Efficient storage method, device, electronic device and storage medium

Abstract

The embodiments of the present invention provide an efficient storage method, device, electronic device and storage medium. The method includes: determining a group of images to be processed, determining a reference image area corresponding to each image to be processed, each of the reference image areas being able to completely cover the reference tracking object and the reference marking object included in the image to be processed, and the reference image area being formed based on at least two image blocks of the same shape and size; obtaining a first image result based on the third image block in the reference image area corresponding to each image to be processed and storing the second image result based on the fourth image block in the reference image area corresponding to each image to be processed and storing the second image result. The technical solution of the present application reduces the amount of data in the area where the reference tracking object is located by nearly half, which can save storage space, improve transmission efficiency, and reduce requirements for storage devices and network bandwidth.

Description

Technical Field

[0001] The present invention relates to the field of image storage technology, and in particular to an efficient storage method, device, electronic equipment and storage medium. Background Art

[0002] Intelligent transportation plays an increasingly important role in modern society. In intelligent transportation scenarios, image storage has become a key component of storage services. For example, the demand for storing and reading massive amounts of images generated by various image services such as vehicle passing images, violation images, face images, and structured data is growing.

[0003] In order to adapt to this change in demand, image storage has gradually shifted from traditional centralized storage to the popular distributed storage. Distributed storage has improved storage flexibility to a certain extent. However, due to the extremely large number of images generated in intelligent transportation scenarios, a large amount of storage space will still be occupied during the storage process. This not only increases storage costs, but also places higher requirements on the capacity and performance of storage devices. Summary of the invention

[0004] The embodiments of the present invention provide an efficient storage method, device, electronic device and storage medium to significantly reduce the image storage amount and reduce storage costs.

[0005] In a first aspect, an embodiment of the present invention provides an efficient storage method, the method comprising:

[0006] Determine a to-be-processed image group, wherein the to-be-processed image group includes at least two to-be-processed images, each of which is a different captured image of a capture screen from the same field of view angle for a reference tracking object;

[0007] Determine a reference image region corresponding to each image to be processed, each of the reference image regions can completely cover a reference tracking object and a reference marker object included in the image to be processed, the reference image region is a local image region in the image to be processed, and the reference image region is formed according to at least two image blocks of the same shape and size;

[0008] Obtaining and storing a first image result based on a third image block in a reference image area corresponding to each image to be processed, wherein the third image block includes a reference tracking object, and the first image result is a composite image that presents each third image block in sequence according to the shooting time sequence of each image to be processed;

[0009] A second image result is obtained and stored based on a fourth image block in a reference image area corresponding to each image to be processed, wherein the fourth image block does not contain a reference tracking object, the third image block and / or the fourth image block includes a reference marker object, and the second image result includes image information formed by adding the fourth image blocks corresponding to each image to be processed to different color channels respectively.

[0010] In a second aspect, an embodiment of the present invention further provides a high-efficiency storage device, the device comprising:

[0011] A first determination module is used to determine a to-be-processed image group, wherein the to-be-processed image group includes at least two to-be-processed images, each of which is a different captured image of a collection screen from the same field of view angle for a reference tracking object;

[0012] A second determination module is used to determine a reference image region corresponding to each image to be processed, each of the reference image regions can completely cover the reference tracking object and the reference marker object included in the image to be processed, the reference image region is a local image region in the image to be processed, and the reference image region is formed according to at least two image blocks of the same shape and size;

[0013] A first storage module, configured to obtain and store a first image result based on a third image block in a reference image area corresponding to each image to be processed, wherein the third image block includes a reference tracking object, and the first image result is a composite image that presents each third image block in sequence according to the shooting time sequence of each image to be processed;

[0014] A second storage module is used to obtain and store a second image result based on a fourth image block in a reference image area corresponding to each image to be processed, wherein the fourth image block does not contain a reference tracking object, the third image block and / or the fourth image block includes a reference marker object, and the second image result includes image information formed by adding the fourth image blocks corresponding to each image to be processed to different color channels respectively.

[0015] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the efficient storage method of any one of the above embodiments.

[0019] In a fourth aspect, an embodiment of the present invention further provides a computer-readable medium, wherein the computer-readable medium stores computer instructions, and the computer instructions are used to enable a processor to implement the efficient storage method of any one of the above embodiments when executed.

[0020] The technical solution of the embodiment of the present invention determines a group of images to be processed including images to be processed, each of which is a different captured image of a reference tracking object from the same field of view, and determines the reference image area corresponding to each image to be processed, each reference image area completely covers the reference tracking object and the reference marker object, and ensures that the reference tracking object and the reference marker object images can be stored completely to avoid losing key information. The first image result is obtained based on the third image block in the reference image area corresponding to each image to be processed, so as to present each third image block in the order of shooting time, which can not only clearly show the state change and position movement of the reference tracking object at different time points, but also reduce the amount of data reflecting the location area of ​​the reference tracking object by nearly half, which can save storage space, improve transmission efficiency, reduce the requirements for storage devices and network bandwidth, and fully reflect the true color information of the reference tracking object itself. However, the second image result is obtained based on the fourth image block in the reference image area corresponding to each image to be processed, and the fourth image block that does not contain the reference tracking object is added to different color channels respectively, so that the background information of different images can be distinguished and integrated, and the environmental background of the reference tracking object can be better analyzed. At the same time, the detailed information near the reference tracking object is retained, so that the details of the surrounding environment can be presented, providing more detailed content for subsequent image processing and analysis.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0023] Figure 1 This is a schematic diagram of a flow chart of an efficient storage method provided by an embodiment of the present invention;

[0024] Figure 2a is a schematic diagram of an image group in which images are interrelated in an efficient storage provided by an embodiment of the present invention;

[0025] Figure 2b It is a schematic diagram of a local image region containing a reference tracking object in an image to be processed provided by an embodiment of the present invention;

[0026] Figure 2c is a schematic diagram of a first image result in an efficient storage provided by an embodiment of the present invention;

[0027] Figure 2d is a schematic diagram of another first image result in efficient storage provided by an embodiment of the present invention;

[0028] Figure 2e is a schematic diagram of a second image result in efficient storage provided by an embodiment of the present invention;

[0029] Figure 2f is a schematic diagram of another efficient storage of a second image result provided by an embodiment of the present invention;

[0030] Figure 3 It is a flowchart of another efficient storage method provided by an embodiment of the present invention;

[0031] Figure 4a It is a schematic diagram of screening image blocks including reference tracking objects in an efficient storage provided by an embodiment of the present invention;

[0032] Figure 4b It is a schematic diagram of constructing a reference selection box in an efficient storage provided by an embodiment of the present invention;

[0033] Figure 4c It is a moving schematic diagram of an efficient storage reference selection box provided by an embodiment of the present invention;

[0034] Figure 5 It is a schematic diagram of the structure of a high-efficiency storage device provided by an embodiment of the present invention;

[0035] Figure 6 It is a structural schematic diagram of an electronic device for implementing an efficient storage method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0037] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0038] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0039] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0040] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0041] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0042] Figure 1 A flow chart of an efficient storage method provided in an embodiment of the present invention is applicable to the case of efficiently storing a plurality of mutually related images to be processed. The efficient storage method can be executed by an efficient storage device, which can be implemented in the form of software and / or hardware, and optionally, by an electronic device, which can be a mobile terminal, a PC or a server, etc.

[0043] like Figure 1 As shown, the efficient storage method provided in this embodiment may include the following process:

[0044] S110: Determine a to-be-processed image group, where the to-be-processed image group includes at least two to-be-processed images, each of which is a different captured image of a reference tracking object from a captured screen at the same field of view angle.

[0045] In order to achieve load balancing of storage devices, each front-end camera sends the image to be processed to each storage node in turn according to the polling principle, and then aggregates and stores the image to be processed written to each storage node. However, the above scheme does not take into account the mutual information reference between the images to be processed, resulting in a large amount of data. To this end, this scheme fully considers the mutual information reference between the images to be processed during image storage, and groups multiple images to be processed with mutual information reference into a group of images to be processed. Polling and storing storage nodes in units of image groups to be processed means that instead of processing a single image to be processed, the entire image group to be processed is taken as a whole and queried, stored or other operations are performed on different storage nodes. In this way, the mutual information reference between the images to be processed can be fully considered during image storage, so that the images to be processed can be further compressed and stored. Among them, storage nodes generally refer to devices or servers used to store image data.

[0046] See also Figure 2a Each image to be processed in the image group to be processed is a set composed of at least two different captured images of the reference tracking object from the same field of view, which means that these images to be processed are obtained by shooting the specific reference tracking object from the same observation angle, and each image to be processed is captured at different capturing times, so the state and position changes of the reference tracking object at different times under the same field of view are recorded, that is, these images to be processed jointly record the state changes and position movements of the specific reference tracking object over a period of time, and the reference tracking objects contained in each image to be processed are correlated with each other.

[0047] Optionally, the images to be processed are different captured images of the captured images from the same field of view of the reference tracking object, and these images to be processed contain specific reference tracking objects. The reference tracking object can be a vehicle for violation detection at a traffic intersection, or a target such as a pedestrian that needs to be paid attention to and analyzed.

[0048] See also Figure 2a Through the image group to be processed, multiple images to be processed for the same reference tracking object and field of view can be processed collectively, avoiding the isolated processing of a single image to be processed. Not only the processing efficiency is improved, but more importantly, the correlation between the reference tracking objects can be used to further compress the images to be processed. For example, when performing correlation analysis on a series of continuously captured images to be processed of the same reference tracking object, the entire image group can be further compressed and stored at one time. Moreover, each image to be processed comes from the same field of view, which makes the analysis of the reference tracking object more accurate and convenient, and the position changes and morphological changes of the reference tracking object in different images to be processed can be directly compared, without considering the perspective differences and deformation problems caused by different field of view angles.

[0049] By adopting the above scheme, the image group is polled as a unit, which can manage and store image data more efficiently. For example, during the storage process, the entire image group can be stored in a suitable storage node at one time, avoiding repeated operations on a single image, reducing storage time and resource consumption, and when storing images, the mutual information reference between the images to be processed can be fully considered, so that the images to be processed can be further compressed and stored, reducing the space occupied by image storage.

[0050] As an optional but non-limiting implementation method, at least two images to be processed in each group of images to be processed include at least a first image to be processed, a second image to be processed and a third image to be processed. The first image to be processed is a snapshot image when the reference tracking object approaches the stop line of the traffic intersection but has not reached the stop line of the traffic intersection when the traffic light indicates a no-traffic stage (such as the red light is on). The second image to be processed is a snapshot image when the reference tracking object has crossed the stop line of the traffic intersection when the traffic light indicates a no-traffic stage. The third image to be processed is a snapshot image when the reference tracking object continues to move forward in the direction of travel relative to the position of the second image to be processed when the traffic light indicates a no-traffic stage.

[0051] Among them, each image group to be processed also includes a captured image with an object identifier for describing a reference tracking object, and the captured image with an object identifier for describing the reference tracking object carries a reference image identifier for characterizing that the captured image with the object identifier describing the reference tracking object is not compressed and stored.

[0052] See also Figure 2a , taking the example of not following the traffic lights at a traffic intersection, a chain of evidence for determining not following the traffic lights at a traffic intersection is usually composed of four images. These four images record the process of the reference tracking object not following the traffic lights from different stages, providing conclusive evidence for determining whether the reference tracking object follows the traffic lights. Among them, the first image is when the vehicle does not reach the stop line when the light is red, which is used to determine the initial position of the reference tracking object when the red light is on; the second image is when the reference tracking object has crossed the stop line when the light is red, indicating that the reference tracking object continues to move forward and crosses the stop line when the light is red; the third image is when the reference tracking object is red, and the position in the second image is forward (usually reaching the opposite stop line), which further shows the movement of the reference tracking object in the process of running a red light; the fourth image is a close-up of the object identification (such as the license plate) of the reference tracking object, which is used to clearly record the object identification of the reference tracking object that does not follow the traffic lights.

[0053] See also Figure 2a, the field of view and orientation of the first, second and third images to be processed are exactly the same, which means that these images to be processed are taken from the same angle, and the position changes of the reference tracking object at different stages can be more intuitively compared. This consistency makes the three images highly mutually referenceable, and can more accurately judge the trajectory of the reference tracking object and whether it is moving according to the traffic lights. In addition, since the shooting time difference is in seconds, the lighting and background of the pictures are basically the same. This helps to reduce interference caused by lighting changes or background differences.

[0054] S120. Determine the reference image area corresponding to each image to be processed, each reference image area can completely cover the reference tracking object and the reference marker object included in the image to be processed, the reference image area is a local image area in the image to be processed, and the reference image area is formed based on at least two image blocks of the same shape and size.

[0055] See also Figure 2b The reference image area corresponding to each image to be processed can be a local image area screened and determined from each image to be processed, which can completely cover the reference tracking object and the reference marker object included in the image to be processed, that is, the reference tracking object and the reference marker object included in the image to be processed are completely presented in the reference image area, and at the same time, the image areas that are not concerned in the image to be processed are eliminated, and the reference image area is ensured as much as possible not to contain the image areas that are not concerned in the image to be processed, so that the image size of the reference image area is smaller than the image size of the image to be processed.

[0056] Optionally, the reference tracking object is the main target of attention. For example, in the judgment of not following the traffic lights at the intersection, the vehicle can be considered as the reference tracking object. However, the reference sign object is usually an object with a fixed position or feature related to the reference tracking object, which is used to assist in determining the position, state, etc. of the reference tracking object. For example, in a traffic scene, traffic lights, stop lines, road signs, etc. can all be used as reference sign objects.

[0057] The reference image area contains not only the reference tracking object, but also the reference sign objects, which can provide additional information for analysis. For example, the state of the reference sign object can help determine whether the behavior of the reference tracking object is legal. For example, in a traffic scene, the color of the traffic light can be combined with the position of the vehicle to determine whether the vehicle ran a red light.

[0058] Optionally, by identifying the positions of reference tracking objects and reference marker objects in the image to be processed, and then determining an area that can completely contain them as a reference image area, the size and shape of this reference image area may be adjusted according to the specific objects and scenes to ensure that all reference tracking objects and reference marker objects can be accurately covered in the reference image area.

[0059] Since the reference image area completely covers the reference tracking object and the reference marker object, even when there are interference factors in the image or the position of the target object changes, the reference tracking object and the reference marker object can be more easily presented. Moreover, the limited reference image area is a local image area selected from the image to be processed, and the image size of the reference image area is smaller than the image size of the image to be processed, which can reduce the storage space occupied by storing the image.

[0060] The reference image area is composed of at least two image blocks of the same shape and size, which means that the reference image area is pre-cut into image blocks of the same shape and size. Image blocks are small areas into which an image is divided. These image blocks can be regular rectangles, squares, etc., or irregular shapes divided according to a specific algorithm. Each image block contains image pixel information within a certain range.

[0061] The same shape between image blocks may refer to the outer contour or geometric shape of the image blocks being consistent. For example, if the image blocks are all rectangular, then their four corners are right angles and the ratio of the side lengths is the same. The same size between image blocks may refer to the range occupied by the image blocks in the spatial dimension being consistent, and the size can be measured by the number of pixels, actual size (such as centimeters, inches, etc.). For example, if the image blocks are all rectangles of 100×100 pixels.

[0062] Since the reference image area is composed of several image blocks of the same shape and size, the image storage has a standardized minimum storage unit. This standardized storage facilitates the unified processing and management of image storage, and improves the efficiency of storage and processing. In particular, after determining the block as the minimum unit of storage, subsequent compression operations can be performed around the fixed storage unit. Since the reference image area is composed of an integer multiple of image blocks, the compression process is more efficient and regular, and image compression can be performed according to the characteristics of the image block, thereby improving the compression ratio and reducing the storage space occupied.

[0063] At the same time, storing an integer multiple of image blocks can avoid fragmentation during the storage process, making the storage more compact and orderly, and can solve the problem that file fragmentation will lead to waste of storage space and reduced storage efficiency, effectively avoiding the generation of file fragments and improving the utilization of storage space. In short, dividing the image into image blocks of fixed size and storing them as integer multiples of image blocks effectively avoids file fragmentation, improves storage efficiency, enhances data integrity, and facilitates data management and maintenance.

[0064] S130, obtaining and storing a first image result based on the third image block in the reference image area corresponding to each image to be processed, wherein the third image block includes a reference tracking object, and the first image result is a composite image that presents each third image block in sequence according to the chronological order of shooting time of each image to be processed.

[0065] See also Figure 2b and Figure 2c , for each reference image area corresponding to the image to be processed, the reference image area is composed of at least two image blocks of the same shape and size, and a third image block containing a reference tracking object can be extracted from the reference image area. Then, the third image blocks included in each reference image area are stitched together into one image in the order of the shooting time of each image to be processed, and the first image result is obtained and stored. For example, for a series of continuously shot traffic monitoring images, the third image blocks containing vehicles in each reference image area are synthesized in time sequence to form a first image result showing the vehicle's driving trajectory. Alternatively, see Figure 2b and Figure 2d The third image block may also include a reference marker object (such as Figure 2d In this way, the first image result will include a third image block that is stitched and synthesized in chronological order and includes a reference tracking object and a reference marker object.

[0066] By adopting the above method, each third image block is presented in the order of shooting time, which can not only clearly show the state changes and position movements of the reference tracking object at different time points, but also reduce the amount of data reflecting the location area of ​​the reference tracking object by nearly half, which can save storage space, improve transmission efficiency, reduce the requirements for storage devices and network bandwidth, and fully reflect the true color information of the reference tracking object itself.

[0067] S140, obtaining and storing a second image result based on the fourth image block in the reference image area corresponding to each image to be processed, wherein the fourth image block does not contain a reference tracking object, the third image block and / or the fourth image block includes a reference marker object, and the second image result includes image information formed by adding the fourth image blocks corresponding to each image to be processed to different color channels respectively.

[0068] See also Figure 2b and Figure 2e , from the reference image area corresponding to each image to be processed, a portion that does not contain the reference tracking object is selected as the fourth image block, and in the reference image area, except for the third image block that contains the reference tracking object, other image blocks are determined as the fourth image blocks. For example, in a group of images that contain a specific person as a reference tracking object, the reference image area is an image area range within a certain range surrounding the reference tracking object, and the portion of the image block that does not contain the reference tracking object within the reference image area is the fourth image block, which may be the environmental background surrounding the reference tracking object.

[0069] See also Figure 2b and Figure 2e When generating the second image result, the fourth image blocks in the corresponding reference image areas of each image to be processed are added to different color channels respectively, which means that when the fourth image blocks in different reference image areas are generated, the color channel information of a color channel is extracted from the fourth image blocks, so that the fourth image blocks in different images to be processed are allocated to different color channels to form new image information. Then the image information formed by the fourth image blocks in different reference image areas that have been added to different color channels constitutes the second image result. For example, the color channel may include three color channels: red, green, and blue. If there are fourth image blocks of three images to be processed, the fourth image block of the first image may be added to the red channel, the fourth image block of the second image may be added to the green channel, and the fourth image block of the third image may be added to the blue channel.

[0070] After the fourth image blocks in the three images to be processed are added to different color channels respectively and the signal light block set is processed, the three different image color channels are finally combined to form a second image result of a complete color channel. Since the fourth image blocks in different images to be processed are added to different color channels respectively, the second image result of the complete color channel contains more detail information, and the combination of different color channels can present richer details, providing more basis for image analysis and processing. By generating the second image result, the fourth image blocks of multiple reference image areas can be integrated together, which saves storage space compared to storing multiple separate image blocks.

[0071] In one example, the fourth image block may include a reference marker object or may not include a reference marker object, see Figure 2e If the fourth image block includes a reference marker object, the second image result is based on the fourth image block that does not include the reference tracking object and the fourth image block that includes the reference marker object (such as Figure 2e The fourth image block of the signal light in the image is generated; see Figure 2f If the fourth image block does not include the reference marker object, the second image result is generated based only on the fourth image block that does not include the reference tracking object, and does not involve the fourth image block that includes the reference marker object (such as Figure 2e The fourth image block of the signal light in the image.

[0072] The technical solution of the embodiment of the present invention determines a group of images to be processed including images to be processed, each of which is a different captured image of a reference tracking object from the same field of view, and determines the reference image area corresponding to each image to be processed, each reference image area completely covers the reference tracking object and the reference marker object, and ensures that the reference tracking object and the reference marker object images can be stored completely to avoid losing key information. The first image result is obtained and stored based on the third image block in the reference image area corresponding to each image to be processed, so as to present each third image block in the order of shooting time, which can not only clearly show the state change and position movement of the reference tracking object at different time points, but also reduce the amount of data reflecting the location area of ​​the reference tracking object by nearly half, which can save storage space, improve transmission efficiency, reduce the requirements for storage devices and network bandwidth, and fully reflect the true color information of the reference tracking object itself. However, the second image result is obtained based on the fourth image block in the reference image area corresponding to each image to be processed, and the fourth image block that does not contain the reference tracking object is added to different color channels respectively, so that the background information of different images can be distinguished and integrated, and the environmental background of the reference tracking object can be better analyzed. At the same time, the detailed information near the reference tracking object is retained, so that the details of the surrounding environment can be presented, providing more detailed content for subsequent image processing and analysis.

[0073] Figure 3 A flow chart of another efficient storage method provided for an embodiment of the present invention. The technical solution of this embodiment further optimizes the process of determining the reference image area corresponding to each image to be processed in the aforementioned embodiment on the basis of the technical solution of the aforementioned embodiment. This embodiment can be combined with various optional solutions in one or more of the aforementioned embodiments.

[0074] like Figure 3 As shown, the efficient storage method provided in this embodiment may include the following process:

[0075] S310: Determine a to-be-processed image group, where the to-be-processed image group includes at least two to-be-processed images, each of which is a different captured image of a capture screen from the same field of view angle for a reference tracking object.

[0076] S320, determining the reference selection frame required for each image to be processed, where the reference selection frame is formed by aggregating a border formed by at least two first image blocks and a border formed by a second image block, where each first image block is an image block that includes at least a reference tracking object and / or a reference marking object among at least two image blocks pre-divided corresponding to the image to be processed, and the second image block is used to connect non-adjacent first image blocks to form a continuous whole.

[0077] See also Figure 4a , the image to be processed is pre-divided into several image blocks. Since the similarities between the images to be processed in the image group to be processed are very high, in order to more effectively store and process each image to be processed, each image to be processed is divided into N×M image blocks with N horizontal and M vertical dimensions. This division method divides the image into regular small units, and each image block becomes the smallest unit for storage. For example, if the resolution of the image is 1000×800, it is divided into 10 horizontal and 8 vertical image blocks, then the size of each image block is 100×100 pixels.

[0078] See also Figure 4a After determining that the image block is the smallest unit of storage, no matter how the subsequent screening and compression are performed, all images to be processed are stored in an integer multiple of the area of ​​the image block, which means that the size of the stored image must be an integer multiple of the image block size, avoiding the storage of irregular partial image blocks, thereby effectively avoiding the generation of file fragments. For example, if the block size is 100×100 pixels, then the stored image can be 200×200 pixels, 300×300 pixels, etc., but not 250×250 pixels.

[0079] See also Figure 4a , respectively identify the first image block containing at least the reference tracking object and / or the reference marker object from each image to be processed, that is, the image block occupied by the reference tracking object and / or the reference marker object, which can be achieved by image recognition, such as a target detection algorithm, which can locate the position of the reference tracking object and / or the reference marker object in the image to be processed and determine the image block occupied by the reference tracking object and / or the reference marker object. For example, through the target detection algorithm, it can be determined that the vehicle to be processed is located in the image block from the 3rd row and the 5th column to the 4th row and the 6th column, and the traffic light is located in the image block from the 7th row and the 2nd column.

[0080] See also Figure 4a , the first image block refers to the first image block that contains at least a reference tracking object and / or a reference sign object among the several image blocks into which the image to be processed is pre-divided. The reference tracking object and the reference sign object are targets with specific meaning and importance in the image. For example, in a traffic monitoring image, a vehicle can be a reference tracking object, and a traffic light can be a reference sign object. In actual situations, since each first image block is screened from the several image blocks into which the image to be processed is pre-divided, some first image blocks containing reference tracking objects may not be adjacent to each other. Therefore, it is necessary to add some second image blocks to play a connecting role, and the non-adjacent first image blocks are connected by the second image blocks to form a continuous whole.

[0081] See also Figure 4b The reference selection frame is formed by aggregating the borders formed by at least two first image blocks and the borders formed by the second image block, which means that a selection frame that can surround all reference tracking objects and / or reference marker objects is determined by determining the borders of the first image block containing the reference tracking object and the borders of the second image block connecting these blocks. For example, in a group of images, by identifying the first image block and the second image block in each image, and then determining a reference selection frame (which can be a rectangular frame or a polygonal frame of other shapes) based on the borders of these blocks, this selection frame can contain all reference tracking objects and reference marker objects as completely as possible.

[0082] For example, see Figure 4a and Figure 4b , taking the case that the image group to be processed includes three images to be processed, in order to achieve the purpose of continuous area, the first image blocks containing reference tracking objects and / or reference marker objects in the three images to be processed are taken to form a collection. If the collection has formed a continuous area, the reference selection box is formed; if the collection is still separated, the second image block in the image to be processed is found, and the separated first image block areas are connected into a continuous area. The exhaustive method can be used to try one by one. For example, by connecting the second image block to the first image block containing the reference tracking object and / or the reference marker object, a valid area of ​​X (X≤N*M) blocks can be divided, see Figure 4b In the middle yellow area, the three images to be processed occupy 6 image blocks each, and the border of this valid area is called the reference selection box.

[0083] In the above manner, by determining the reference selection frame, attention can be focused on the area containing the reference tracking object and the reference marker object, highlighting the key target in the image. The introduction of the second image block enables the non-adjacent first image blocks to be connected to form a continuous whole, which helps to maintain the integrity and readability of the image and avoid the fragmentation of the target due to the division of the image. After determining the reference selection frame, specific processing can be performed on the area within this frame without having to process the entire image, which can greatly improve processing efficiency and reduce the consumption of computing resources.

[0084] Optionally, three images not marked as reference images are selected from the image group to be processed, and local image areas that can completely cover the reference tracking object and the reference mark object included in the image to be processed are extracted from each pair to be processed and used as the reference image area. Considering that each image to be processed in the image group to be processed captured by the camera usually contains irrelevant redundant areas, the image areas involving other tracking objects that are not related to the reference tracking object are deleted, and only the effective area that is sufficient to reflect the entire process of the reference tracking object continuing to move in the traffic light indication in the no-traffic stage is retained. This effective area includes three parts: one is the three image block areas where the reference tracking object continues to move in the traffic light indication in the no-traffic stage, the second is the image block area where the traffic light is located, and the third is the image block area where these two parts of the image block area are connected to form a continuous whole.

[0085] As an optional but non-limiting implementation method, each image to be processed is pre-divided into at least two image blocks of the same shape and size, and the position and size of the at least two image blocks pre-divided in each image to be processed are adjusted and determined based on the capture position area where the reference tracking object is located when the reference tracking object is captured, so that the image blocks containing the reference tracking object in each image to be processed do not overlap with each other in position.

[0086] See also Figure 4a , each image to be processed records three position areas of the reference tracking object, which means that these images to be processed are taken at different places or times. Since the reference tracking object is in different positions, these three positions need to be recorded and analyzed separately. These three positions are separated from each other. In order to better analyze the movement of the reference tracking object during the waiting stage indicated by the traffic light, the images to be processed need to be segmented so that the image blocks occupied by the reference tracking objects in the three images to be processed do not overlap with each other. This can be achieved by adjusting the position and size of the image blocks. Adjusting the position and size of the blocks can assign the reference tracking object in each image to be processed to an independent image block.

[0087] See also Figure 4a, the positions and sizes of at least two image blocks pre-divided in each to-be-processed image are adjusted and determined according to the capture position area where the reference tracking object is located, that is, the division of the image blocks can be dynamically adjusted according to the appearance position of the reference tracking object in different images, so that the divided blocks can better adapt to the position change of the tracking object. One of the purposes of adjusting the image blocks is to make the image blocks containing the reference tracking object in each to-be-processed image not overlap in position, so as to ensure that each reference tracking object is assigned to an independent image block, avoiding the overlap of image blocks containing the same reference tracking object.

[0088] See also Figure 4a , the image block when the reference tracking object does not reach the stop line must include the stop line on the side of the traffic intersection. This is to ensure that when analyzing the reference tracking object, it can be accurately judged whether the reference tracking object stops moving before the stop line. If the image block when the reference tracking object does not reach the stop line does not include the stop line on the side of the traffic intersection, then when analyzing whether the reference tracking object violates the traffic lights or other violations, incorrect judgments may occur.

[0089] As an optional but non-limiting implementation, determining the reference selection frame required for each image to be processed includes the following steps A1-A2:

[0090] Step A1: For each image to be processed, color comparison is performed based on color information corresponding to the reference tracking object and color information of each image block pre-divided in the image to be processed.

[0091] Step A2: based on the color comparison result, at least two image blocks pre-divided from the image to be processed include at least a first image block of a reference tracking object, so as to construct a reference selection box required for each image to be processed, and the similarity between the color information of the first image block and the color information corresponding to the reference tracking object is greater than a preset similarity.

[0092] See also Figure 4aFor each image to be processed, the color information corresponding to the reference tracking object in each image to be processed is determined, which can be obtained by color analysis of the known reference tracking object, and the color information may include a specific red hue, saturation and brightness range. Then, the color information of the reference tracking object is compared with the color information of each pre-divided image block in the image to be processed. This comparison can be achieved by calculating the similarity between colors, such as using a color distance algorithm or other related color comparison methods. For example, for an image block, if its main color is red, and the red color of the reference tracking object is close in hue, saturation and brightness, then it can be considered that this image block has a certain similarity in color with the reference tracking object.

[0093] See also Figure 4a , based on the result of color comparison, at least first image blocks containing a reference tracking object are screened out from at least two image blocks pre-divided in the image to be processed, and the similarity between the color information of these first image blocks and the color information corresponding to the reference tracking object is greater than a preset similarity. The preset similarity is a preset threshold value used to determine which image blocks may contain the reference tracking object. For example, if the preset similarity is 80%, only those image blocks whose color similarity with the reference tracking object is greater than 80% will be selected as first image blocks. Finally, these first image blocks are used to construct the reference selection box required for each image to be processed. The reference selection box can be a rectangular box or a box of other shapes surrounding all the first image blocks. Its purpose is to select the area that may contain the reference tracking object for subsequent processing and analysis.

[0094] For example, see Figure 4a After dividing each image to be processed into multiple image blocks, the image blocks involved in the reference tracking object or the reference marker object are retained. The color of the reference tracking object can be obtained through reference tracking object recognition, and then it is determined whether the color exists in each image block near the reference tracking object. If the color exists, it means that the image block belongs to the image block occupied by the reference tracking object. This method can avoid the complex and precise calculation of the contour of the reference tracking object.

[0095] By comparing and screening based on color information, image blocks that may contain reference tracking objects can be determined more quickly. Color is an important feature of an image. For certain targets, such as objects of a specific color or objects with obvious color features, using color information can effectively narrow the search range and improve the accuracy of target detection. Only analyzing and comparing the color of the first image block that may contain the reference tracking object, rather than performing a comprehensive analysis of the entire image, avoids complex and detailed calculations of the reference tracking object's outline, which can greatly reduce the computational complexity. At the same time, color information is relatively stable and is not easily affected by factors such as changes in lighting and angles.

[0096] S330. According to the reference selection box required by each image to be processed, a reference image area corresponding to each image to be processed is determined from each image to be processed. The reference image area is a local image area screened out from the image to be processed according to the reference selection box mapped to the image to be processed. The reference image area can completely cover the reference tracking object and the reference marker object included in the image to be processed. The image block in the reference image area has the same shape and size as the image block pre-divided for the image to be processed.

[0097] The reference image region is a local image region in the image to be processed, and the reference image region is formed based on at least two image blocks of the same shape and size.

[0098] See also Figure 4a The reference image area is a local image area selected from the image to be processed. This selection process is based on the reference selection box mapped to the image to be processed, that is, the reference selection box defines a specific range on the image to be processed, and the image area within this range is the reference image area. An important feature of the reference image area is that it can completely cover the reference tracking objects and reference marker objects included in the image to be processed. The reference tracking object is usually a specific target that needs to be focused on and tracked, while the reference marker object can be some iconic elements that assist in identification and positioning.

[0099] See also Figure 4a , the image blocks in the reference image area have the same shape and size as the image blocks pre-divided for the image to be processed. This means that when the image to be processed is pre-divided, a specific shape and size standard of the image blocks is determined, and the image blocks in the reference image area also follow this standard. The reference image area is composed of at least two image blocks of the same shape and size, that is, the reference image area is not a random image part, but is composed of image blocks arranged according to certain rules, and these image blocks together constitute a reference image area with a specific shape and range.

[0100] As an optional but non-limiting implementation, according to the reference selection box required by each image to be processed, the reference image area corresponding to each image to be processed is determined from each image to be processed, including the following steps B1-B2:

[0101] Step B1, deleting the target border in the reference selection frame mapped to each image to be processed to obtain the target selection frame required by each image to be processed, wherein the target border is a border that does not contain a target detection frame in the borders formed by each image block corresponding to the reference selection frame after the reference selection frame is controlled to move synchronously in each image to be processed, and the target border will not destroy the continuous overall state of the borders formed by each image block corresponding to the reference selection frame after being deleted from the borders formed by each image block corresponding to the reference selection frame, wherein the target detection frame is a detection frame that tracks the reference tracking object and the reference mark object in the image to be processed respectively.

[0102] Step B2: using the target selection box mapped to each image to be processed, respectively screening out reference image regions corresponding to each image to be processed from each image to be processed.

[0103] See also Figure 4c , the target frame is the frame that does not contain the target detection frame in the frame formed by each image block corresponding to the reference selection frame detected after the reference selection frame is controlled to move synchronously in each image to be processed. The target detection frame is the detection frame that tracks the reference tracking object and the reference mark object in the image to be processed respectively, which means that the image block surrounded by the target frame does not contain the object to be tracked. The target frame also needs to meet another condition, that is, after being deleted from the frame formed by each image block corresponding to the reference selection frame, it will not destroy the continuous overall state between the frames formed by each image block corresponding to the reference selection frame. This means that after deleting the target frame, the remaining frames can still form a continuous whole, and there will be no separation or discontinuity of the image blocks. For example, if a gap or discontinuous part appears between the image blocks after deleting a certain frame, then this frame is not the target frame. After the target frame is screened out by the above conditions, it is deleted from the reference selection frame mapped to each image to be processed to obtain the target selection frame required by each image to be processed. The target selection frame is the result of removing the frames that do not contain the target detection frame and do not destroy the continuous overall state on the basis of the reference selection frame.

[0104] The target selection box mapped to each image to be processed is used to filter out the reference image area corresponding to each image to be processed from each image to be processed. Since the target selection box is optimized based on the reference selection box, the reference image area containing the reference tracking object and the reference sign object can be more accurately filtered out using the target selection box. For example, in a traffic monitoring image, the target selection box can be used to more accurately select the area containing vehicles and traffic signs as the reference image area.

[0105] As an optional but non-limiting implementation, the target frame in the reference selection frame mapped to each image to be processed is deleted to obtain the target selection frame required by each image to be processed, including steps C1-C3:

[0106] Step C1, controlling the reference selection box mapped to each image to be processed to synchronously perform a reference movement operation in each image to be processed; wherein the reference movement operation is to move the reference selection box mapped to the image to be processed along a reference direction and a reference speed in the image to be processed while ensuring that all target detection boxes are within the reference selection box.

[0107] Among them, the reference direction corresponding to the reference movement operation includes at least one of the following: the direction of upward translation in the image to be processed, the direction of downward translation in the image to be processed, the direction of left translation in the image to be processed, and the direction of right translation in the image to be processed.

[0108] Step C2: When it is detected that the reference side edge of the target detection frame overlaps with the reference side edge of the reference selection frame mapped to the image to be processed, stop the reference selection frame and synchronously perform reference movement operations in each image to be processed, and the reference side is the side opposite to the reference direction.

[0109] Step C3, for the reference selection boxes mapped to each image to be processed, if it is detected that there is a target border in the borders formed by each image block corresponding to the reference selection box mapped to each image to be processed, the target border is deleted from the borders formed by each image block corresponding to the reference selection box, and the reference selection boxes mapped to each image to be processed after the target border is deleted are re-merged to obtain the target selection boxes required by each image to be processed.

[0110] In order to further reduce the number of borders formed by the image blocks included in the reference selection frame, the four up, down, left and right movement schemes of the reference candidate frame can be traversed to further delete the borders in the reference selection frame, and the movement scheme with the least remaining reference selection borders is selected to determine the target selection frame corresponding to the final valid area.

[0111] Refer to the right move solution of the selection box: Figure 4b and Figure 4c , using the previously obtained reference selection frame and four target detection frames (such as the target detection frames of the reference tracking object and the reference identification object), calculate the minimum distance L between the left edge of the four target detection frames and the left edge of the reference selection frame. The way to calculate the minimum distance L is to let the reference selection frame corresponding to the effective area move right synchronously in the three images to be processed until the left edge of any reference selection frame touches the target detection frame corresponding to the reference tracking object or reference identification object of any image to be processed. This method can avoid the complex and detailed calculation of the target contour of the vehicle or traffic light. Traverse the three images to be processed respectively, and determine whether there is a target frame formed by the image block without a target detection frame in the reference selection frame after the reference selection frame is moved right by a distance of L. Delete the target frame, and recombine to form the final effective area, which can be used as the target selection frame. The left shift scheme of the reference selection frame is similar and will not be repeated here.

[0112] Take the downward movement of the reference selection box as an example, see Figure 4b and Figure 4c , using the reference selection frame and the four target detection frames obtained above, calculate the minimum distance L between the upper edge of the four target detection frames and the upper edge of the reference selection frame. Traverse the three images to be processed respectively, and determine whether there is a target frame formed by an image block without a target detection frame in the reference selection frame after the reference selection frame moves down by a distance U, delete the target frame formed by the image block, and recombine to form the final valid area. The upward movement scheme of the reference selection frame is similar and will not be repeated here.

[0113] See also Figure 4b and Figure 4c , taking the right shift of the reference selection box as an example, the distance between the left edge of the vehicle and signal light target detection box and the left edge of the reference selection box is calculated on the three new images after the first round of processing. It is found that the minimum distance difference between the left edge of the signal light target detection box and the left edge of the reference selection box is L, then the reference selection box is shifted right by L, and it is judged that there are two image blocks without target detection boxes after the reference selection box is shifted right by L, so the two blocks are deleted and recombined to form the final valid area, see the green area. By traversing the four moving schemes of the reference selection box, it is determined that the right shift is the scheme with the least remaining mask blocks, and the target selection box corresponding to the final valid area is determined based on this.

[0114] S340, obtaining and storing a first image result based on the third image block in the reference image area corresponding to each image to be processed, wherein the third image block contains a reference tracking object, and the first image result is a composite image that presents each third image block in sequence according to the chronological order of shooting time of each image to be processed.

[0115] As an optional but non-limiting implementation, obtaining a first image result based on a third image block in a reference image region corresponding to each image to be processed includes the following steps D1-D2:

[0116] Step D1: According to the sequence of shooting time of each to-be-processed image, a reference image region corresponding to the to-be-processed image with the earliest shooting time is determined from each to-be-processed image.

[0117] Step D2, in accordance with the chronological order of shooting time of each image to be processed, the third image blocks in the remaining reference image areas corresponding to each image to be processed, except for the reference image area corresponding to the image to be processed with the earliest shooting time, are sequentially superimposed on the reference image area corresponding to the image to be processed with the earliest shooting time to perform image synthesis, so that the third image blocks in the reference image areas corresponding to each image to be processed can be presented in the chronological order of shooting time of each image to be processed in the first image result after image synthesis.

[0118] See also Figure 2c , arrange the images to be processed in chronological order according to their shooting time, and then determine the reference image area corresponding to the image to be processed with the earliest shooting time from these images to be processed. This reference image area is determined according to the aforementioned method and can completely cover the reference tracking objects and reference sign objects included in the image to be processed. For example, assuming that there is a group of images of traffic scenes shot at different times, first find the image with the earliest shooting time, and then determine the reference image area in the image, which may contain a reference tracking object such as a specific vehicle and a reference sign object such as a traffic light.

[0119] See also Figure 2c , according to the sequence of shooting time of each to-be-processed image, the third image blocks in the remaining reference image areas (i.e., other reference image areas except the reference image area with the earliest shooting time) in the reference image areas corresponding to each to-be-processed image except the reference image area corresponding to the to-be-processed image with the earliest shooting time are sequentially superimposed on the reference image area corresponding to the to-be-processed image with the earliest shooting time. The third image block is a part of the reference image area. Through the superposition operation, each third image block in the reference image area corresponding to each to-be-processed image can be presented according to the sequence of shooting time of each to-be-processed image.

[0120] See also Figure 2cOptionally, the third image blocks in the reference image blocks sorted according to the shooting time are sequentially synthesized. The synthesis process may involve operations such as image stitching and fusion, so that the third image blocks can be organically combined together to form a continuous overall image. The first image result is finally obtained. The first image result is displayed by combining the third image blocks in the reference image blocks of each image to be processed in the order of shooting time.

[0121] Optionally, for each reference image area corresponding to the image to be processed, a third image block containing the reference tracking object is further extracted, which can be achieved by using the image recognition algorithm again to accurately locate the position of the reference tracking object in the reference image area and extracting the smallest image block containing the object as the third image block. Furthermore, the synthesis order of the third image block can be determined according to the order of shooting time of each image to be processed, and the shooting time order of each image to be processed can be determined by reading the timestamp information of each image to be processed or according to the numbering order of the images to be processed.

[0122] Figure 2b and Figure 2c Taking the case where the image group to be processed includes at least the first image to be processed, the second image to be processed and the third image to be processed, which are three images captured in the traffic scene, the block occupied by the vehicle in the second image and the block occupied by the vehicle in the third image are superimposed on the first image according to the original positions, so that one image contains three positions of the vehicle. This process of merging using blocks does not require accurate detection of the contour of the vehicle and has a small amount of calculation.

[0123] See also Figure 2c Each third image block contains the shooting time point information when the snapshot was taken. The time information accurate to the second level can be superimposed on the image in the form of an on-screen menu adjustment (OSD), so that the timing information can be clearly displayed and the complete process of the vehicle violation can be clearly displayed. In this synthesized first image result, the part from the first image is called block set A, the part from the second image is called block set B, and the part from the third image is called block set C.

[0124] S350, obtaining and storing a second image result based on the fourth image block in the reference image area corresponding to each image to be processed, wherein the fourth image block does not contain a reference tracking object, the third image block and / or the fourth image block includes a reference marker object, and the second image result includes image information formed by adding the fourth image blocks corresponding to each image to be processed to different color channels respectively.

[0125] As an optional but non-limiting implementation, obtaining a second image result based on a fourth image block in a reference image region corresponding to each image to be processed includes the following steps F1-F2:

[0126] Step F1: for each image to be processed, extracting color channel information of the same color channel corresponding to each pixel from the fourth image block in each image to be processed.

[0127] Step F2: obtaining a second image result based on different color channel information correspondingly extracted from the fourth image blocks in each to-be-processed image, wherein the fourth image blocks in different to-be-processed images respectively extract color channel information of different color channels.

[0128] In an optional example, when a reference mark object is included in the fourth image block, obtaining a second image result based on different color channel information extracted from the fourth image blocks in each image to be processed may include the following steps: combining the fourth image block containing the reference mark object in each image to be processed with the color channel information extracted from the fourth image block in each image to be processed to obtain an image processing result for each image to be processed; and using the image processing results of each image to be processed as the second image result.

[0129] In another optional example, when the fourth image block includes a reference marker object, obtaining a second image result based on different color channel information extracted from the fourth image blocks in each image to be processed may include the following steps: merging the different color channel information extracted from the fourth image blocks in each image to be processed to obtain a color channel information merging result, wherein the different color channel information is merged in such a way that different color channel information from pixels at the same position is merged; merging the fourth image block in each image to be processed that includes the reference marker object with the color channel information merging result to obtain a second image result.

[0130] See also Figure 4c In order to restore the original scenes of each image to be processed in the image group to be processed from the first image result in the future, a three-channel composite image of different scenes is remade. This synthesis can reduce file packaging consumption. Figure 2b and Figure 2c , the signal light block set of the first picture plus the R channel (A R ), but delete the part belonging to block set A; take the traffic light block set of the second picture and add the G channel (B G ), but delete the part belonging to block set B; take the signal light block set of the third picture and add the B channel (C B), but delete the part belonging to block set C. Combine these three images together, and the final composite image contains two channels for each pixel in the blocks other than the traffic lights, and nine channels for each pixel in the traffic light blocks.

[0131] See also Figure 2b and Figure 2c When there is a problem with the stored image and the original scene of each image to be processed in the image group to be processed needs to be restored, first take the block set A of the first composite image and the block set A of the second composite image. R + signal light block set, merged to form scene A image, this scene A image has both 3-channel color image - block set A, which contains the true color information of the vehicle, and 1-channel surrounding scene, reflecting the integrity of the scene; then, take block set B of the first composite image and block set B of the second composite image G + signal light block set, merged to form scene B image, this scene B image has both 3-channel color image - block set B, including the true color information of the vehicle, and 1-channel surrounding scene, reflecting the integrity of the scene; then, take the block set C of the first composite image and the block set C of the second composite image B + Traffic light block set, merged to form scene C image. This scene C image has both a 3-channel color image - block set C, which contains the true color information of the vehicle, and a 1-channel surrounding scene, reflecting the integrity of the scene.

[0132] Obviously, the above processing not only reflects the three complete scenes corresponding to the three locations of the vehicle violation, but also reflects the true color information of the vehicle itself and its vicinity. At the same time, the amount of stored data is greatly reduced: assuming that the image color information contained in each channel is S, the original data volume of each color image is 3S, and the total data volume of the three color images is 9S. In the actual construction survey process, in order to capture more vehicle information, the traffic lights usually occupy a smaller proportion of the image area. Taking the above figure as an example, the area occupied by the traffic light block set is one-seventh of the entire image, so the amount of data contained in the first composite image is , the amount of data contained in the second synthetic image is , then the total data volume of the two composite graphs is , reduced by nearly 88%. The smaller the proportion of the traffic light block set area, the more the data volume is reduced.

[0133] Optionally, the image segmentation and compression is completed by the storage node, which increases the service burden of the storage node. For further optimization, the camera completes the image segmentation and compression before sending the image group to the storage node. The details are as follows. The camera captures four red light running pictures and marks the close-up pictures with a special mark, such as T. The camera performs two rounds of processing on the three pictures that are not specially marked as in step 2, and does not perform special processing on the close-up pictures.

[0134] The technical solution of the embodiment of the present invention determines a group of images to be processed including images to be processed, each of which is a different captured image of a reference tracking object from the same field of view, and determines the reference image area corresponding to each image to be processed, each reference image area completely covers the reference tracking object and the reference marker object, and ensures that the reference tracking object and the reference marker object images can be stored completely to avoid losing key information. The first image result is obtained based on the third image block in the reference image area corresponding to each image to be processed, so as to present each third image block in the order of shooting time, which can not only clearly show the state change and position movement of the reference tracking object at different time points, but also reduce the amount of data reflecting the location area of ​​the reference tracking object by nearly half, which can save storage space, improve transmission efficiency, reduce the requirements for storage devices and network bandwidth, and fully reflect the true color information of the reference tracking object itself. However, the second image result is obtained based on the fourth image block in the reference image area corresponding to each image to be processed, and the fourth image block that does not contain the reference tracking object is added to different color channels respectively, so that the background information of different images can be distinguished and integrated, and the environmental background of the reference tracking object can be better analyzed. At the same time, the detailed information near the reference tracking object is retained, so that the details of the surrounding environment can be presented, providing more detailed content for subsequent image processing and analysis.

[0135] Figure 5 A schematic diagram of the structure of an efficient storage device provided in an embodiment of the present invention. The embodiment of the present invention is suitable for efficiently storing multiple mutually related images to be processed. The efficient storage device can be implemented in the form of software and / or hardware, and optionally, can be implemented by an electronic device, which can be a mobile terminal, a PC or a server, etc.

[0136] like Figure 5 As shown, the efficient storage device provided in this embodiment may include the following:

[0137] A first determination module 510 is used to determine a to-be-processed image group, wherein the to-be-processed image group includes at least two to-be-processed images, each of which is a different captured image of a reference tracking object from a captured image at the same field of view angle;

[0138] A second determining module 520 is used to determine a reference image region corresponding to each image to be processed, each of the reference image regions can completely cover the reference tracking object and the reference marker object included in the image to be processed, the reference image region is a local image region in the image to be processed, and the reference image region is formed according to at least two image blocks of the same shape and size;

[0139] A first storage module 530 is used to obtain and store a first image result based on a third image block in a reference image area corresponding to each image to be processed, wherein the third image block includes a reference tracking object, and the first image result is a composite image that presents each third image block in sequence according to the shooting time sequence of each image to be processed;

[0140] The second storage module 540 is used to obtain and store a second image result based on the fourth image block in the reference image area corresponding to each image to be processed, wherein the fourth image block does not contain a reference tracking object, the third image block and / or the fourth image block includes a reference marker object, and the second image result includes image information formed by adding the fourth image blocks corresponding to each image to be processed to different color channels respectively.

[0141] On the basis of the above embodiment, optionally, at least two images to be processed in each of the groups of images to be processed include at least a first image to be processed, a second image to be processed and a third image to be processed, the first image to be processed being a captured image when the traffic light indicates a no-traffic phase and the reference tracking object is approaching the stop line at the traffic intersection but has not reached the stop line at the traffic intersection, the second image to be processed being a captured image when the traffic light indicates a no-traffic phase and the reference tracking object has crossed the stop line at the traffic intersection, and the third image to be processed being a captured image when the traffic light indicates a no-traffic phase and the reference tracking object continues to move forward in the direction of travel relative to the position of the second image to be processed.

[0142] Based on the above embodiment, optionally, determining the reference image region corresponding to each to-be-processed image includes:

[0143] Determine a reference selection frame required for each image to be processed, wherein the reference selection frame is formed by aggregating a frame formed by at least two first image blocks and a frame formed by a second image block, wherein each first image block is an image block that contains at least a reference tracking object and / or a reference marking object among at least two image blocks pre-divided corresponding to the image to be processed, and the second image block is used to connect non-adjacent first image blocks to form a continuous whole;

[0144] According to the reference selection box required by each image to be processed, the reference image area corresponding to each image to be processed is determined from each image to be processed, the reference image area is a local image area screened out from the image to be processed according to the reference selection box mapped to the image to be processed, the reference image area can completely cover the reference tracking object and reference marker object included in the image to be processed, and the image block in the reference image area has the same shape and size as the image block pre-divided for the image to be processed.

[0145] On the basis of the above embodiments, optionally, each image to be processed is pre-divided into at least two image blocks of the same shape and size, and the position and size of the at least two image blocks pre-divided in each of the images to be processed are adjusted and determined according to the capture position area where the reference tracking object is located when the reference tracking object is captured, so that the image blocks containing the reference tracking object in each image to be processed do not overlap with each other in position.

[0146] Based on the above embodiment, optionally, determining the reference selection frame required for each image to be processed includes:

[0147] For each image to be processed, color comparison is performed based on color information corresponding to the reference tracking object and color information of each image block pre-divided in the image to be processed;

[0148] Based on the color comparison result, at least two image blocks pre-divided from the image to be processed include at least a first image block of a reference tracking object, so as to construct a reference selection box required for each image to be processed, and the similarity between the color information of the first image block and the color information corresponding to the reference tracking object is greater than a preset similarity.

[0149] On the basis of the above embodiment, optionally, according to the reference selection box required by each image to be processed, determining the reference image area corresponding to each image to be processed from each image to be processed includes:

[0150] The target frame in the reference selection frame mapped to each image to be processed is deleted to obtain the target selection frame required by each image to be processed, wherein the target frame is a frame that does not contain a target detection frame in the frames formed by each image block corresponding to the reference selection frame after the reference selection frame is controlled to move synchronously in each image to be processed, and the target frame will not destroy the continuous overall state of the frames formed by each image block corresponding to the reference selection frame after being deleted from the frames formed by each image block corresponding to the reference selection frame, wherein the target detection frame is a detection frame that tracks a reference tracking object and a reference marker object in the image to be processed respectively;

[0151] The target selection boxes mapped to the images to be processed are used to filter out reference image regions corresponding to the images to be processed from the images to be processed.

[0152] Based on the above embodiment, optionally, deleting the target frame in the reference selection frame mapped to each image to be processed to obtain the target selection frame required by each image to be processed includes:

[0153] Controlling the reference selection frames mapped to the images to be processed to synchronously perform reference movement operations in the images to be processed respectively; wherein the reference movement operation is to move the reference selection frames mapped to the images to be processed along a reference direction and a reference speed in the images to be processed while ensuring that all target detection frames are within the reference selection frame, and the reference direction corresponding to the reference movement operation includes at least one of the following: a direction of upward translation in the images to be processed, a direction of downward translation in the images to be processed, a direction of leftward translation in the images to be processed, and a direction of rightward translation in the images to be processed;

[0154] When it is detected that the reference side edge of the target detection frame overlaps with the reference side edge of the reference selection frame mapped to the image to be processed, the reference selection frame is stopped from synchronously performing reference movement operations in each image to be processed, wherein the reference side is the side opposite to the reference direction;

[0155] For the reference selection boxes mapped to each image to be processed, if it is detected that there is a target box in the box formed by each image block corresponding to the reference selection box mapped to each image to be processed, the target box is deleted from the box formed by each image block corresponding to the reference selection box, and the reference selection boxes mapped to each image to be processed with the target box deleted are re-merged to obtain the target selection boxes required by each image to be processed.

[0156] On the basis of the above embodiment, optionally, obtaining the first image result based on the third image block in the reference image area corresponding to each image to be processed includes:

[0157] According to the sequence of shooting time of each to-be-processed image, a reference image region corresponding to the to-be-processed image with the earliest shooting time is determined from each to-be-processed image;

[0158] According to the chronological order of shooting time of each image to be processed, the third image blocks in the remaining reference image areas corresponding to each image to be processed, except for the reference image area corresponding to the image to be processed with the earliest shooting time, are superimposed on the reference image area corresponding to the image to be processed with the earliest shooting time to perform image synthesis, so that the third image blocks in the reference image areas corresponding to each image to be processed can be presented in the chronological order of shooting time of each image to be processed in the first image result after image synthesis.

[0159] On the basis of the above embodiment, optionally, obtaining a second image result based on a fourth image block in a reference image area corresponding to each image to be processed includes:

[0160] For each image to be processed, extracting color channel information of the same color channel corresponding to each pixel from the fourth image block in each of the images to be processed;

[0161] The second image result is obtained based on the different color channel information correspondingly extracted from the fourth image blocks in each of the images to be processed, and the fourth image blocks in different images to be processed respectively extract color channel information of different color channels.

[0162] On the basis of the above embodiment, optionally, when the fourth image block includes a reference mark object, obtaining a second image result based on different color channel information correspondingly extracted from the fourth image blocks in each of the images to be processed includes:

[0163] Combining the fourth image block containing the reference mark object in each of the images to be processed with the color channel information correspondingly extracted from the fourth image block in each of the images to be processed, to obtain an image processing result for each of the images to be processed;

[0164] The image processing results of each image to be processed are used as the second image results.

[0165] On the basis of the above embodiment, optionally, when the fourth image block includes a reference mark object, obtaining a second image result based on different color channel information correspondingly extracted from the fourth image blocks in each of the images to be processed includes:

[0166] Merging the different color channel information extracted from the fourth image blocks in the images to be processed to obtain a color channel information merging result, wherein the different color channel information is merged so as to merge the different color channel information of pixels at the same position;

[0167] The fourth image block containing the reference mark object in each of the to-be-processed images is combined with the color channel information combination result to obtain a second image result.

[0168] The technical solution provided by the embodiment of the present invention determines a group of images to be processed including images to be processed, each of which is a different captured image of a reference tracking object from the same field of view, and determines the reference image area corresponding to each image to be processed, each reference image area completely covers the reference tracking object and the reference marker object, and ensures that the reference tracking object and the reference marker object images can be stored completely to avoid losing key information. The first image result is obtained based on the third image block in the reference image area corresponding to each image to be processed, so as to present each third image block in the order of shooting time, which can not only clearly show the state change and position movement of the reference tracking object at different time points, but also reduce the amount of data reflecting the location area of ​​the reference tracking object by nearly half, which can save storage space, improve transmission efficiency, reduce the requirements for storage devices and network bandwidth, and fully reflect the true color information of the reference tracking object itself. However, the second image result is obtained based on the fourth image block in the reference image area corresponding to each image to be processed, and the fourth image block that does not contain the reference tracking object is added to different color channels respectively, so that the background information of different images can be distinguished and integrated, and the environmental background of the reference tracking object can be better analyzed. At the same time, the detailed information near the reference tracking object is retained, so that the details of the surrounding environment can be presented, providing more detailed content for subsequent image processing and analysis.

[0169] The high-efficiency storage device provided in the embodiment of the present invention can execute the high-efficiency storage method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the high-efficiency storage method.

[0170] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0171] Figure 6 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 6 , which shows an electronic device (eg Figure 6The terminal device in the embodiment of the present invention may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0172] like Figure 6 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An edit / output (I / O) interface 605 is also connected to the bus 604.

[0173] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0174] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present invention are executed.

[0175] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

[0176] The electronic device provided in the embodiment of the present invention and the efficient storage method provided in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0177] An embodiment of the present invention provides a computer storage medium on which a computer program is stored. When the program is executed by a processor, the efficient storage method provided by the above embodiment is implemented.

[0178] It should be noted that the computer-readable medium of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0179] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0180] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0181] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: determines a group of images to be processed, wherein the group of images to be processed includes at least two images to be processed, and each of the images to be processed is a different captured image of a capture screen from the same field of view angle for a reference tracking object; determines a reference image area corresponding to each image to be processed, and each of the reference image areas can completely cover the reference tracking object and the reference marker object included in the image to be processed; obtains and stores a first image result based on a third image block in the reference image area corresponding to each image to be processed, wherein the third image block includes the reference tracking object, and the first image result is a composite image that presents each third image block in sequence according to the shooting time sequence of each image to be processed; obtains and stores a second image result based on a fourth image block in the reference image area corresponding to each image to be processed, wherein the fourth image block does not include the reference tracking object, and the third image block and / or the fourth image block include the reference marker object, and the second image result includes image information formed by adding the fourth image block corresponding to each image to be processed to different color channels.

[0182] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0183] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0184] The units involved in the embodiments of the present invention may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0185] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0186] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0187] The above description is only a preferred embodiment of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present invention (but not limited to) to form a technical solution.

[0188] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present invention. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0189] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. An efficient storage method, characterized in that: The method comprises: Determine an image group to be processed, wherein the image group to be processed is composed of a plurality of images to be processed that have mutual information reference when storing images, and the plurality of images to be processed in the image group to be processed are polled and stored by a storage node in units of the image group to be processed, and the image group to be processed includes at least two images to be processed, and each of the images to be processed is a different captured image of a captured picture from the same field of view angle for a reference tracking object; Determine a reference image region corresponding to each image to be processed, each of the reference image regions can completely cover a reference tracking object and a reference marker object included in the image to be processed, the reference image region is a local image region in the image to be processed, and the reference image region is formed according to at least two image blocks of the same shape and size; Obtaining and storing a first image result based on a third image block in a reference image area corresponding to each image to be processed, wherein the third image block includes a reference tracking object, and the first image result is a composite image that presents each third image block in sequence according to the shooting time sequence of each image to be processed; A second image result is obtained and stored based on a fourth image block in a reference image area corresponding to each image to be processed, wherein the fourth image block does not contain a reference tracking object, the third image block and / or the fourth image block includes a reference marker object, and the second image result includes image information formed by adding the fourth image blocks corresponding to each image to be processed to different color channels respectively.

2. The method according to claim 1, characterized in that Determine the reference image region corresponding to each image to be processed, including: Determine a reference selection frame required for each image to be processed, wherein the reference selection frame is formed by aggregating a frame formed by at least two first image blocks and a frame formed by a second image block, wherein each first image block is an image block that contains at least a reference tracking object and / or a reference marking object among at least two image blocks pre-divided corresponding to the image to be processed, and the second image block is used to connect non-adjacent first image blocks to form a continuous whole; According to the reference selection box required by each image to be processed, the reference image area corresponding to each image to be processed is determined from each image to be processed, the reference image area is a local image area screened out from the image to be processed according to the reference selection box mapped to the image to be processed, the reference image area can completely cover the reference tracking object and reference marker object included in the image to be processed, and the image block in the reference image area has the same shape and size as the image block pre-divided for the image to be processed.

3. The method according to claim 2, characterized in that Each image to be processed is pre-divided into at least two image blocks of the same shape and size. The position and size of the at least two image blocks pre-divided in each of the images to be processed are adjusted and determined based on the capture position area where the reference tracking object is located when the reference tracking object is captured, so that the image blocks containing the reference tracking object in each of the images to be processed do not overlap with each other in position.

4. The method according to claim 2, characterized in that: According to the reference selection boxes required by the images to be processed, the reference image regions corresponding to the images to be processed are determined from the images to be processed, including: The target frame in the reference selection frame mapped to each image to be processed is deleted to obtain the target selection frame required by each image to be processed, wherein the target frame is a frame that does not contain a target detection frame in the frames formed by each image block corresponding to the reference selection frame after the reference selection frame is controlled to move synchronously in each image to be processed, and the target frame will not destroy the continuous overall state of the frames formed by each image block corresponding to the reference selection frame after being deleted from the frames formed by each image block corresponding to the reference selection frame, wherein the target detection frame is a detection frame that tracks a reference tracking object and a reference marker object in the image to be processed respectively; The target selection boxes mapped to the images to be processed are used to filter out reference image regions corresponding to the images to be processed from the images to be processed.

5. The method according to claim 4, characterized in that The target frame in the reference selection frame mapped to each image to be processed is deleted to obtain the target selection frame required by each image to be processed, including: Controlling the reference selection frames mapped to the images to be processed to synchronously perform reference movement operations in the images to be processed respectively; wherein the reference movement operation is to move the reference selection frames mapped to the images to be processed along a reference direction and a reference speed in the images to be processed while ensuring that all target detection frames are within the reference selection frame, and the reference direction corresponding to the reference movement operation includes at least one of the following: a direction of upward translation in the images to be processed, a direction of downward translation in the images to be processed, a direction of leftward translation in the images to be processed, and a direction of rightward translation in the images to be processed; When it is detected that the reference side edge of the target detection frame overlaps with the reference side edge of the reference selection frame mapped to the image to be processed, the reference selection frame is stopped from synchronously performing reference movement operations in each image to be processed, wherein the reference side is the side opposite to the reference direction; For the reference selection boxes mapped to each image to be processed, if it is detected that there is a target box in the box formed by each image block corresponding to the reference selection box mapped to each image to be processed, the target box is deleted from the box formed by each image block corresponding to the reference selection box, and the reference selection boxes mapped to each image to be processed with the target box deleted are re-merged to obtain the target selection boxes required by each image to be processed.

6. The method according to claim 1, characterized in that Obtaining a first image result based on a third image block in a reference image region corresponding to each image to be processed includes: According to the sequence of shooting time of each to-be-processed image, a reference image region corresponding to the to-be-processed image with the earliest shooting time is determined from each to-be-processed image; According to the chronological order of shooting time of each image to be processed, the third image blocks in the remaining reference image areas corresponding to each image to be processed, except for the reference image area corresponding to the image to be processed with the earliest shooting time, are superimposed on the reference image area corresponding to the image to be processed with the earliest shooting time to perform image synthesis, so that the third image blocks in the reference image areas corresponding to each image to be processed can be presented in the chronological order of shooting time of each image to be processed in the first image result after image synthesis.

7. The method according to claim 1, characterized in that Obtaining a second image result based on a fourth image block in a reference image region corresponding to each image to be processed includes: For each image to be processed, extracting color channel information of the same color channel corresponding to each pixel from the fourth image block in each of the images to be processed; The second image result is obtained based on the different color channel information correspondingly extracted from the fourth image blocks in each of the images to be processed, and the fourth image blocks in different images to be processed respectively extract color channel information of different color channels.

8. An efficient storage device, characterized in that: The device comprises: A first determination module is used to determine a to-be-processed image group, wherein the to-be-processed image group is composed of a plurality of to-be-processed images that have mutual information reference when storing images, wherein a plurality of to-be-processed images in the to-be-processed image group are polled and stored by a storage node in units of a to-be-processed image group, wherein the to-be-processed image group includes at least two to-be-processed images, and each of the to-be-processed images is a different captured image of a captured screen from the same field of view angle for a reference tracking object; A second determination module is used to determine a reference image region corresponding to each image to be processed, each of the reference image regions can completely cover the reference tracking object and the reference marker object included in the image to be processed, the reference image region is a local image region in the image to be processed, and the reference image region is formed according to at least two image blocks of the same shape and size; A first storage module, configured to obtain and store a first image result based on a third image block in a reference image area corresponding to each image to be processed, wherein the third image block includes a reference tracking object, and the first image result is a composite image that presents each third image block in sequence according to the shooting time sequence of each image to be processed; A second storage module is used to obtain and store a second image result based on a fourth image block in a reference image area corresponding to each image to be processed, wherein the fourth image block does not contain a reference tracking object, the third image block and / or the fourth image block includes a reference marker object, and the second image result includes image information formed by adding the fourth image blocks corresponding to each image to be processed to different color channels respectively.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the efficient storage method described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the efficient storage method according to any one of claims 1 to 7 when executed by a computer processor.

Images