first captured image, and clustering the scattered image into the archive to which the first captured image belongs.

[0011] Optionally, when the first captured image in the target cluster image cannot be determined based on the device information in the captured information, the method also includes: obtaining the geographic location, timestamp and captured object characteristics in the captured information; determining the target acquisition device whose distance from the geographic location is within a preset range from the cluster set based on the geographic location and timestamp; obtaining a second record set of the target acquisition device within a second preset time period, wherein the timestamp is within the second preset time period; determining the second captured image in the target cluster image based on the captured object characteristics and the second feature corresponding to the image in the second record set.

[0012] Optionally, based on the captured object feature and the second feature corresponding to the image in the second record set, determining the second captured image in the target aggregate image includes: determining the second feature corresponding to each image in the second record set; comparing the captured object feature and the second feature corresponding to each image in the second record set to obtain a third comparison result, wherein the third comparison result is used to represent the feature matching degree between the captured object feature and the second feature; based on the third comparison result, determining the image corresponding to the highest feature matching degree greater than a second threshold value from the second record set as the second captured image.

[0013] Optionally, the method further includes: archiving the scattered image into a file to which the second captured image belongs.

[0014] According to another aspect of an embodiment of the present application, a device for clustering images is also provided, including: an acquisition module, used to acquire snapshot information corresponding to scattered images in a historical scatter point set, wherein the scattered images in the historical scatter point set are snapshot images that have not been clustered; a determination module, used to determine, from the clustering set, based on the snapshot information, a target clustering image whose feature matching degree with the scattered image is greater than a preset threshold, wherein the images in the clustering set are snapshot images that have completed clustering; and a clustering module, used to cluster the scattered images into an archive to which the target clustering image belongs.

[0015] According to another aspect of the embodiments of the present application, there is also provided an electronic device, including: a memory for storing program instructions; a processor, connected to the memory, for executing program instructions to implement the following functions: obtaining snapshot information corresponding to a scattered image in a historical scatter point set, wherein the scattered image in the historical scatter point set is a snapshot image that has not been clustered; based on the snapshot information, determining a target clustered image from the clustered set whose feature matching degree with the scattered image is greater than a preset threshold, wherein the image in the clustered set is a snapshot image that has completed clustering; and clustering the scattered image into the archive to which the target clustered image belongs.

[0016] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, including a stored computer program, wherein the device where the non-volatile storage medium is located executes the above-mentioned image archiving method by running the computer program.

[0017] According to another aspect of the embodiments of the present application, a computer program product is provided, including computer instructions, which implement the above-mentioned image archiving method when executed by a processor.

[0018] In an embodiment of the present application, by obtaining snapshot information corresponding to a scattered image in a historical scatter point set, wherein the scattered image in the historical scatter point set is a snapshot image that has not been clustered; based on the snapshot information, a target clustered image whose feature matching degree with the scattered image is greater than a preset threshold is determined from the clustered set, wherein the image in the clustered set is a snapshot image that has completed clustering; and the scattered image is clustered into the archive to which the target clustered image belongs, thereby achieving the purpose of improving the clustering efficiency, thereby achieving the technical effect of enhancing the reliability of image matching, and further solving the technical problem in the related art that snapshot images that have not been archived cannot be clustered, resulting in a poor clustering rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 is a hardware structure block diagram of a computer terminal for implementing a method for image archiving according to an embodiment of the present application;

[0021] Figure 2 is a flow chart of a method for image aggregation according to an embodiment of the present application;

[0022] Figure 3 It is a structural diagram of an image archiving device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] First, some nouns or terms that appear in the process of explaining the embodiments of the present application are subject to the following explanations:

[0026] Personnel profiling: In some technical or management fields, such as security and social media, profiling refers to identifying and aggregating people with specific characteristics (such as image features, behavior patterns, etc.) for monitoring, analysis, or personalized services. This approach involves complex algorithms and data processing techniques, such as feature extraction, matching, and classification, to achieve efficient and accurate personnel profiling.

[0027] The method embodiment of image archiving provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a method for image archiving. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions connected via a wired and / or wireless network. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0028] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the method of image archiving in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned method of image archiving. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission module 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0031] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0032] It should be noted that, in some optional embodiments, the above Figure 1 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0033] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a method for image archiving. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] Figure 2 is a flow chart of a method for image aggregation according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0035] Step S202, obtaining snapshot information corresponding to the scattered point images in the historical scattered point set, wherein the scattered point images in the historical scattered point set are snapshot images that have not been clustered.

[0036] In the above step S202, in conventional archiving, the captured image will only be directly compared with the archived feature values. If the match is successful, it will be archived in the archive. If the match is not successful, it will fall into the historical scattered point collection. Archiving generally refers to the process of organizing, classifying and archiving related images with specific purposes or meanings. The captured images that have not been archived refer to those images that have not been classified or organized into a specific collection or category, that is, the above-mentioned scattered point images. The capture information is the metadata associated with each scattered point image, including but not limited to timestamp, camera position, camera number, shooting angle, lighting conditions, etc.

[0037] Step S204, based on the snapshot information, determine from the clustering set a target clustering image whose feature matching degree with the scattered image is greater than a preset threshold, wherein the images in the clustering set are snapshot images that have completed clustering.

[0038] In the above step S204, the archive collection includes the captured images that have been sorted, classified and archived according to certain rules or standards. These images can be organized according to time, location, event type or other characteristics. According to the captured information of the scattered image, one or more target archive images with a feature matching degree greater than a preset threshold value with the scattered image are found from the archive collection. In an optional embodiment, the feature matching degree can be the similarity or correlation degree of the two images in terms of visual content, shooting conditions, time and location, etc.

[0039] The following is an optional step to determine the target poly image:

[0040] 1. Extract key features of scattered images: First, extract key feature information from the scattered images, such as the image's color histogram, texture features, edge information, shape features, etc., as well as any information that can be directly obtained from the captured information, such as timestamps, location coordinates, etc.

[0041] 2. Define matching calculation methods: Based on the needs of the application scenario, define one or more methods for calculating the matching between two images. These methods can be based on the visual similarity of the image content (such as using feature matching algorithms, template matching algorithms, etc.), or based on the similarity of metadata (such as the proximity of time and location).

[0042] 3. Set a preset threshold: Determine a preset threshold of matching degree to determine whether two images are sufficiently similar or related. The selection of this threshold depends on the specific application scenario and requirements, for example, it can be determined through experiments or experience.

[0043] 4. Traverse the clustered file set: For each image in the clustered file set, use the previously defined matching degree calculation method to compare it with the scattered image and calculate the matching degree between them.

[0044] 5. Filter the target polymorphic image: compare the calculated matching degree with the preset threshold. If the matching degree of a polymorphic image is greater than the threshold, it is regarded as the target polymorphic image and added to a candidate list.

[0045] 6. Processing multiple target cluster images (if there are multiple): If multiple target cluster images with matching degrees greater than a threshold are found, further processing is required to determine which one (or which ones) is the most appropriate.

[0046] 7. Output results: Finally, output the found target aggregate image or candidate list for subsequent analysis, display or processing.

[0047] Step S206, clustering the scattered point image into the archive to which the target clustered image belongs.

[0048] In the above step S206, the scattered image is aggregated into the archive to which the target aggregated image belongs, which is a process of integrating unclassified or unarchived image data into an existing classification system. The archive to which the above target aggregated image belongs is the target archive of the scattered image. The scattered image is added to the target archive. At the same time, in order to maintain the integrity and accessibility of the data, the metadata of the scattered image needs to be updated to reflect its new archive affiliation. For example, it includes modifying the naming convention of the image file, updating the record in the database, adding or modifying the label, annotation or attribute associated with the image, etc. After adding the scattered image to the target archive, the consistency of the archive can also be maintained by performing some additional steps. For example, checking for duplicates in the archive, updating the statistical information of the archive (such as the number of images, total size, etc.), and performing any necessary cleaning or optimization operations. After the aggregation operation is completed, a notification can be sent to the relevant personnel or a report can be generated to inform them that the scattered image has been successfully archived and provide detailed information about the content of the new archive.

[0049] Through the above steps S202 to S206, the purpose of improving the clustering efficiency is achieved, thereby achieving the technical effect of enhancing the reliability of image matching, and further solving the technical problem in the related art that the snapshot images that have not been archived cannot be clustered, resulting in a poor clustering rate. The following is an explanation.

[0050] In the above-mentioned image clustering method, the scattered image in the historical scatter point set is determined in the following manner: obtaining the historical snapshot image acquired by the acquisition device; extracting the feature information of the historical snapshot image; comparing the feature information with the clustering feature information of each image in the clustering set in turn to obtain a first comparison result; when the first comparison result indicates that the feature information is inconsistent with the clustering feature information of all images in the clustering set, the historical snapshot image is determined as the scattered image in the historical scatter point set.

[0051] In an embodiment of the present application, historical snapshot images that have been stored but not archived or grouped are obtained from various image acquisition devices (such as surveillance cameras, cameras, etc.), and feature information of the historical snapshot images, such as color distribution, texture, etc., is obtained. The purpose of feature extraction is to simplify image data and make it easier to process, compare and classify. The grouping set is a predefined image set, in which the images have been classified or archived according to certain standards or rules. Each image has its corresponding grouping feature information in the grouping set, and these feature information are used to describe and distinguish different images. The feature information of the extracted historical snapshot image is compared one by one with the grouping feature information of each image in the grouping set, for example, it can be measured based on the similarity or distance measurement between feature vectors, so as to obtain a first comparison result, which can indicate the degree of similarity between the historical snapshot image and an image in the grouping set, or whether a completely matching image is found. If the feature information of the historical snapshot image is inconsistent with the grouping feature information of all images in the grouping set, that is, no archived image matching the image is found, then the historical snapshot image is regarded as a scattered image.

[0052] In step S204 of the above-mentioned image archiving method, a target archiving image having a feature matching degree with the scattered image greater than a preset threshold is determined from the archiving set based on the captured information, including: obtaining metadata in the captured information, wherein the metadata includes: timestamp, geographic location, device information, and captured object features; based on the timestamp and the device number in the device information, determining from the archiving set a first record set of the acquisition device corresponding to the device number within a first preset time period, wherein the timestamp is within the first preset time period; determining the first captured image in the target archiving image based on the captured object features and the first feature corresponding to the image in the first record set.

[0053] In the embodiment of the present application, the captured information includes not only the image data itself, but also a series of metadata related thereto. The metadata includes but is not limited to timestamp, geographic location, device information (such as device number, model, etc.) and captured object features (such as color, shape, size, etc.). The timestamp is the specific time when the image is captured, and the device number identifies the acquisition device that captures the image. These two information points are used to filter out image records captured by the same device within a specific time period from the aggregated set. The first preset time period is a time range set as required, which is used to limit the breadth of the search and reduce unnecessary calculations. For example, the first preset time period can be the day where the timestamp is located, and the image records with timestamps within the first preset time period are considered as potential matching candidates. Through the above-mentioned screening conditions, a set of image records that meet the conditions can be extracted from the aggregated set, namely the first record set. This set contains all image records captured by a specified device (i.e., the same device) within a specified time period. The captured object features are extracted from the captured information and are used to describe the feature information of the main object or scene in the image. Each image in the first record set has its corresponding first feature, which is extracted and stored when the image is archived. Using feature matching algorithms (such as feature vector comparison, similarity calculation, etc.), the features of the captured object are compared with the first features of each image in the first record set to evaluate the similarity or matching between them. After the feature matching is completed, a series of matching scores will be obtained. According to a preset threshold (a standard for measuring whether the matching is sufficient), image records above the threshold can be screened out from the matching scores. These image records above the threshold are considered to be candidate images with a high degree of matching with the target scattered image features. Among them, the image with the highest matching degree (or the image selected according to other business rules) is determined as the first captured image in the target aggregate image.

[0054] In the above steps, the first captured image in the target archived image is determined based on the first feature corresponding to the feature of the captured object and the images in the first record set, including: determining the first feature corresponding to each image in the first record set; comparing the feature of the captured object and the first feature corresponding to each image in the first record set to obtain a second comparison result, wherein the second comparison result is used to represent the feature matching degree between the feature of the captured object and the first feature; based on the second comparison result, determining the image corresponding to the highest feature matching degree whose feature matching degree is greater than a preset threshold from the first record set as the first captured image, and archiving the scattered image into the archive to which the first captured image belongs.

[0055] In an embodiment of the present application, feature extraction is performed on each image in the first record set (i.e., a set of images captured by a designated device within a first preset time period after being screened). These features (referred to as first features) can generally represent key information of the image, such as color distribution, texture pattern, shape features, etc. The first features are pre-extracted and stored when the image is archived for subsequent comparison and matching. The captured object features provided in the captured information are compared with the first features of each image in the first record set. This comparison can be accomplished, for example, by a feature matching algorithm, which can calculate the similarity or distance between two sets of features. The result of the comparison (referred to as the second comparison result) is used to quantify the degree of match between the captured object features and the first features. The degree of match can be a numerical value indicating the degree of similarity between the two, or it can be a classification result, such as "match" or "mismatch". After obtaining the second comparison result, a preset threshold needs to be set to determine which images have a sufficiently high degree of match. Screen out all images whose feature matching degrees are greater than the preset threshold. If the matching degrees of multiple images are greater than the preset threshold, then it is necessary to further select the image with the highest matching degree from these images as the first captured image. The scattered images are grouped into the archive to which the first captured image belongs, that is, the scattered images are classified into the collection of archived images with the most similar features, so as to achieve orderly management and rapid retrieval of images.

[0056] In the above-mentioned image archiving method, when the first captured image in the target archiving image cannot be determined based on the device information in the captured information, the method also includes: obtaining the geographic location, timestamp and captured object characteristics in the captured information; determining the target acquisition device within a preset range of the geographic location from the archiving set based on the geographic location and timestamp; obtaining a second record set of the target acquisition device within a second preset time period, wherein the timestamp is within the second preset time period; determining the second captured image in the target archiving image based on the captured object characteristics and the second feature corresponding to the image in the second record set.

[0057] In an embodiment of the present application, when the device information is not sufficient to directly locate the first captured image in the target aggregate image, it is necessary to extract other useful information from the captured information, including geographic location, timestamp and captured object features. Using the geographic location information, all target acquisition devices located at or near the geographic location can be screened out. For example, the target acquisition device may be all acquisition devices within a radius of 1 km (i.e., the above-mentioned preset range) with the scattered image as the center. At the same time, combined with the timestamp information, the scope can be further narrowed, and only active acquisition devices within a certain time period before and after the capture event (i.e., the second preset time period) are considered. For example, the second preset time period can also be the day where the timestamp is located. For each filtered target acquisition device, all image records within the second preset time period are obtained to form a second record set. Feature extraction (called second features) is performed on each image in the second record set, and these features should be able to reflect the key information of the image, such as color, texture, shape, etc. The feature matching algorithm is used to compare the captured object features with the second features of each image in the second record set, and the similarity or matching degree between them is calculated. According to the matching results, all images with a matching degree greater than a preset threshold are screened out. If there are multiple images that meet the conditions, the one with the highest matching degree can be selected as the second captured image.

[0058] In the above steps, the second captured image in the target aggregate image is determined based on the captured object feature and the second feature corresponding to the image in the second record set, including: determining the second feature corresponding to each image in the second record set; comparing the captured object feature and the second feature corresponding to each image in the second record set to obtain a third comparison result, wherein the third comparison result is used to represent the feature matching degree between the captured object feature and the second feature; based on the third comparison result, determining the image corresponding to the highest feature matching degree whose feature matching degree is greater than the second threshold value from the second record set as the second captured image.

[0059] In an embodiment of the present application, one or more feature vectors (i.e., second features) that can represent the key information of each image in the second record set are generated. The second features may include, for example, color histograms, texture descriptors, shape features, edge information, etc. After extracting the second features of all images, the captured object features provided in the captured information are compared with these second features. The result of the comparison (referred to as the third comparison result) is a quantitative value or a classification result, which is used to represent the feature matching degree between the captured object feature and the second feature. The higher the matching degree, the more similar the two features are, that is, the closer the image is to the captured object visually. After obtaining the third comparison results of all images, a second threshold value needs to be set to filter out images with sufficiently high feature matching degrees. This threshold value is set according to the requirements and expected results of the actual application scenario, or needs to be determined based on experience or experiments. Only when the feature matching degree of the image is greater than the second threshold value, the image is considered to have sufficient similarity with the captured object, and therefore will be retained as a candidate for the second captured image. If the feature matching degrees of multiple images are all greater than the second threshold value, then it is necessary to further select one of these candidate images as the second captured image. This is usually done by comparing their matching scores and selecting the image with the highest matching score as the final second captured image.

[0060] In the above-mentioned method for clustering images, the method further includes: clustering the scattered-point images into the archive to which the second captured image belongs.

[0061] The above method is explained below with specific examples and steps:

[0062] Step 1: Capture historical scattered snapshot information

[0063] The system first starts a comprehensive scan of historical scattered points (collections), accurately locates and extracts the captured images (i.e. scattered point images) and their related metadata in each historical scattered point. These metadata include but are not limited to timestamps, geographic locations (latitude and longitude), device numbers, and features of captured objects.

[0064] Step 2: Feature comparison

[0065] For each snapshot point, the system further analyzes all snapshot records of the same device on that day. Subsequently, the system uses the image features of these scattered images and the image features of the snapshot records to compare one by one, looking for records that highly match the features of the current snapshot on the device. Once a matching record is found, it means that the current snapshot (i.e. the above-mentioned scattered image) can be regarded as the same file and thus aggregated into the corresponding aggregate file.

[0066] Step 3: Compare data of devices near the coordinates

[0067] If the current snapshot (i.e. the scattered image mentioned above) fails to find a matching record in the device, the system will turn to a wider search range. Using the coordinate information of the scattered image, the system intelligently locates all monitoring devices near the coordinate point in the coordinate information and obtains the snapshot data of these devices on that day. This process makes full use of the spatial analysis capabilities of the geographic information system to ensure the accuracy and efficiency of the search. Subsequently, the system uses feature matching technology again to carefully screen the acquired data to find potential matches. Once a matching situation occurs, it means that the scattered image can form an effective association with other snapshot records and is successfully classified into the corresponding cluster.

[0068] Step 4: Circular comparison

[0069] The above process is not a one-time task, but a continuous cycle. The system will repeat the above steps based on the new snapshot data to ensure that each snapshot image can be processed promptly and accurately. In this way, the snapshots of the day are continuously compared in a cycle, and the snapshots in the historical scattered points can be merged into the archive as much as possible, thereby improving the archiving rate of the snapshots.

[0070] The image archiving method provided in the embodiment of the present application adopts a double-loop comparison mechanism: first, the captured images within the target point are efficiently compared in a loop to ensure that no potential matches are missed; second, the comparison range is broadened to include the captured images of nearby points in the loop comparison process to enhance the accuracy of cross-regional recognition. At the same time, in order to address the problem of uneven quality of captured images, direct comparison of captured images is adopted to avoid the inability to match archives due to fuzzy feature values, thereby effectively reducing the accumulation of historical scattered points. This series of optimization measures significantly improves the archiving efficiency and accuracy of captured images.

[0071] Figure 3 is a structural diagram of an image aggregation device according to an embodiment of the present application, such as Figure 3 As shown, the device comprises:

[0072] An acquisition module 30 is used to acquire snapshot information corresponding to a scattered point image in a historical scattered point set, wherein the scattered point image in the historical scattered point set is a snapshot image that has not been aggregated;

[0073] A determination module 32 is used to determine, from the clustering set, a target clustering image whose feature matching degree with the scattered image is greater than a preset threshold value according to the snapshot information, wherein the images in the clustering set are snapshot images that have completed clustering;

[0074] The clustering module 34 is used to cluster the scattered point images into the archive to which the target clustered image belongs.

[0075] Through the acquisition module 30, determination module 32 and aggregation module 34 in the above-mentioned image aggregation device, the purpose of improving the aggregation efficiency is achieved, thereby realizing the technical effect of enhancing the reliability of image matching, and further solving the technical problem in the related technology that it is impossible to aggregate the snapshots that have not been archived, resulting in a poor aggregation rate.

[0076] In the determination module in the above-mentioned image clustering device, the determination module is also used to determine the scattered images in the historical scatter point set. Specifically, the scattered images in the historical scatter point set are determined in the following manner: obtaining the historical snapshot images acquired by the acquisition device; extracting the feature information of the historical snapshot images; comparing the feature information with the clustering feature information of each image in the clustering set in turn to obtain a first comparison result; when the first comparison result indicates that the feature information is inconsistent with the clustering feature information of all images in the clustering set, the historical snapshot image is determined as the scattered image in the historical scatter point set.

[0077] In the determination module in the above-mentioned image archiving device, the determination module is also used to obtain metadata in the captured information, wherein the metadata includes: timestamp, geographic location, device information, and captured object characteristics; based on the timestamp and the device number in the device information, determine from the archiving set a first record set of the acquisition device corresponding to the device number within the first preset time period, wherein the timestamp is within the first preset time period; based on the captured object characteristics and the first feature corresponding to the image in the first record set, determine the first captured image in the target archiving image.

[0078] In the determination module in the above-mentioned image clustering device, the determination module is also used to determine the first feature corresponding to each image in the first record set; compare the captured object feature with the first feature corresponding to each image in the first record set to obtain a second comparison result, wherein the second comparison result is used to represent the feature matching degree between the captured object feature and the first feature; based on the second comparison result, determine the image corresponding to the highest feature matching degree whose feature matching degree is greater than a preset threshold from the first record set as the first captured image, and cluster the scattered image into the archive to which the first captured image belongs through the clustering module.

[0079] In the determination module in the above-mentioned image archiving device, the determination module is also used to obtain the geographic location, timestamp and captured object characteristics in the captured information; determine the target acquisition device whose distance from the geographic location is within a preset range from the archiving set based on the geographic location and timestamp; obtain a second record set of the target acquisition device within a second preset time period, wherein the timestamp is within the second preset time period; determine the second captured image in the target archiving image based on the captured object characteristics and the second feature corresponding to the image in the second record set.

[0080] In the determination module in the above-mentioned image archiving device, the determination module is also used to determine the second feature corresponding to each image in the second record set; compare the captured object feature and the second feature corresponding to each image in the second record set to obtain a third comparison result, wherein the third comparison result is used to represent the feature matching degree of the captured object feature and the second feature; based on the third comparison result, determine the image corresponding to the highest feature matching degree whose feature matching degree is greater than the second threshold from the second record set as the second captured image.

[0081] In the archiving module in the above-mentioned image archiving device, the archiving module is also used to aggregate the scattered image into the archive to which the second captured image belongs.

[0082] It should be noted that Figure 3 The apparatus shown in the image is used to perform Figure 2 The method for image clustering shown in the figure, therefore the relevant explanations and instructions in the above-mentioned method for image clustering are also applicable to the device for image clustering, and will not be repeated here.

[0083] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory, and is used to execute program instructions to implement the following functions: obtaining snapshot information corresponding to a scattered image in a historical scatter point set, wherein the scattered image in the historical scatter point set is a snapshot image that has not been clustered; based on the snapshot information, determining a target clustered image from the clustered set whose feature matching degree with the scattered image is greater than a preset threshold, wherein the image in the clustered set is a snapshot image that has completed clustering; and clustering the scattered image into the archive to which the target clustered image belongs.

[0084] It should be noted that the above electronic equipment is used to execute Figure 2 The image clustering method shown in the figure, therefore the relevant explanations and instructions in the above-mentioned image clustering method are also applicable to the electronic device and will not be repeated here.

[0085] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following image clustering method by running the computer program: obtaining snapshot information corresponding to a scattered image in a historical scatter point set, wherein the scattered image in the historical scatter point set is a snapshot image that has not been clustered; based on the snapshot information, determining a target clustered image from the clustering set whose feature matching degree with the scattered image is greater than a preset threshold, wherein the image in the clustering set is a snapshot image that has completed clustering; and clustering the scattered image into the archive to which the target clustered image belongs.

[0086] It should be noted that the above non-volatile storage medium is used to execute Figure 2The method for image archiving shown in the figure, therefore the relevant explanations and instructions in the above-mentioned method for image archiving are also applicable to the non-volatile storage medium and will not be repeated here.

[0087] The embodiments of the present application also provide a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the image archiving method in each embodiment of the present application.

[0088] The embodiments of the present application also provide a computer program, which, when executed by a processor, implements the steps of the image archiving method in each embodiment of the present application.

[0089] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0090] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0092] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0093] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0095] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for image aggregation, characterized in that: include: Acquire snapshot information corresponding to a scattered point image in a historical scattered point set, wherein the scattered point image in the historical scattered point set is a snapshot image that has not been aggregated; According to the snapshot information, a target clustered image whose feature matching degree with the scattered image is greater than a preset threshold is determined from the clustered image set, wherein the images in the clustered image set are snapshot images that have completed clustering; The scattered point image is clustered into the archive to which the target clustered image belongs.

2. The method according to claim 1, characterized in that: The scatter image in the historical scatter set is determined by: Obtain historical snapshot images collected by the collection device; Extracting feature information of the historical captured image; Comparing the feature information with the clustering feature information of each image in the clustering set in sequence to obtain a first comparison result; When the first comparison result indicates that the feature information is inconsistent with the cluster feature information of all images in the cluster set, the historical captured image is determined as a scattered point image in the historical scattered point set.

3. The method according to claim 1, characterized in that According to the captured information, a target clustered image having a feature matching degree with the scattered image greater than a preset threshold is determined from the clustered image set, including: Obtaining metadata in the captured information, wherein the metadata includes: timestamp, geographic location, device information, and captured object features; According to the timestamp and the device number in the device information, determine from the aggregated file set a first record set of the collection device corresponding to the device number within a first preset time period, wherein the timestamp is within the first preset time period; A first captured image in the target aggregate image is determined based on the captured object feature and a first feature corresponding to the image in the first record set.

4. The method according to claim 3, characterized in that: Determining a first captured image in the target aggregated image according to the captured object feature and a first feature corresponding to the image in the first record set includes: Determine a first feature corresponding to each image in the first record set; Comparing the captured object feature with a first feature corresponding to each image in the first record set to obtain a second comparison result, wherein the second comparison result is used to indicate a feature matching degree between the captured object feature and the first feature; According to the second comparison result, the image corresponding to the highest feature matching degree whose feature matching degree is greater than the preset threshold in the first record set is determined as the first captured image, and the scattered point image is archived in the file to which the first captured image belongs.

5. The method according to claim 3, characterized in that: In the case where the first captured image in the target aggregated image cannot be determined according to the device information in the captured information, the method further includes: Obtaining the geographic location, timestamp and captured object features in the captured information; According to the geographic location and the timestamp, determine, from the aggregate archive set, a target acquisition device whose distance from the geographic location is within a preset range; Acquire a second record set of the target acquisition device within a second preset time period, wherein the timestamp is within the second preset time period; A second captured image in the target aggregate image is determined based on the captured object feature and a second feature corresponding to the image in the second record set.

6. The method according to claim 5, characterized in that Determining a second captured image in the target aggregate image according to the captured object feature and a second feature corresponding to the image in the second record set includes: Determine a second feature corresponding to each image in the second record set; Comparing the captured object feature with the second feature corresponding to each image in the second record set to obtain a third comparison result, wherein the third comparison result is used to indicate a feature matching degree between the captured object feature and the second feature; According to the third comparison result, an image corresponding to a highest feature matching degree whose feature matching degree is greater than a second threshold value in the second record set is determined as the second captured image.

7. The method according to claim 6, characterized in that The method further comprises: The scattered-point images are aggregated into the archive to which the second captured image belongs.

8. An image aggregation device, characterized in that: include: An acquisition module, used for acquiring snapshot information corresponding to a scattered point image in a historical scattered point set, wherein the scattered point image in the historical scattered point set is a snapshot image that has not been aggregated; A determination module, configured to determine, from a clustering set, a target clustering image whose feature matching degree with the scattered point image is greater than a preset threshold value according to the snapshot information, wherein the images in the clustering set are snapshot images that have completed clustering; A clustering module is used to cluster the scattered image into the archive to which the target clustered image belongs.

9. An electronic device, characterized in that: include: A memory for storing program instructions; A processor is connected to the memory and is used to execute program instructions to implement the following functions: obtaining snapshot information corresponding to a scattered image in a historical scatter point set, wherein the scattered image in the historical scatter point set is a snapshot image that has not been clustered; determining, based on the snapshot information, a target clustered image whose feature matching degree with the scattered image is greater than a preset threshold from the clustered set, wherein the image in the clustered set is a snapshot image that has completed clustering; and clustering the scattered image into an archive to which the target clustered image belongs.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the image archiving method described in any one of claims 1 to 7 by running the computer program.

11. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the image archiving method described in any one of claims 1 to 7 is implemented.

Images